Eneko Agirre

Eneko Agirre
Universidad del País Vasco / Euskal Herriko Unibertsitatea | UPV/EHU · Computer Languages and Systems

BSc, MSc, PhD in Computer Science

About

316
Publications
39,400
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
12,293
Citations
Citations since 2017
76 Research Items
7116 Citations
201720182019202020212022202302004006008001,0001,2001,400
201720182019202020212022202302004006008001,0001,2001,400
201720182019202020212022202302004006008001,0001,2001,400
201720182019202020212022202302004006008001,0001,2001,400
Additional affiliations
April 2011 - August 2011
Stanford University
Position
  • Visiting Associate Professor
April 2009 - August 2009
Stanford University
Position
  • Visiting Associate Professor
February 2008 - present
Universidad del País Vasco / Euskal Herriko Unibertsitatea
Position
  • Professor (Associate)

Publications

Publications (316)
Preprint
Full-text available
Given the impact of language models on the field of Natural Language Processing, a number of Spanish encoder-only masked language models (aka BERTs) have been trained and released. These models were developed either within large projects using very large private corpora or by means of smaller scale academic efforts leveraging freely available data....
Preprint
Full-text available
Round-trip Machine Translation (MT) is a popular choice for paraphrase generation, which leverages readily available parallel corpora for supervision. In this paper, we formalize the implicit similarity function induced by this approach, and show that it is susceptible to non-paraphrase pairs sharing a single ambiguous translation. Based on these i...
Preprint
Full-text available
Formal verse poetry imposes strict constraints on the meter and rhyme scheme of poems. Most prior work on generating this type of poetry uses existing poems for supervision, which are difficult to obtain for most languages and poetic forms. In this work, we propose an unsupervised approach to generate poems following any given meter and rhyme schem...
Preprint
Full-text available
Recent work has shown that NLP tasks such as Relation Extraction (RE) can be recasted as Textual Entailment tasks using verbalizations, with strong performance in zero-shot and few-shot settings thanks to pre-trained entailment models. The fact that relations in current RE datasets are easily verbalized casts doubts on whether entailment would be e...
Preprint
Full-text available
The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples. In this demonstration we introduce a new workflow where the analyst directly verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-s...
Chapter
We present PhrasIS, a dataset of Phrase pairs with Inference and Similarity annotations for the evaluation of semantic representations. This dataset fills the gap between word and sentence-level datasets, allowing to evaluate compositional models at a finer granularity than sentences. Contrary to other datasets, the phrase pairs are extracted from...
Article
Full-text available
Biosanitary experts around the world are directing their efforts towards the study of COVID-19. This effort generates a large volume of scientific publications at a speed that makes the effective acquisition of new knowledge difficult. Therefore, Information Systems are needed to assist biosanitary experts in accessing, consulting and analyzing the...
Preprint
Full-text available
Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field. We present a survey of recent work that uses these large language models to solve NLP tasks via pre-training then fine-tuning, prompting, or text generation approaches. We also present approaches that use pre-train...
Preprint
Full-text available
Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal (text-only) train and inference procedure based on automatic off-the-shelf captioning of images and pretraine...
Preprint
Full-text available
Relation extraction systems require large amounts of labeled examples which are costly to annotate. In this work we reformulate relation extraction as an entailment task, with simple, hand-made, verbalizations of relations produced in less than 15 min per relation. The system relies on a pretrained textual entailment engine which is run as-is (no t...
Article
In cross-Lingual Named Entity Disambiguation (XNED) the task is to link Named Entity mentions in text in some native language to English entities in a knowledge graph. XNED systems usually require training data for each native language, limiting their application for low resource languages with small amounts of training data. Prior work have propos...
Preprint
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on monolingual data. We first produce a synthetic parallel corpus using unsupervised machine translation, and use...
Article
Cortical circuits rely on the temporal regularities of speech to optimize signal parsing for sound-to-meaning mapping. Bottom-up speech analysis is accelerated by top–down predictions about upcoming words. In everyday communications, however, listeners are regularly presented with challenging input—fluctuations of speech rate or semantic content. I...
Article
This work is a companion reproducibility paper of the experiments and results reported in Lastra-Diaz et al. (2019a), which is based on the evaluation of a companion reproducibility dataset with the HESML V1R4 library and the long-term reproducibility tool called Reprozip. Human similarity and relatedness judgements between concepts underlie most o...
Preprint
Full-text available
Generating an image from its textual description requires both a certain level of language understanding and common sense knowledge about the spatial relations of the physical entities being described. In this work, we focus on inferring the spatial relation between entities, a key step in the process of composing scenes based on text. More specifi...
Article
Generating an image from its textual description requires both a certain level of language understanding and common sense knowledge about the spatial relations of the physical entities being described. In this work, we focus on inferring the spatial relation between entities, a key step in the process of composing scenes based on text. More specifi...
Article
Full-text available
In this paper, we survey the methods and concepts developed for the evaluation of dialogue systems. Evaluation, in and of itself, is a crucial part during the development process. Often, dialogue systems are evaluated by means of human evaluations and questionnaires. However, this tends to be very cost- and time-intensive. Thus, much work has been...
Preprint
Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but it was recently shown that the separate training in different languages causes departures from this assumption. In this paper, we p...
Conference Paper
Full-text available
The lack of time-efficient and reliable evaluation methods hamper the development of conversational dialogue systems (chatbots). Evaluations requiring humans to converse with chatbots are time and cost-intensive, put high cognitive demands on the human judges, and yield low-quality results. In this work, we introduce Spot The Bot, a cost-efficient...
Preprint
The interaction of conversational systems with users poses an exciting opportunity for improving them after deployment, but little evidence has been provided of its feasibility. In most applications, users are not able to provide the correct answer to the system, but they are able to provide binary (correct, incorrect) feedback. In this paper we pr...
Preprint
Full-text available
The lack of time-efficient and reliable evaluation methods hamper the development of conversational dialogue systems (chatbots). Evaluations requiring humans to converse with chatbots are time and cost-intensive, put high cognitive demands on the human judges, and yield low-quality results. In this work, we introduce \emph{Spot The Bot}, a cost-eff...
Article
Cross-environment activity recognition in smart homes is a very challenging problem, specially for data-driven approaches. Currently, systems developed to work for a certain environment degrade substantially when applied to a new environment, where not only sensors, but also the monitored activities may be different. Some systems require manual lab...
Chapter
Full-text available
While systems for question answering over knowledge bases (KB) continue to progress, real world usage requires systems that are robust to incomplete KBs. Dependence on the closed world assumption is highly problematic, as in many practical cases the information is constantly evolving and KBs cannot keep up. In this paper we formalize a typology of...
Article
Back-translation provides a simple yet effective approach to exploit monolingual corpora in Neural Machine Translation (NMT). Its iterative variant, where two opposite NMT models are jointly trained by alternately using a synthetic parallel corpus generated by the reverse model, plays a central role in unsupervised machine translation. In order to...
Chapter
Zero-shot learning is a very promising research topic. For a vision-based action recognition system, for instance, zero-shot learning allows to recognise actions never seen during the training phase. Previous works in zero-shot action recognition have exploited in several ways the visual appearance of input videos to infer actions. Here, we propose...
Preprint
The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. We present DoQA, a dataset with 2,437 dialogues and 10,917 QA pairs. The dialogues are collected from three Stack Exchange sites using the Wizard of Ozmethod with crowdsourcing. Compared to pr...
Preprint
We review motivations, definition, approaches, and methodology for unsupervised cross-lingual learning and call for a more rigorous position in each of them. An existing rationale for such research is based on the lack of parallel data for many of the world's languages. However, we argue that a scenario without any parallel data and abundant monoli...
Conference Paper
Full-text available
In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. For this, we introduce an intermediate representation that is based on the logical query plan in a database called Operation Trees (OT). This representation allows us to invert the annotation process without losing flexibil...
Preprint
Full-text available
In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. For this, we introduce an intermediate representation that is based on the logical query plan in a database called Operation Trees (OT). This representation allows us to invert the annotation process without losing flexibil...
Preprint
Both human and machine translation play a central role in cross-lingual transfer learning: many multilingual datasets have been created through professional translation services, and using machine translation to translate either the test set or the training set is a widely used transfer technique. In this paper, we show that such translation proces...
Preprint
The combination of visual and textual representations has produced excellent results in tasks such as image captioning and visual question answering, but the inference capabilities of multimodal representations are largely untested. In the case of textual representations, inference tasks such as Textual Entailment and Semantic Textual Similarity ha...
Preprint
Full-text available
Word embeddings and pre-trained language models allow to build rich representations of text and have enabled improvements across most NLP tasks. Unfortunately they are very expensive to train, and many small companies and research groups tend to use models that have been pre-trained and made available by third parties, rather than building their ow...
Preprint
Back-translation provides a simple yet effective approach to exploit monolingual corpora in Neural Machine Translation (NMT). Its iterative variant, where two opposite NMT models are jointly trained by alternately using a synthetic parallel corpus generated by the reverse model, plays a central role in unsupervised machine translation. In order to...
Article
Full-text available
Article
Full-text available
Human similarity and relatedness judgements between concepts underlie most of cognitive capabilities, such as categorisation, memory, decision-making and reasoning. For this reason, the proposal of methods for the estimation of the degree of similarity and relatedness between words and concepts has been a very active line of research in the fields...
Article
Full-text available
This data article introduces a reproducibility dataset with the aim of allowing the exact replication of all experiments, results and data tables introduced in our companion paper (Lastra-Díaz et al., 2019), which introduces the largest experimental survey on ontology-based semantic similarity methods and Word Embeddings (WE) for word similarity re...
Preprint
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through nearest neighbor or related retrieval methods. In this paper, we propose an alternative approach to this proble...
Preprint
Recent research in cross-lingual word embeddings has almost exclusively focused on offline methods, which independently train word embeddings in different languages and map them to a shared space through linear transformations. While several authors have questioned the underlying isomorphism assumption, which states that word embeddings in differen...
Preprint
Full-text available
Word embeddings typically represent different meanings of a word in a single conflated vector. Empirical analysis of embeddings of ambiguous words is currently limited by the small size of manually annotated resources and by the fact that word senses are treated as unrelated individual concepts. We present a large dataset based on manual Wikipedia...
Preprint
Full-text available
In this paper we survey the methods and concepts developed for the evaluation of dialogue systems. Evaluation is a crucial part during the development process. Often, dialogue systems are evaluated by means of human evaluations and questionnaires. However, this tends to be very cost and time intensive. Thus, much work has been put into finding meth...
Article
Semantic Textual Similarity and Natural Language Inference are two popular natural language understanding tasks used to benchmark sentence representation models where two sentences are paired. In such tasks sentences are represented as bag of words, sequences, trees or convolutions, but the attention model is based on word pairs. In this article we...
Article
Full-text available
This article has been withdrawn at the request of the author. The Publisher apologizes for any inconvenience this may cause. The full Elsevier Policy on Article Withdrawal can be found at https://www.elsevier.com/about/our-business/policies/article-withdrawal.
Preprint
While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems using monolingual corpora only. In this paper, we identify and address several deficiencies of existing unsupervised SMT approach...
Preprint
In this paper we introduce vSTS, a new dataset for measuring textual similarity of sentences using multimodal information. The dataset is comprised by images along with its respectively textual captions. We describe the dataset both quantitatively and qualitatively, and claim that it is a valid gold standard for measuring automatic multimodal textu...
Preprint
Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like semantics/syntax and similarity/relatedness. In this paper, we show that each embedding model captures more information than...
Preprint
Full-text available
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite the potential of this approach for low-resource settings, existing systems are far behind their supervised coun...
Preprint
Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using comparable corpora or closely-related languages, and we show that they often fail in more realistic scenarios. Thi...
Preprint
Full-text available
UKB is an open source collection of programs for performing, among other tasks, knowledge-based Word Sense Disambiguation (WSD). Since it was released in 2009 it has been often used out-of-the-box in sub-optimal settings. We show that nine years later it is the state-of-the-art on knowledge-based WSD. This case shows the pitfalls of releasing open...
Article
Using a dictionary to map independently trained word embeddings to a shared space has shown to be an effective approach to learn bilingual word embeddings. In this work, we propose a multi-step framework of linear transformations that generalizes a substantial body of previous work. The core step of the framework is an orthogonal transformation, an...
Article
Full-text available
Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation. The main approach is to train monolingual embeddings first and then map them using bilingual dictionaries. In this work, we present a novel method to learn bilingual embeddings bas...
Article
Full-text available
In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs. There have been several proposals to alleviate this issue with, for instance, triangulation and semi-supervised learning techniques, but they still require a strong cr...
Conference Paper
Full-text available
Semantic Textual Similarity (STS) measures the meaning similarity of sentences. Applications include machine translation (MT), summarization, generation, question answering (QA), short answer grading, semantic search, dialog and conversational systems. The STS shared task is a venue for assessing the current state-of-the-art. The 2017 task focuses...
Article
User acceptance of artificial intelligence agents might depend on their ability to explain their reasoning to the users. We focus on a specific text processing task, the Semantic Textual Similarity task (STS), where systems need to measure the degree of semantic equivalence between two sentences. We propose to add an interpretability layer (iSTS fo...
Conference Paper
This work presents parallel corpora automatically annotated with several NLP tools, including lemma and part-of-speech tagging, named-entity recognition and classification, named-entity disambiguation, word-sense disambiguation, and coreference. The corpora comprise both the well-known Europarl corpus and a domain-specific question-answer troublesh...
Article
Full-text available
Named Entity Disambiguation (NED) is the task of linking a named-entity mention to an instance in a knowledge-base, typically Wikipedia. This task is closely related to word-sense disambiguation (WSD), where the supervised word-expert approach has prevailed. In this work we present the results of the word-expert approach to NED, where one classifie...