Conference PaperPDF Available

InVeRo: Making Semantic Role Labeling Accessible with Intelligible Verbs and Roles

Authors:

Abstract and Figures

Semantic Role Labeling (SRL) is deeply dependent on complex linguistic resources and sophisticated neural models, which makes the task difficult to approach for non-experts. To address this issue we present a new platform named Intelligible Verbs and Roles (InVeRo). This platform provides access to a new verb resource, VerbAtlas, and a state-of-the-art pre-trained implementation of a neural, span-based architecture for SRL. Both the resource and the system provide human-readable verb sense and semantic role information, with an easy to use Web interface and RESTful APIs available at http://nlp.uniroma1.it/invero.
Content may be subject to copyright.
InVeRo: Making Semantic Role Labeling Accessible
with Intelligible Verbs and Roles
Simone Conia1,Fabrizio Brignone2,Davide Zanfardino2, and Roberto Navigli1
1Sapienza NLP Group, Department of Computer Science, Sapienza University of Rome
2Babelscape, Italy
lastname@di.uniroma1.it, lastname@babelscape.com
Abstract
Semantic Role Labeling (SRL) is deeply de-
pendent on complex linguistic resources and
sophisticated neural models, which makes the
task difficult to approach for non-experts. To
address this issue we present a new platform
named Intelligible Verbs and Roles (InVeRo).
This platform provides access to a new verb
resource, VerbAtlas, and a state-of-the-art pre-
trained implementation of a neural, span-based
architecture for SRL. Both the resource and
the system provide human-readable verb sense
and semantic role information, with an easy to
use Web interface and RESTful APIs available
at http://nlp.uniroma1.it/invero.
1 Introduction
Since its introduction (Gildea and Jurafsky,2002),
Semantic Role Labeling (SRL) has been recog-
nized as a key task to enable Natural Language Un-
derstanding in that it aims at explicitly answering
the "Who did What to Whom, When and Where?"
question by identifying and labeling the predicate-
argument structure of a sentence, namely, the actors
that take part in the scenario outlined by a predicate.
In fact, SRL has already proven to be useful in a
wide range of downstream tasks, including Ques-
tion Answering (Shen and Lapata,2007;He et al.,
2015), Information Extraction (Christensen et al.,
2011), Situation Recognition (Yatskar et al.,2016),
Machine Translation (Marcheggiani et al.,2018),
and Opinion Role Labeling (Zhang et al.,2019).
Unfortunately, the integration of SRL knowl-
edge into downstream applications has often been
hampered and slowed down by the intrinsic com-
plexity of the task itself (Navigli,2018). Indeed,
SRL is strongly intertwined with elaborate linguis-
tic theories, as identifying and labeling predicate-
argument relations requires well-defined predicate
sense and semantic role inventories such as the
popular PropBank (Palmer et al.,2005), VerbNet
(Kipper-Schuler,2005), or FrameNet (Baker et al.,
1998). The linguistic intricacies of such resources
may, however, dishearten and turn away new prac-
titioners. Regardless of which linguistic resource is
used in the task, to further complicate the situation
SRL has been usually divided into four subtasks
– predicate identification, predicate sense disam-
biguation, argument identification and argument
classification – but, to the best of our knowledge,
recent state-of-the-art systems do not address all
these four subtasks simultaneously without relying
on external systems (Swayamdipta et al.,2017;He
et al.,2018;Strubell et al.,2018;He et al.,2019).
Therefore, obtaining predicate sense and semantic
role annotations necessitates the tedious orchestra-
tion of multiple automatic systems, which in its
turn further complicates the use of SRL in prac-
tice and in semantics-first approaches to NLP more
generally.
In this paper, we present InVeRo (Intelligibile
Verbs and Roles), an online platform designed to
tackle the aforementioned issues and make Seman-
tic Role Labeling accessible to a broad audience.
InVeRo brings together resources and tools to per-
form human-readable SRL, and it accomplishes
this by using the intelligible verb senses and se-
mantic roles of a recently proposed resource named
VerbAtlas (Di Fabio et al.,2019) and exploiting
them to annotate sentences with high performance.
In more detail, the InVeRo platform includes:
a Resource API to obtain linguistic informa-
tion about the verb senses and semantic roles
in VerbAtlas.
a Model API to effortlessly annotate sentences
using a state-of-the-art end-to-end pretrained
model for span-based SRL.
a Web interface where users can easily query
linguistic information and automatically an-
notate sentences on-the-go without having to
write a single line of code.
Notably, InVeRo also takes advantage of PropBank
to get the best of both worlds, and provides an-
notations according to both resources, enabling
comparability and fostering integration.
2 The InVeRo Platform
The InVeRo platform aims at making SRL more
approachable to a wider audience, not only in or-
der to promote advances in the area of SRL itself,
but also to encourage the integration of semantics
into other fields of NLP. The two main barriers to
this objective are the complexity of i) the linguistic
resources used in SRL which are, however, indis-
pensable for the definition of the task itself, and ii)
the complexity of the recently proposed techniques.
Section 2.1 explains how InVeRo takes advan-
tage of the intelligible verb senses and semantic
roles of VerbAtlas to gently introduce non-expert
users to SRL, while Section 2.2 details how the
InVeRo model for SRL can make semantic role
annotations accessible to everyone.
2.1 Intelligible Verb Senses and Roles
One of the most contentious points of discussion in
SRL is how to formalize predicate-argument struc-
tures, that is, the semantic roles that actors can
play in a scenario defined by a predicate. Prop-
Bank (Palmer et al.,2005), one of the most popular
predicate-argument structure inventories, uses an
enumerative approach where each predicate sense
has a possibly different roleset, e.g., for the predi-
cate make, the sense make.01 (as in “making a prod-
uct”) bears the semantic roles ARG 0(creator), ARG 1
(creation), ARG 2(created from) and ARG 3(benefi-
ciary), whereas make.02 (as in “cause to be”) bears
only ARG 0(impeller) and ARG 1(impelled). This
exhaustive approach, however, requires an expert
linguist to tell which roles share similar seman-
tics across senses (e.g., AR G0is an agent in both
make.01 and make.02) and which do not (e.g., ARG1
is a product in make.01 but a result in make.02).
On the other hand, VerbAtlas (Di Fabio et al.,
2019), a recently proposed predicate-argument
structure inventory, in contrast to the enumerative
approach of PropBank and the thousands of frame-
specific roles of FrameNet, adopts a small set of ex-
plicit and intelligible semantic roles (AGE NT,PROD-
UCT,RESU LT,DES TIN ATION ,
. . .
,THE ME) inspired by
VerbNet (Kipper-Schuler,2005). As a result, in
VerbAtlas, whenever two predicate senses can bear
the same semantic role, the semantics of this role
is coherent across the two predicate senses by defi-
nition, resulting in readable labels for non-expert
users. VerbAtlas also clusters predicate senses into
so-called frames (COO K,DRINK,HIT, etc.) inspired
by FrameNet (Baker et al.,1998), with the idea
that senses sharing similar semantic behavior lie in
the same frame. For non-expert users, this organi-
zation has the added advantage of explicitly link-
ing predicate senses that are otherwise unrelated,
like make.01 and create.01 in PropBank which, in-
stead, are part of the same frame MOU NT-A SSEMB LE-
PROD UCE in VerbAtlas and, therefore, also share the
same semantic roles. In a bid to make SRL more
accessible, the InVeRo platform adopts the intelli-
gible verb senses and semantic roles of VerbAtlas.
2.2 An All-in-One Solution for SRL
As already mentioned in Section 1, the traditional
SRL pipeline consists of four main steps: predicate
identification, predicate sense disambiguation, ar-
gument identification and argument classification.
While some of the above steps are considered easier
than others, each of them features distinct peculiar-
ities, which has driven recent works to focus on
improving only specific aspects of the entire SRL
pipeline. Instead, little attention has been paid to
systems that can tackle all the above-mentioned
steps at the same time. As a result, anyone wishing
to take advantage of SRL annotations in another
NLP task has to choose, mix and match multiple
automatic systems in order to obtain sentences fully
annotated with predicate sense and semantic role
labels. Understandably, this has been a major de-
terrent for the integration of semantics into down-
stream applications.
As part of the InVeRo platform, not only do
we introduce an all-in-one model that addresses
the complete SRL pipeline with a single forward
pass, but we also make this model available through
a Web interface to let everyone label sentences
with SRL annotations without the need to install
any software. In other words, a user only has to
provide a raw text sentence; the InVeRo all-in-one
model for SRL takes care of the rest, making the
predicate sense and role labeling process accessible
and effortless.
Model Design.
The InVeRo all-in-one system for
SRL is based on the ideas put forward by He et al.
(2018) in that, unlike other works that used word-
level BIO tagging schemes to label arguments (He
et al.,2017;Strubell et al.,2018;Tan et al.,2018),
it directly models span-level features. In particular,
we follow He et al. (2018) by letting the neural
model learn span-level representations from the
word-level representations of the span start and
span end words, while also adding a span-length
specific trainable embedding. More formally, the
span representation
sij
from word
i
to word
j
is
obtained as follows:
sij =Ws(ew
iew
jel
ji) + bs
where
ew
i
and
ew
j
are the word representations of
start and end of the span,
el
ji
is the span length
embedding, and is the concatenation operation.
However, our approach features a few key dif-
ferences that set the InVeRo model apart from the
aforementioned works. First, it creates contextu-
alized word representations from the inner states
of BERT (
bert-base-cased
), a recent language
model trained on massive amounts of textual data
(Devlin et al.,2018). Differently from the recent
work of Shi and Lin (2019), our model takes ad-
vantage of the topmost four layers of BERT and
directly builds a word representation from its sub-
word representations, similarly to Bevilacqua and
Navigli (2020). More formally, given the BERT
representations
hk
ij
at layer
k
of the
mi
subwords
wij in word wi, with 1jmi:
cij =h1
ij h2
ij h3
ij h4
ij
c0
ij =ReLU(Wccij +bc)
ew
i=1
miX
j
c0
ij
Second, in contrast to other span-based SRL sys-
tems, our model integrates predicate disambigua-
tion as an additional objective in a multitask fash-
ion (Caruana,1997). Third, our model is trained to
jointly learn to label sentences with both VerbAtlas
and PropBank so as to exploit the complementary
knowledge of the two resources, and, at the same
time, provide a means to directly compare the pred-
icate sense and semantic role labels of two different
inventories for the same input sentences.1
Comparison with previous systems.
Over the
years, several SRL systems have been developed
1
We used the PropBank-to-VerbAtlas mappings avail-
able at
http://verbatlas.org/download
to remap
CoNLL-2012.
and made available as prepackaged downloads, e.g.
SENNA
2
, or as online demos, e.g., AllenNLP’s
SRL demo
3
. However, recent BERT-based online
systems, such as AllenNLP’s SRL demo, do not
perform predicate sense disambiguation (in addi-
tion to predicate identification, argument identi-
fication and argument classification), which is a
crucial step in SRL, especially when considering
that the PropBank roles ARG 0,ARG 1, through ARG 5
become meaningful only if they are associated with
a PropBank predicate sense (see Section 2.1).
Results.
Thanks to the use of contextualized
word representations from BERT, the joint exploita-
tion of two complementary linguistic resources for
SRL, and the introduction of a predicate sense dis-
ambiguation layer, our model achieves 84.0% in
F
1
score in the standard argument identification
and classification test split of the CoNLL-2012
dataset (Pradhan et al.,2012), significantly outper-
forming the previous state of the art among end-
to-end models, currently represented by Strubell
et al. (2018) with a 0.6% absolute improvement
in F
1
score
4
(84.0% against 83.4%). We note that
this measure does not take into account the perfor-
mance on predicate sense disambiguation, where
our system achieves 86.1% in F
1
score, which is
a significant absolute improvement (+5.7%) over
the most-frequent-sense strategy (86.1% against
80.4%).
3 The InVeRo APIs
To foster the integration of semantics into a wider
range of applications, the InVeRo platform intro-
duces a set of RESTful APIs
5
that offer i) easy-to-
use abstractions to query resource-specific informa-
tion in VerbAtlas (Section 3.1), and ii) out-of-the-
box predicate and semantic role annotations from
a state-of-the-art pretrained model (Section 3.2).
3.1 Resource API
The Resource API provides a RESTful interface to
easily link predicate-level information, e.g., predi-
cate lemmas and/or predicate senses, to VerbAtlas-
specific features, e.g., frames and semantic roles.
In particular:
2https://ronan.collobert.com/senna
3https://demo.allennlp.org/
semantic-role- labeling
4Score computed with the official CoNLL-2005 script.
5http://nlp.uniroma1.it/invero/
api-documentation
the
/predicate
endpoint exposes functionali-
ties to obtain frame-level information start-
ing from a predicate lemma or a synset
from WordNet 3.0 (Fellbaum et al.,1998) or
BabelNet 4.0 (Navigli and Ponzetto,2012);
the
/frame
endpoint exposes functionalities
to retrieve, for a given frame, its Predicate Ar-
gument Structure, and the WordNet/BabelNet
synsets belonging to this frame.
Also included is a manually-curated PropBank-to-
VerbAtlas alignment to remap existing corpora like
the CoNLL-2009 and CoNLL-2012 datasets. In
particular:
the
/align/sense
endpoint returns, for a
given PropBank predicate sense, its corre-
sponding VerbAtlas frame, i.e., the VerbAt-
las frame that generalizes the given PropBank
predicate sense;
the
/align/roles
endpoint returns, for a
given PropBank predicate sense, e.g., aim.01,
the alignment of each role in the PropBank ar-
gument structure of the given predicate sense
to a VerbAtlas role, e.g., AR G0
AGE NT,AR G1
THE ME, and so on.
The online documentation provides an overview of
the accepted parameters at the endpoints available
in the Resource API.
3.2 Model API
To encourage the integration of SRL into down-
stream applications, the Model API offers a simple
solution for out-of-the-box role labeling by provid-
ing an interface to a full end-to-end state-of-the-art
pretrained model. Unlike most currently available
models which focus on specific aspects of the entire
SRL task, our solution jointly addresses in a single
forward pass the whole traditional SRL pipeline,
namely, i) predicate identification, ii) predicate
sense disambiguation, iii) argument identification,
and iv) argument classification. Furthermore, our
model is fully self-contained as it does not require
any of the additional linguistic information, from
lemmatization to part-of-speech tags and syntac-
tic parse trees, that are usually exploited by many
systems. Our Model API is:
Easy to use:
an end user avoids the struggle
of mixing and matching a set of automatic
systems where each system independently ad-
dresses a different part of the SRL pipeline;
Fully self-contained:
the only input to the
underlying model is a raw text sentence, drop-
ping any dependency on external preprocess-
ing tools;
State-of-the-Art:
the underlying model car-
ries out SRL with high performances on the
standard CoNLL-2012 benchmark dataset.
Usage.
The Model API exposes a single endpoint
named
/model/
which accepts
GET
requests with a
single parameter named
sentence
containing the
raw text sentence to label with semantic role annota-
tions. The Model API returns a
JSON
response that
contains, for each predicate it identifies in the sen-
tence, the semantic role that each argument plays
with respect to the identified predicate. For exam-
ple, the response for the sentence “Eliminating the
income tax will benefit peasants" contains:
[{
"tokenIndex":0,
...
},{
"tokenIndex":5,
"verbatlas":{
"frameName":"HELP_HEAL_CARE_CURE",
"roles":[
{"role":"agent","score":0.89,"span":[0,4]},
{"role":"beneficiary","score":1.,"span":[6,7]}
]
},
"propbank":{
"frameName":"benefit.01",
"roles":[
{"role":"ARG0","score":0.97,"span":[0,4]},
{"role":"ARG1","score":1.00,"span":[6,7]}
]
},
}]
Our Model API also supports the more popular
PropBank predicate sense and semantic role labels
so as to provide a direct comparison with VerbAtlas
and promote synergistic approaches that exploit
both inventories to advance SRL.
4 The InVeRo User Interface
Like many other linguistic resources in SRL, Ver-
bAtlas may be daunting for inexperienced practi-
tioners who may still face difficulties in finding
their way with the formalisms defined in a linguis-
tic resource for SRL. On top of the previously de-
scribed APIs (Section 3) and in an effort to make
VerbAtlas easier to interact with, the InVeRo plat-
form includes a public-facing Web interface that
provides a user-friendly environment to explore not
only the functionalities offered by the resource, but
Figure 1: A look at the online interface when a user searches for resource-specific information about VerbAtlas.
The user can a) search for a frame name, as in the Figure, or an individual predicate. The interface displays
b) all the predicates belonging to the same frame, with each predicate c) directly linked to BabelNet. The right
side displays the d) selected predicate with e) its WordNet gloss, f) the semantic roles of its predicate-argument
structure, and g) the selectional preferences of each role.
Figure 2: A look at the online interface when a user inserts a sentence in the search bar. The system uses a
pretrained model to display all the information of all the steps of a traditional SRL pipeline: predicate identification,
predicate sense disambiguation, argument identification and argument classification.
Figure 3: The interface can seamlessly switch between VerbAtlas and PropBank labels with a single click (the
switch button at the top-right). Here we show the same sentence as in Figure 2but labeled with PropBank predicates
and roles, which enables comparison across the two annotation styles.
also to understand visually how an SRL system an-
notates a sentence in a live interactive demo. The
Web interface mirrors the functionalities of both the
Resource API and the Model API in a minimal uni-
fied view, letting users perform resource-specific
queries or annotate sentences wherever they are
without writing a single line of code.
Resource interface. Figure 1shows the Web in-
terface when a user inserts the name of a VerbAtlas
frame in the search bar. Notice that, since the inter-
face makes use of the Resource API, a user can also
search for other resource-specific information such
as individual predicates. Particular attention has
been given to the visualization of a VerbAtlas frame
(Figure 1, left side) which displays all the predi-
cate senses that share similar semantic behavior.
Each predicate sense is also conveniently linked to
BabelNet 4.0 (Navigli and Ponzetto,2012), a multi-
lingual knowledge graph where users can find more
information such as hypernyms, hyponyms, and se-
mantically related concepts. Equally important is
the visualization of a VerbAtlas predicate-argument
structure (Figure 1, right side) which displays all
the semantic roles that the currently selected predi-
cate/frame can bear in a sentence.
Model interface.
Figure 2shows, instead, the
online model interface when a user inserts a sen-
tence with its corresponding predicate sense and
semantic role labels from VerbAtlas. Notice how
the user can quickly switch between the VerbAtlas
and the PropBank predicate sense and semantic
role annotations with just a single click, so that the
two annotation styles can easily be compared one
with the other (Figures 2and 3). To the best of
our knowledge, this is the first online demo where
a neural model helps users visualize all the four
steps of the traditional SRL pipeline for two dif-
ferent linguistic resources for SRL, VerbAtlas and
PropBank, at the same time.
5 Conclusion and Future Work
Semantic Role Labeling is deeply dependent on
complex linguistic resources and elaborate neural
models: the combination of these two factors has
made Semantic Role Labeling (SRL) difficult to
approach for experts from other fields who are inter-
ested in exploring its integration into downstream
applications. In this paper, we aim at ameliorat-
ing both of the issues by presenting the InVeRo
platform. InVeRo features easy-to-use RESTful
APIs to effortlessy query VerbAtlas, a recently in-
troduced linguistic resource for SRL, and to trans-
parently use a pretrained state-of-the-art end-to-end
system for the recent VerbAtlas-style and the more
traditional PropBank-style approaches to SRL. No-
tably, the InVeRo system is fully self-contained
as it tackles all the steps of the traditional SRL
pipeline – predicate identification, predicate sense
disambiguation, argument identification, and argu-
ment classification – and it does not require ex-
ternal tools such as lemmatizers, part-of-speech
taggers or syntactic tree parsers: users just have to
provide a raw text sentence to obtain its correspond-
ing predicate and argument labels. Moreover, the
InVeRo platform includes an online Web interface
which repackages the APIs in a user-friendly envi-
ronment. Thanks to this interface, users can eas-
ily obtain human-readable linguistic information
about VerbAtlas, but also annotate entire sentences
on-the-go without the need to install any software.
InVeRo is a growing platform: in the future, we
plan to enhance our Model API by adding, along-
side the already available state-of-the-art span-
based model, the state-of-the-art dependency-based
model of Conia and Navigli (2020a), so that users
can easily switch between the two approaches and
choose the one that best suits their needs. Thanks to
BabelNet and recent advances in cross-lingual tech-
niques for tasks where semantics is crucial (Barba
et al.,2020;Blloshmi et al.,2020;Conia and Nav-
igli,2020b;Pasini,2020;Scarlini et al.,2020), we
also plan to provide support for multiple languages
to enable SRL integration into multilingual and
cross-lingual settings. We believe that the InVeRo
platform can make SRL more accessible to the
research community, and we look forward to the
development of semantics-first approaches in an
ever wider range of NLP applications.
Acknowledgments
The authors gratefully acknowledge
the support of the ERC Consolidator
Grant MOUSSE No. 726487 under
the European Union’s Horizon 2020
research and innovation programme.
This work was supported in part by the MIUR
under grant “Dipartimenti di eccellenza 2018-
2022” of the Department of Computer Science of
Sapienza University.
References
Collin F. Baker, Charles J. Fillmore, and John B. Lowe.
1998. The Berkeley FrameNet Project. In 36th An-
nual Meeting of the Association for Computational
Linguistics and 17th International Conference on
Computational Linguistics, COLING-ACL ’98, Au-
gust 10-14, 1998, Université de Montréal, Montréal,
Quebec, Canada. Proceedings of the Conference,
pages 86–90.
Edoardo Barba, Luigi Procopio, Niccolò Campol-
ungo, Tommaso Pasini, and Roberto Navigli. 2020.
MuLaN: Multilingual Label propagatioN for word
sense disambiguation. In Proceedings of the Twenty-
Ninth International Joint Conference on Artificial In-
telligence, IJCAI 2020, pages 3837–3844.
Michele Bevilacqua and Roberto Navigli. 2020. Break-
ing through the 80% glass ceiling: Raising the state
of the art in Word Sense Disambiguation by in-
corporating knowledge graph information. In Pro-
ceedings of the 58th Annual Meeting of the Asso-
ciation for Computational Linguistics, pages 2854–
2864, Online.
Rexhina Blloshmi, Rocco Tripodi, and Roberto Nav-
igli. 2020. XL-AMR: Enabling Cross-Lingual AMR
parsing with transfer learning techniques. In Pro-
ceedings of the 2020 Conference on Empirical Meth-
ods in Natural Language Processing, EMNLP 2020.
Rich Caruana. 1997. Multitask learning.Mach. Learn.,
28(1):41–75.
Janara Christensen, Mausam, Stephen Soderland, and
Oren Etzioni. 2011. An analysis of open infor-
mation extraction based on semantic role labeling.
In Proceedings of the 6th International Conference
on Knowledge Capture (K-CAP 2011), June 26-29,
2011, Banff, Alberta, Canada, pages 113–120.
Simone Conia and Roberto Navigli. 2020a. Bridg-
ing the gap in multilingual Semantic Role Labeling:
A language agnostic approach. In Proceedings of
the 28th International Conference on Computational
Linguistics, COLING 2020.
Simone Conia and Roberto Navigli. 2020b. Con-
ception: Multilingually-enhanced, human-readable
concept vector representations. In Proceedings of
the 28th International Conference on Computational
Linguistics, COLING 2020.
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and
Kristina Toutanova. 2018. BERT: pre-training of
deep bidirectional transformers for language under-
standing.arXiv preprint arXiv:1810.04805.
Andrea Di Fabio, Simone Conia, and Roberto Navigli.
2019. VerbAtlas: A novel large-scale verbal seman-
tic resource and its application to Semantic Role La-
beling. In Proceedings of the 2019 Conference on
Empirical Methods in Natural Language Processing
and the 9th International Joint Conference on Nat-
ural Language Processing, EMNLP-IJCNLP 2019,
Hong Kong, China, November 3-7, 2019, pages 627–
637.
Christiane Fellbaum et al. 1998. WordNet: An elec-
tronic database. MIT Press, Cambridge, MA.
Daniel Gildea and Daniel Jurafsky. 2002. Automatic
labeling of semantic roles.Comput. Linguistics,
28(3):245–288.
Luheng He, Kenton Lee, Omer Levy, and Luke Zettle-
moyer. 2018. Jointly predicting predicates and ar-
guments in neural semantic role labeling. In Pro-
ceedings of the 56th Annual Meeting of the Asso-
ciation for Computational Linguistics, ACL 2018,
Melbourne, Australia, July 15-20, 2018, Volume 2:
Short Papers, pages 364–369.
Luheng He, Kenton Lee, Mike Lewis, and Luke Zettle-
moyer. 2017. Deep semantic role labeling: What
works and what’s next. In Proceedings of the 55th
Annual Meeting of the Association for Computa-
tional Linguistics, ACL 2017, Vancouver, Canada,
July 30 - August 4, Volume 1: Long Papers, pages
473–483.
Luheng He, Mike Lewis, and Luke Zettlemoyer. 2015.
Question-answer driven semantic role labeling: Us-
ing natural language to annotate natural language. In
Proceedings of the 2015 Conference on Empirical
Methods in Natural Language Processing, EMNLP
2015, Lisbon, Portugal, September 17-21, 2015,
pages 643–653.
Shexia He, Zuchao Li, and Hai Zhao. 2019. Syntax-
aware multilingual semantic role labeling. In Pro-
ceedings of the 2019 Conference on Empirical Meth-
ods in Natural Language Processing and the 9th In-
ternational Joint Conference on Natural Language
Processing, EMNLP-IJCNLP 2019, Hong Kong,
China, November 3-7, 2019, pages 5349–5358.
Karin Kipper-Schuler. 2005. VerbNet: A broad-
coverage, comprehensive verb lexicon. University
of Pensylvania.
Diego Marcheggiani, Jasmijn Bastings, and Ivan Titov.
2018. Exploiting semantics in neural machine
translation with graph convolutional networks. In
Proceedings of the 2018 Conference of the North
American Chapter of the Association for Computa-
tional Linguistics: Human Language Technologies,
NAACL-HLT, New Orleans, Louisiana, USA, June 1-
6, 2018, Volume 2 (Short Papers), pages 486–492.
Roberto Navigli. 2018. Natural Language Understand-
ing: Instructions for (present and future) use. In
Proc. of IJCAI 2018, pages 5697–5702.
Roberto Navigli and Simone Paolo Ponzetto. 2012.
Babelnet: The automatic construction, evaluation
and application of a wide-coverage multilingual se-
mantic network.Artif. Intell., 193:217–250.
Martha Palmer, Paul R. Kingsbury, and Daniel Gildea.
2005. The Proposition Bank: An annotated corpus
of semantic roles.Comput. Linguistics, 31(1):71–
106.
Tommaso Pasini. 2020. The knowledge acquisition
bottleneck problem in multilingual Word Sense Dis-
ambiguation. In Proceedings of the Twenty-Ninth
International Joint Conference on Artificial Intelli-
gence, IJCAI 2020, pages 4936–4942.
Sameer Pradhan, Alessandro Moschitti, Nianwen Xue,
Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-
2012 Shared Task: Modeling Multilingual Unre-
stricted Coreference in OntoNotes. In Joint Confer-
ence on EMNLP and CoNLL - Shared Task, CoNLL
2012, pages 1–40, Stroudsburg, PA, USA.
Bianca Scarlini, Tommaso Pasini, and Roberto Nav-
igli. 2020. With more contexts comes better per-
formance: Contextualized sense embeddings for all-
round Word Sense Disambiguation. In Proceedings
of the 2020 Conference on Empirical Methods in
Natural Language Processing, EMNLP 2020.
Dan Shen and Mirella Lapata. 2007. Using semantic
roles to improve question answering. In EMNLP-
CoNLL 2007, Proceedings of the 2007 Joint Con-
ference on Empirical Methods in Natural Language
Processing and Computational Natural Language
Learning, June 28-30, 2007, Prague, Czech Repub-
lic, pages 12–21.
Peng Shi and Jimmy Lin. 2019. Simple BERT mod-
els for relation extraction and semantic role labeling.
arXiv preprint arXiv:1904.05255, abs/1904.05255.
Emma Strubell, Patrick Verga, Daniel Andor,
David Weiss, and Andrew McCallum. 2018.
Linguistically-informed self-attention for seman-
tic role labeling. In Proceedings of the 2018
Conference on Empirical Methods in Natural
Language Processing, Brussels, Belgium, October
31 - November 4, 2018, pages 5027–5038.
Swabha Swayamdipta, Sam Thomson, Chris Dyer, and
Noah A. Smith. 2017. Frame-semantic parsing
with softmax-margin segmental RNNs and a syn-
tactic scaffold.arXiv preprint arXiv:1706.09528,
abs/1706.09528.
Zhixing Tan, Mingxuan Wang, Jun Xie, Yidong Chen,
and Xiaodong Shi. 2018. Deep semantic role label-
ing with self-attention. In Proceedings of the Thirty-
Second AAAI Conference on Artificial Intelligence,
(AAAI-18), the 30th innovative Applications of Arti-
ficial Intelligence (IAAI-18), and the 8th AAAI Sym-
posium on Educational Advances in Artificial Intel-
ligence (EAAI-18), New Orleans, Louisiana, USA,
February 2-7, 2018, pages 4929–4936.
Mark Yatskar, Luke S. Zettlemoyer, and Ali Farhadi.
2016. Situation recognition: Visual semantic role
labeling for image understanding. In 2016 IEEE
Conference on Computer Vision and Pattern Recog-
nition, CVPR 2016, Las Vegas, NV, USA, June 27-30,
2016, pages 5534–5542.
Meishan Zhang, Peili Liang, and Guohong Fu. 2019.
Enhancing opinion role labeling with semantic-
aware word representations from semantic role la-
beling. In Proceedings of the 2019 Conference of the
North American Chapter of the Association for Com-
putational Linguistics: Human Language Technolo-
gies, NAACL-HLT 2019, Minneapolis, MN, USA,
June 2-7, 2019, Volume 1 (Long and Short Papers),
pages 641–646.
... Commentators describe how the game unfolds and how players interact, making football commentaries an interesting benchmark for learning grounded verb semantics from video. To understand how linguistic predicates relate to visual events in the dataset, we use the output of the state of the art semantic role labeller InVeRo 8 [9] as silver annotations (which has high accuracy in both predicate and argument prediction of 86.1% and 84%, respectively). The objective of this annotation step is to have a sense of how "situated" the collected data is. ...
... The embedding layer is fine-tuned during training. The encoder and decoder modules use bi-directional GRUs [7] with 256 units and 2 9 A typical movement which consists of the full back running behind the winger to receive the ball upfront. 10 Table 9: Statistics about the videos contained in the GOAL dataset. ...
... 10 Table 9: Statistics about the videos contained in the GOAL dataset. Figure 4: Distribution of the VerbAtlas predicative structures extracted by the InVeRo model [9]. ...
Preprint
Recent video+language datasets cover domains where the interaction is highly structured, such as instructional videos, or where the interaction is scripted, such as TV shows. Both of these properties can lead to spurious cues to be exploited by models rather than learning to ground language. In this paper, we present GrOunded footbAlL commentaries (GOAL), a novel dataset of football (or `soccer') highlights videos with transcribed live commentaries in English. As the course of a game is unpredictable, so are commentaries, which makes them a unique resource to investigate dynamic language grounding. We also provide state-of-the-art baselines for the following tasks: frame reordering, moment retrieval, live commentary retrieval and play-by-play live commentary generation. Results show that SOTA models perform reasonably well in most tasks. We discuss the implications of these results and suggest new tasks for which GOAL can be used. Our codebase is available at: https://gitlab.com/grounded-sport-convai/goal-baselines.
... This technique was crucial for pinpointing and designating the semantic roles associated with each component of the sentences. For SRL, the InVeRo semantic parser was utilized [3]. The synergy of these two methodologies enabled the thorough annotation of our corpus with both syntactic and semantic layers, which were integrated into the CS roles (e.g., who, and what doing). ...
Preprint
Full-text available
This paper presents an approach to enhancing Augmentative and Alternative Communication (AAC) systems by integrating Colourful Semantics (CS) with transformer-based language models specifically tailored for Brazilian Portuguese. We introduce an adapted BERT model, BERTptCS, which incorporates the CS framework for improved prediction of communication cards. The primary aim is to enhance the accuracy and contextual relevance of communication card predictions, which are essential in AAC systems for individuals with complex communication needs (CCN). We compared BERTptCS with a baseline model, BERTptAAC, which lacks CS integration. Our results demonstrate that BERTptCS significantly outperforms BERTptAAC in various metrics, including top-k accuracy, Mean Reciprocal Rank (MRR), and Entropy@K. Integrating CS into the language model improves prediction accuracy and offers a more intuitive and contextual understanding of user inputs, facilitating more effective communication.
... The process of semantic role labelling typically consists of predicate identification and its sense disambiguation, followed by identification of semantic roles and finally their labelling. The state-of-theart BERT models like AllenNLP's models (Gardner et al., 2018) or InVeRo (Conia et al., 2020) perform all mentioned subtasks except for predicate sense disambiguation which is missing. Ideally, the tool would use predicate senses to label semantic roles. ...
Conference Paper
Full-text available
This paper focuses on Predicate Sense Disambiguation (PSD) based on PropBank guidelines. Different approaches to this task have been proposed, from purely supervised or knowledge-based, to recently hybrid approaches that have shown promising results. We introduce one of the hybrid approaches-a PSD pipeline based on both supervised models and handcrafted rules. To train three supervised POS, DEP and POS DEP models we used syntactic features (lemma, part-of-speech tag, dependency parse) and semantic features (semantic role labels). These features enable per-token classification, which to be applied to unseen words, requires handcrafted rules to make predictions specifically for nouns in light verb constructions, unseen verbs and unseen phrasal verbs. Experiments were done on newly-developed dataset and the results show a token-level accuracy of 96% for the proposed PSD pipeline.
... Furthermore, we annotated part of the British English corpus of CHILDES with semantic roles for allowing its usage as a training dataset for fine-tuning PictoBERT to perform pictogram prediction based on a semantic structure, in an approach similar to Pereira et al. (2020). For doing so, we used InVeRo (Conia et al., 2020) and SLING (Ringgaard et al., 2017) as semantic parsers. We used InVeRo for predicate disambiguation to identify the sentence's predicates and its relative semantic frames. ...
Article
Augmentative and Alternative Communication (AAC) boards are essential tools for people with Complex Communication Needs (e.g., a person with down’s syndrome, autism, or cerebral palsy). These boards allow the construction of messages by arranging pictograms in sequence. In this context, a pictogram is a picture with a label that denotes an action, object, person, animal, or place. Predicting the next pictogram to be set in a sentence in construction is an essential feature for AAC boards to facilitate communication. Previous work in this task used n-gram statistical language models and knowledge bases. However, neural network literature suggests they can cope better with the task, and transformers-based models like BERT (Bidirectional Encoder Representations from Transformers) are revolutionizing this field. In this paper, we present PictoBERT, an adaptation of BERT for the next pictogram prediction task. We changed the BERT’s input embeddings to allow word-sense usage instead of words, considering that a word-sense represents a pictogram better than a simple word. The proposed model outperforms the n-gram models and knowledge bases. Besides, PictoBERT can be fine-tuned to adapt to different users’ needs, making transfer learning its main characteristic.
Thesis
Full-text available
Augmentative and Alternative Communication (AAC) systems assist individuals with com- plex communication needs to express themselves. Communication cards are a popular method used in AAC, where users select cards and arrange them in sequence to form a sentence. How- ever, the limited number of cards displayed and the need to navigate multiple pages or folders can hinder users’ communication ability. To overcome these barriers, various methods, such as vocabulary organization, color coding systems, motor planning, and predictive models, have been proposed to aid message authoring. Predictive models can suggest the most probable next cards based on prior input. Recent advancements in Artificial Intelligence (AI) and Machine Learning (ML) have shown potential for improving the accessibility and customization of AAC systems. This study proposes adapting large language models to communication card predic- tion in AAC systems to facilitate message authoring. The proposed method involves three main steps: 1) adapting a text corpus to the AAC domain by either converting it into a corpus of telegraphic sentences or incorporating features that enable the exploration of visual cues; 2) fine-tuning a transformer-based language model using the adapted corpus; and 3) replacing the language model decoder weights with an encoded representation of the user’s vocabulary to generate a probability distribution over the user’s vocabulary items during inference. The proposed method leverages that transformers-based language models, such as Bidirectional Encoder Representations from Transformers (BERT), share the weights of the input embed- dings layer with the decoder in the language modeling head. Therefore, the plug-and-play method can be used without additional training for zero-shot communication card prediction. The method was evaluated in English and Brazilian Portuguese using a zero-shot setting and a few-shot setting, where a small text corpus was used for fine-tuning. Additionally, the im- pact of incorporating additional features into the training sentences by labeling them with the Colourful Semantics structure was assessed. The results demonstrate that the proposed method’s models outperform models pre-trained for the task. Moreover, the results indicate that incorporating Colourful Semantics improves the accuracy of communication card predic- tion. Thus, the proposed method utilizes the transfer learning ability of transformers-based language models to facilitate message authoring in AAC systems in a low-effort setting.
Conference Paper
Full-text available
Notwithstanding the growing interest in cross-lingual techniques for Natural Language Processing , there has been a surprisingly small number of efforts aimed at the development of easy-to-use tools for cross-lingual Semantic Role Labeling. In this paper, we fill this gap and present InVeRo-XL, an off-the-shelf state-of-the-art system capable of annotating text with predicate sense and semantic role labels from 7 predicate-argument structure inventories in more than 40 languages. We hope that our system-with its easy-to-use RESTful API and Web interface-will become a valuable tool for the research community , encouraging the integration of sentence-level semantics into cross-lingual downstream tasks. InVeRo-XL is available online at http://nlp.uniroma1.it/invero.
Conference Paper
Full-text available
While cross-lingual techniques are finding increasing success in a wide range of Natural Language Processing tasks, their application to Semantic Role Labeling (SRL) has been strongly limited by the fact that each language adopts its own linguistic formalism, from PropBank for English to AnCora for Spanish and PDT-Vallex for Czech, inter alia. In this work, we address this issue and present a unified model to perform cross-lingual SRL over heterogeneous linguistic resources. Our model implicitly learns a high-quality mapping for different formalisms across diverse languages without resorting to word alignment and/or translation techniques. We find that, not only is our cross-lingual system competitive with the current state of the art but that it is also robust to low-data scenarios. Most interestingly, our unified model is able to annotate a sentence in a single forward pass with all the inventories it was trained with, providing a tool for the analysis and comparison of linguistic theories across different languages. We release our code and model at https://github.com/SapienzaNLP/unify-srl.
Conference Paper
Full-text available
To date, the most successful word, word sense, and concept modelling techniques have used large corpora and knowledge resources to produce dense vector representations that capture semantic similarities in a relatively low-dimensional space. Most current approaches, however, suffer from a monolingual bias, with their strength depending on the amount of data available across languages. In this paper we address this issue and propose Conception, a novel technique for building language-independent vector representations of concepts which places multilinguality at its core while retaining explicit relationships between concepts. Our approach results in high-coverage representations that outperform the state of the art in multilingual and cross-lingual Semantic Word Similarity and Word Sense Disambiguation, proving particularly robust on low-resource languages. Conception - its software and the complete set of representations - is available at https://github.com/SapienzaNLP/conception.
Conference Paper
Full-text available
Recent research indicates that taking advantage of complex syntactic features leads to favorable results in Semantic Role Labeling. Nonetheless, an analysis of the latest state-of-the-art multilingual systems reveals the difficulty of bridging the wide gap in performance between high-resource (e.g., English) and low-resource (e.g., German) settings. To overcome this issue, we propose a fully language-agnostic model that does away with morphological and syntactic features to achieve robustness across languages. Our approach outperforms the state of the art in all the languages of the CoNLL-2009 benchmark dataset, especially whenever a scarce amount of training data is available. Our objective is not to reject approaches that rely on syntax, rather to set a strong and consistent language-independent baseline for future innovations in Semantic Role Labeling. We release our model code and checkpoints at https://github.com/SapienzaNLP/multi-srl.
Conference Paper
Full-text available
Contextualized word embeddings have been employed effectively across several tasks in Natural Language Processing, as they have proved to carry useful semantic information. However, it is still hard to link them to structured sources of knowledge. In this paper we present ARES (context-AwaRe Embeddings of Senses), a semi-supervised approach to producing sense embeddings for the lexical meanings within a lexical knowledge base that lie in a space that is comparable to that of contextualized word vectors. ARES representations enable a simple 1-Nearest-Neighbour algorithm to outperform state-of-the-art models, not only in the English Word Sense Disambiguation task, but also in the multilingual one, whilst training on sense-annotated data in English only. We further assess the quality of our embeddings in the Word-in-Context task, where, when used as an external source of knowledge, they consistently improve the performance of a neural model, leading it to compete with other more complex architectures. ARES em-beddings for all WordNet concepts and the automatically-extracted contexts used for creating the sense representations are freely available at http://sensembert.org/ares.
Conference Paper
Full-text available
To date, the most successful word, word sense, and concept modelling techniques have used large corpora and knowledge resources to produce dense vector representations that capture semantic similarities in a relatively low-dimensional space. Most current approaches, however, suffer from a monolingual bias, with their strength depending on the amount of data available across languages. In this paper we address this issue and propose Conception, a novel technique for building language-independent vector representations of concepts which places multilinguality at its core while retaining explicit relationships between concepts. Our approach results in high-coverage representations that outperform the state of the art in multilingual and cross-lingual Semantic Word Similarity and Word Sense Disambiguation, proving particularly robust on low-resource languages. Conception - its software and the complete set of representations - is available at https://github.com/SapienzaNLP/conception.
Conference Paper
Full-text available
Recent research indicates that taking advantage of complex syntactic features leads to favorable results in Semantic Role Labeling. Nonetheless, an analysis of the latest state-of-the-art multilingual systems reveals the difficulty of bridging the wide gap in performance between high-resource (e.g., English) and low-resource (e.g., German) settings. To overcome this issue, we propose a fully language-agnostic model that does away with morphological and syntactic features to achieve robustness across languages. Our approach outperforms the state of the art in all the languages of the CoNLL-2009 benchmark dataset, especially whenever a scarce amount of training data is available. Our objective is not to reject approaches that rely on syntax, rather to set a strong and consistent language-independent baseline for future innovations in Semantic Role Labeling. We release our model code and checkpoints at https://github.com/SapienzaNLP/multi-srl.
Conference Paper
Full-text available
Abstract Meaning Representation (AMR) is a popular formalism of natural language that represents the meaning of a sentence as a semantic graph. It is agnostic about how to derive meanings from strings and for this reason it lends itself well to the encoding of semantics across languages. However, cross-lingual AMR parsing is a hard task, because training data are scarce in languages other than English and the existing English AMR parsers are not directly suited to being used in a cross-lingual setting. In this work we tackle these two problems so as to enable cross-lingual AMR parsing: we explore different transfer learning techniques for producing automatic AMR annotations across languages and develop a cross-lingual AMR parser, XL-AMR. This can be trained on the produced data and does not rely on AMR aligners or source-copy mechanisms as is commonly the case in English AMR parsing. The results of XL-AMR significantly surpass those previously reported in Chinese, German, Italian and Spanish. Finally we provide a qualitative analysis which sheds light on the suitability of AMR across languages. We release XL-AMR at github.com/SapienzaNLP/xl-amr.
Conference Paper
Full-text available
Contextualized word embeddings have been employed effectively across several tasks in Natural Language Processing, as they have proved to carry useful semantic information. However, it is still hard to link them to structured sources of knowledge. In this paper we present ARES (context-AwaRe Embeddings of Senses), a semi-supervised approach to producing sense embeddings for the lexical meanings within a lexical knowledge base that lie in a space that is comparable to that of contextualized word vectors. ARES representations enable a simple 1-Nearest-Neighbour algorithm to outperform state-of-the-art models, not only in the English Word Sense Disambiguation task, but also in the multilingual one, whilst training on sense-annotated data in English only. We further assess the quality of our embeddings in the Word-in-Context task, where, when used as an external source of knowledge, they consistently improve the performance of a neural model, leading it to compete with other more complex architectures. ARES em-beddings for all WordNet concepts and the automatically-extracted contexts used for creating the sense representations are freely available at http://sensembert.org/ares.
Conference Paper
Full-text available
Word Sense Disambiguation (WSD) is the task of identifying the meaning of a word in a given context. It lies at the base of Natural Language Processing as it provides semantic information for words. In the last decade, great strides have been made in this field and much effort has been devoted to mitigate the knowledge acquisition bottleneck problem, i.e., the problem of semantically annotating texts at a large scale and in different languages. This issue is ubiquitous in WSD as it hinders the creation of both multilingual knowledge bases and manually-curated training sets. In this work, we first introduce the reader to the task of WSD through a short historical digression and then take the stock of the advancements to alleviate the knowledge acquisition bottleneck problem. In that, we survey the literature on manual, semi-automatic and automatic approaches to create English and multilingual corpora tagged with sense annotations and present a clear overview over supervised models for WSD. Finally, we provide our view over the future directions that we foresee for the field.
Conference Paper
Full-text available
Neural architectures are the current state of the art in Word Sense Disambiguation (WSD). However, they make limited use of the vast amount of relational information encoded in Lexical Knowledge Bases (LKB). We present Enhanced WSD Integrating Synset Embed-dings and Relations (EWISER), a neural supervised architecture that is able to tap into this wealth of knowledge by embedding information from the LKB graph within the neural architecture, and to exploit pretrained synset embeddings, enabling the network to predict synsets that are not in the training set. As a result , we set a new state of the art on almost all the evaluation settings considered, also breaking through, for the first time, the 80% ceiling on the concatenation of all the standard all-words English WSD evaluation benchmarks. On multilingual all-words WSD, we report state-of-the-art results by training on nothing but English.
Conference Paper
Full-text available
We present VerbAtlas, a new, hand-crafted lexical-semantic resource whose goal is to bring together all verbal synsets from WordNet into semantically-coherent frames. The frames define a common, prototypical argument structure while at the same time providing new concept-specific information. In contrast to PropBank, which defines enumerative semantic roles, VerbAtlas comes with an explicit, cross-frame set of semantic roles linked to selectional preferences expressed in terms of WordNet synsets, and is the first resource enriched with semantic information about implicit, shadow, and default arguments. We demonstrate the effectiveness of VerbAtlas in the task of dependency-based Semantic Role Labeling and show how its integration into a high-performance system leads to improvements on both the in-domain and out-of-domain test sets of CoNLL-2009. VerbAtlas is available at http://verbatlas.org.
Conference Paper
The knowledge acquisition bottleneck strongly affects the creation of multilingual sense-annotated data, hence limiting the power of supervised systems when applied to multilingual Word Sense Disambiguation. In this paper, we propose a semi-supervised approach based upon a novel label propagation scheme, which, by jointly leveraging contextualized word embeddings and the multilingual information enclosed in a knowledge base, projects sense labels from a high-resource language, i.e., English, to lower-resourced ones. Backed by several experiments, we provide empirical evidence that our automatically created datasets are of a higher quality than those generated by other competitors and lead a supervised model to achieve state-of-the-art performances in all multilingual Word Sense Disambiguation tasks. We make our datasets available for research purposes at https://github.com/SapienzaNLP/mulan.