About
259
Publications
49,856
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,148
Citations
Publications
Publications (259)
Phraseological models distinguish word combinations in terms of lexical fixedness, a concept that refers to whether or not a word within a phrase can be substituted with a synonym. Seeking to shed further light on the issue of lexical fixedness, the present study explores the processing of Verb+Noun free combinations and Verb+Noun collocations by f...
Distributional semantics develops theories and methods to represent the meaning of natural language expressions, with vectors encoding their statistical distribution in linguistic contexts. It is at once a theoretical model to express meaning, a practical methodology to construct semantic representations, a computational framework for acquiring mea...
The distributional representation of a lexical item is typically a vector representing its co-occurrences with linguistic contexts. This chapter introduces the basic notions to construct distributional semantic representations from corpora. We present (i) the major types of linguistic contexts used to characterize the distributional properties of l...
This chapter presents current research in compositional distributional semantics, which aims at designing methods to construct the interpretation of complex linguistic expressions from the distributional representations of the lexical items they contain. This theme includes two major questions that we are going to explore: What is the distributiona...
Distributional semantics develops theories and methods to represent the meaning of natural language expressions, with vectors encoding their statistical distribution in linguistic contexts. It is at once a theoretical model to express meaning, a practical methodology to construct semantic representations, a computational framework for acquiring mea...
The most recent development in distributional semantics is represented by models based on artificial neural networks. In this chapter, we focus on the use of neural networks to build static embeddings. Like random encoding models, neural networks incrementally learn embeddings by reducing the high dimensionality of distributional data without build...
Distributional semantics develops theories and methods to represent the meaning of natural language expressions, with vectors encoding their statistical distribution in linguistic contexts. It is at once a theoretical model to express meaning, a practical methodology to construct semantic representations, a computational framework for acquiring mea...
Distributional semantics is the study of how distributional information can be used to model semantic facts. Its theoretical foundation has become known as the Distributional Hypothesis: Lexemes with similar linguistic contexts have similar meanings. This chapter presents the epistemological principles of distributional semantics. First, we explore...
Distributional semantics develops theories and methods to represent the meaning of natural language expressions, with vectors encoding their statistical distribution in linguistic contexts. It is at once a theoretical model to express meaning, a practical methodology to construct semantic representations, a computational framework for acquiring mea...
This chapter discusses the major types of matrix models, a rich and multifarious family of distributional semantic models (DSMs) that extend and generalize the vector space model in information retrieval from which they derive the use of co-occurrence matrices to represent distributional information. We first focus on a group of matrix DSMs (e.g.,...
This chapter focuses on the evaluation of distributional semantic models (DSMs). Distributional semantics has usually favored intrinsic methods that test DSMs for their ability to model various kinds of semantic similarity and relatedness. Recently, extrinsic evaluation has also become very popular: the distributional vectors are fed into a downstr...
In this chapter, we review random encoding models that directly reduce the dimensionality of distributional data without first building a co-occurrence matrix. While matrix distributional semantic models (DSMs) output either explicit or implicit distributional vectors, random encoding models only produce low-dimensional embeddings, and emphasize ef...
Lexical semantic competence is a multifaceted and complex reality, which includes the ability of drawing inferences, distinguishing different word senses, referring to the entities in the world, and so on. A long-standing tradition of research in linguistics and cognitive science has investigated these issues using symbolic representations. The aim...
A salient property used to distinguish word combinations (i.e., free combinations, collocations, and idioms) in phraseology is lexical fixedness (Howarth, 1998). Lexical fixedness refers to whether or not a word within a phrase can be substituted with a synonym. Phraseological models usually place word combinations on a continuum of lexical fixedne...
The goal of this study is to investigate whether a Transformer-based neural language model infers lexical semantics and use this information for the completion of morphosyntactic patterns. The semantic properties considered are telicity (also combined with definiteness) and agentivity. Both act at the interface between semantics and morphosyntax: t...
Previous research in computational linguistics dedicated a lot of effort to using language modeling and/or distributional semantic models to predict metrics extracted from eye-tracking data. However, it is not clear whether the two components have a distinct contribution, with recent studies claiming that surprisal scores estimated with large-scale...
People constantly use language to learn about the world. Computational linguists have capitalized on this fact to build large language models (LLMs) that acquire co-occurrence-based knowledge from language corpora. LLMs achieve impressive performance on many tasks, but the robustness of their world knowledge has been questioned. Here, we ask: do LL...
Word order, an essential property of natural languages, is injected in Transformer-based neural language models using position encoding. However, recent experiments have shown that explicit position encoding is not always useful, since some models without such feature managed to achieve state-of-the art performance on some tasks. To understand bett...
Both humans and neural language models are able to perform subject-verb number agreement (SVA). In principle, semantics shouldn't interfere with this task, which only requires syntactic knowledge. In this work we test whether meaning interferes with this type of agreement in English in syntactic structures of various complexities. To do so, we gene...
Abstract concepts, notwithstanding their lack of physical referents in real world, are grounded in sensorimotor experience. In fact, images depicting concrete entities may be associated to abstract concepts, both via direct and indirect grounding processes. However, what are the links connecting the concrete concepts represented by images and abstr...
The problem of fake news detection is becoming increasingly interesting for several research fields. Different approaches have been proposed, based on either the content of the news itself or the context and properties of its spread over time, specifically on social media. In the literature, it does not exist a widely accepted general-purpose datas...
A central quest of probing is to uncover how pre-trained models encode a linguistic property within their representations. An encoding, however, might be spurious-i.e., the model might not rely on it when making predictions. In this paper, we try to find encodings that the model actually uses, introducing a usage-based probing setup. We first choos...
Distributional semantics has deeply changed in the last decades. First, predict models stole the thunder from traditional count ones, and more recently both of them were replaced in many NLP applications by contextualized vectors produced by neural language models. Although an extensive body of research has been devoted to Distributional Semantic M...
The recent breakthroughs in the field of deep learning have lead to state-of-the-art results in several Computer Vision and Natural Language Processing tasks such as Visual Question Answering (VQA). Nevertheless, the training requirements in cross-linguistic settings are not completely satisfying at the moment. The datasets suitable for training VQ...
Metaphor is a widespread linguistic and cognitive phenomenon that is ruled by mechanisms which have received attention in the literature. Transformer Language Models such as BERT have brought improvements in metaphor-related tasks. However, they have been used only in application contexts, while their knowledge of the phenomenon has not been analyz...
This work addresses some questions about language processing: what does it mean that natural language sentences are semantically complex? What semantic features can determine different degrees of difficulty for human comprehenders? Our goal is to introduce a framework for argument semantic complexity, in which the processing difficulty depends on t...
Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate. While much work has been devoted to modeling the typicality relation between verbs and arguments in isolation, in this paper we take a broader perspective by assessing whether and to what extent computational approaches have access...
Word embeddings are vectorial semantic representations built with either counting or predicting techniques aimed at capturing shades of meaning from word co-occurrences. Since their introduction, these representations have been criticised for lacking interpretable dimensions. This property of word embeddings limits our understanding of the semantic...
Distributional semantics has deeply changed in the last decades. First, predict models stole the thunder from traditional count ones, and more recently both of them were replaced in many NLP applications by contextualized vectors produced by Transformer neural language models. Although an extensive body of research has been devoted to Distributiona...
Phraseological units (i.e., word combinations) are often distinguished in terms of lexical fixedness and compositionality. The former refers to whether or not a word within a phrase can be substituted with a synonym, while the latter indexes how much the individual meanings of individual words contribute to the overall meaning of a phrase. Word com...
The present study explores the processing of collocations and free combinations by first language (L1) and second language (L2) speakers of Italian. Phraseological models (Howarth, 1998; Ježek, 2005; Masini, 2009) distinguish word combinations in terms of lexical fixedness, which refers to whether or not a word within a phrase can be substituted wi...
Collocational priming is described as a priming effect induced by collocationally related words (Hoey, 2005), and has been taken to support the cognitive reality of collocations. Studies into this phenomenon have shown that collocational priming exists for L1 English speakers (Durrant & Doherty, 2010; Ellis, Frey, & Jalkanen, 2009; Cangir, Büyükkan...
The paper investigates the interaction of lexical and constructional meaning in valency coercion processing, and the effect of (in)compatibility between verb and construction for its successful resolution (Perek, Florent & Martin Hilpert. 2014. Constructional tolerance: Cross-linguistic differences in the acceptability of non-conventional uses of c...
The paper investigates valency coercion effects in Italian by means of an acceptability rating task on nine argument structure constructions. The experimental design follows Perek & Hilpert (2014) in presenting three conditions: grammatical, impossible and coercion stimuli. This design allows us to test several factors: the acceptability of creativ...
The present investigation focuses on first language (L1) and second language (L2) speakers’ sensitivity to lexical fixedness and compositionality of Italian word combinations. Two studies explored language users’ intuitions about three types of word combinations: free combinations, collocations, and idioms. In Study 1, Italian Verb+Noun combination...
This study investigates coercion effects in Italian argument structure, and has a twofold aim: i.) to provide a first insight into how Italian argument structure constructions and verbs interact with one another, and ii.) to contribute to the cross-linguistic debate on the nature of constructions and their interplay with verbal semantics. We propos...
While neural embeddings represent a popular choice for word representation in a wide variety of NLP tasks, their usage for thematic fit modeling has been limited, as they have been reported to lag behind syntax-based count models. In this paper, we propose a complete evaluation of count models and word embeddings on thematic fit estimation, by taki...
Lexical semantics is concerned with modeling the meaning of lexical items. Its leading questions are how forms and meanings combine, what they mean, how they are used, and of course also how they change. The answers to these five questions make up the fundamental theoretical assumptions and commitments which underlie different theories of lexical s...
This paper describes several approaches to the automatic rating of the concreteness of concepts in context, to approach the EVALITA 2020 “CONcreTEXT” task. Our systems focus on the interplay between words and their surrounding context by (i) exploiting annotated resources, (ii) using BERT masking to find potential substitutes of the target in speci...
On the argumenthood of optional PPs with Italian motion verbs
Aktionsart and verb class as predictors of argumenthood: Behavioral evidence about Italian verbs of motion
Collocational priming can be described as a priming effect induced by collocationally related words (Hoey, 2005), and has been taken to support the cognitive reality of collocations. Studies into this phenomenon have shown that collocational priming exists for L1 speakers (L1, Durrant & Doherty, 2010; Ellis, Frey, & Jalkanen, 2009; Cangir, Büyükkan...
Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a structured distributional model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations. The semantic representation of a sentence is a formal...
Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a Structured Distributional Model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations. The semantic representation of a sentence is a formal...
The great majority of compositional models in distributional semantics present methods to compose vectors or tensors in a representation of the sentence. Here we propose to enrich one of the best performing methods (vector addition, which we take as a baseline) with distributional knowledge about events. The resulting model is able to outperform ou...
In this study, we investigated the argumenthood of locative PPs occurring with
motion verbs in Italian, by means of a behavioral experiment based on the traditional
optionality test for argumenthood. Previous research relied on linguists’ intuitions or
corpus frequencies, and to our knowledge no published research on motion verbs in
Italian has emp...
Several unsupervised methods for hypernym detection have been investigated in distributional semantics. Here we present a new approach based on a smoothed version of the distributional inclusion hypothesis. The new method is able to improve hypernym detection after testing on the BLESS dataset.
The present research focuses on the acquisition of verb-noun word combinations by second language learners of Italian. The phraseological approach distinguishes free combinations, collocations and idioms in terms of lexical restriction. Overall, research suggests that idioms and free combinations are less problematic for learners compared to colloc...
The present research focuses on native and non-native speakers’ intuitions about Italian verb-noun word combinations. The phraseological approach distinguishes word combinations in terms of lexical restriction and compositionality. The former refers to whether or not a word within a phrase can be substituted with a synonym; while the latter has to...
The study of the argument vs. adjunct status of the locative phrase optionally occurring with verbs of motion in Italian, both bounded (directed motion) and unbounded (manner of motion), points to the notion of scalar change as a useful model for the argument/adjunct distinction: locative prepositional phrases referring to the scalar change compone...
Some explanations of abstract word learning suggest that these words are learnt primarily from the linguistic input, using statistical co-occurrences of words in language, whereas concrete words can also rely on non-linguistic, experiential information. According to this hypothesis, we expect that, if the learner is not able to fully exploit the in...
The present research focuses on the acquisition of verb-noun word combinations by second language learners of Italian. The phraseological approach distinguishes free combinations, collocations and idioms in terms of lexical restriction. Overall, research suggests that idioms and free combinations are less problematic for learners compared to colloc...
The present work aims at automatically classifying Italian idiomatic and non-idiomatic phrases with a neural network model under constrains of data scarcity. Results are discussed in comparison with an existing unsupervised model devised for idiom type detection and a similar supervised classifier previously trained to detect metaphorical bigrams....
Distributional semantics is a usage-based model of meaning, based on the assumption that the statistical distribution of linguistic items in context plays a key role in characterizing their semantic behavior. Distributional models build semantic representations by extracting co-occurrences from corpora and have become a mainstream research paradigm...
In a standard view, commonly adopted in psycholinguistics and computational linguistics, thematic roles are approached as primitive entities able to represent the roles played by the arguments of a predicate. In theoretical linguistics, however, the inability to reach a consensus on a primitive set of semantic roles led to the proposal of new appro...
The present study combines psycholinguistic evidence on Italian valency coercion and a distributional analysis. The paper suggests that distributional properties can provide useful insights on how general abstract constructions influence the resolution of coercion effects. However, complete understanding of the processing and recognition of coercio...
This paper describes a collection of modules for Italian language processing based on CoreNLP and Universal Dependencies (UD). The software will be freely available for download under the GNU General Public License (GNU GPL). Given the flexibility of the framework, it is easily adaptable to new languages provided with an UD Treebank.
The paper illustrates the design and development of a textual corpus representative of the historical variants of Italian during the Great War, which was enriched with linguistic (lemmatization and pos-tagging) and meta-linguistic annotation. The corpus, after a manual revision of the linguistic annotation, was used for specializing existing NLP to...
The great majority of compositional models in distributional semantics present methods to compose distributional vectors or tensors in a representation of the sentence. Here we propose to enrich the best performing method (vector addition, which we take as a baseline) with distributional knowledge about events, outperforming our baseline.
Distributional Semantic Models have been successfully used for modeling selectional preferences in a variety of scenarios, since distributional similarity naturally provides an estimate of the degree to which an argument satisfies the requirement of a given predicate. However, we argue that the performance of such models on rare verb-argument combi...
The affective content of a text depends on the valence and emotion values of its words. At the same time a word distributional properties deeply influence its affective content. For instance a word may become negatively loaded because it tends to co-occur with other negative expressions. Lexical affective values are used as features in sentiment an...
Complement coercion (begin a book →reading) involves a type clash between an event-selecting verb and an entity-denoting object, triggering a covert event (reading). Two main factors involved in complement coercion have been investigated: the semantic type of the object (event vs. entity), and the typicality of the covert event (the author began a...
Despite the number of NLP studies dedicated to thematic fit estimation, little attention has been paid to the related task of composing and updating verb argument expectations. The few exceptions have mostly modeled this phenomenon with structured distributional models, implicitly assuming a similarly structured representation of events. Recent exp...
This paper introduces UDLex, a computational framework for the automatic extraction of argument structures for several languages. By exploiting the versatility of the Universal Dependency annotation scheme, our system acquires subcat-egorization frames directly from a dependency parsed corpus, regardless of the input language. It thus uses a univer...
In this paper, we introduce a new distributional method for modeling predicate-argument thematic fit judgments. We use a syntax-based DSM to build a prototypical representation of verb-specific roles: for every verb, we extract the most salient second order contexts for each of its roles (i.e. the most salient dimensions of typical role fillers), a...
Recent psycholinguistic and neuroscientific research has emphasized the crucial role of emotions for abstract words, which would be grounded by affective experience, instead of a sensorimotor one. The hypothesis of affective embodiment has been proposed as an alternative to the idea that abstract words are linguistically coded and that linguistic p...
In this work we tested whether a series of compositionality indices that compute the distributional similarity between the vector of a given expression and the vectors of its lexical variants can effectively tell apart idiomatic and more compositional expressions in a set of 13 idiomatic and 13 non-idiomatic Italian target noun-adjective constructi...
We present a method to explore semantic change as a function of variation in distributional semantic spaces. In this paper, we apply this approach to automatically identify the areas of semantic change in the lexicon of Ancient Greek between the pre-Christian and Christian era. Distributional Semantic Models are used to identify meaningful clusters...
The organization of semantic information in the brain has been mainly explored through category-based models, on the assumption that categories broadly reflect the organization of conceptual knowledge. However, the analysis of concepts as individual entities, rather than as items belonging to distinct superordinate categories, may represent a signi...
This paper reports on work, carried out in the framework of the CombiNet project,
focusing on the automatic extraction of word combinations from large corpora, with
a view to represent the full distributional profile of selected lemmas. We describe two
extraction methods, based on part-of-speech sequences (P-method) and syntactic patterns
(S-method...