It is often posited that more predictable parts of a speaker’s meaning tend to be made less explicit, for instance using shorter, less informative words. Studying these dynamics in the domain of referring expressions has proven difficult, with existing studies, both psycholinguistic and corpus-based, providing contradictory results. We test the hypothesis that speakers produce less informative referring expressions (e.g., pronouns vs. full noun phrases) when the context is more informative about the referent, using novel computational estimates of referent predictability. We obtain these estimates training an existing coreference resolution system for English on a new task, masked coreference resolution, giving us a probability distribution over referents that is conditioned on the context but not the referring expression. The resulting system retains standard coreference resolution performance while yielding a better estimate of human-derived referent predictability than previous attempts. A statistical analysis of the relationship between model output and mention form supports the hypothesis that predictability affects the form of a mention, both its morphosyntactic type and its length.

In recent years, the NLP community has shown increasing interest in analysing how deep learning models work. Given that large models trained on complex tasks are difficult to inspect, some of this work has focused on controlled tasks that emulate specific aspects of language. We propose a new set of such controlled tasks to explore a crucial aspect of natural language processing that has not received enough attention: the need to retrieve discrete information from sequences. We also study model behavior on the tasks with simple instantiations of Transformers and LSTMs. Our results highlight the beneficial role of decoder attention and its sometimes unexpected interaction with other components. Moreover, we show that, for most of the tasks, these simple models still show significant difficulties. We hope that the community will take up the analysis possibilities that our tasks afford, and that a clearer understanding of model behavior on the tasks will lead to better and more transparent models.

We release ManyNames v2 (MN v2), a verified version of an object naming dataset that contains dozens of valid names per object for 25K images. We analyze issues in the data collection method originally employed, standard in Language & Vision (L&V), and find that the main source of noise in the data comes from simulating a naming context solely from an image with a target object marked with a bounding box, which causes subjects to sometimes disagree regarding which object is the target. We also find that both the degree of this uncertainty in the original data and the amount of true naming variation in MN v2 differs substantially across object domains. We use MN v2 to analyze a popular L&V model and demonstrate its effectiveness on the task of object naming. However, our fine-grained analysis reveals that what appears to be human-like model behavior is not stable across domains, e.g., the model confuses people and clothing objects much more frequently than humans do. We also find that standard evaluations underestimate the actual effectiveness of the naming model: on the single-label names of the original dataset (Visual Genome), it obtains −27% accuracy points than on MN v2, that includes all valid object names.

People choose particular names for objects, such as dog or puppy for a given dog. Object naming has been studied in Psycholinguistics, but has received relatively little attention in Computational Linguistics. We review resources from Language and Vision that could be used to study object naming on a large scale, discuss their shortcomings, and create a new dataset that affords more opportunities for analysis and modeling. Our dataset, ManyNames, provides 36 name annotations for each of 25K objects in images selected from VisualGenome. We highlight the challenges involved and provide a preliminary analysis of the ManyNames data, showing that there is a high level of agreement in naming, on average. At the same time, the average number of name types associated with an object is much higher in our dataset than in existing corpora for Language and Vision, such that ManyNames provides a rich resource for studying phenomena like hierarchical variation (chihuahua vs. dog), which has been discussed at length in the theoretical literature, and other less well studied phenomena like cross-classification (cake vs. dessert).

Language models keep track of complex information about the preceding context – including, e.g., syntactic relations in a sentence. We investigate whether they also capture information beneficial for resolving pronominal anaphora in English. We analyze two state of the art models with LSTM and Transformer architectures, via probe tasks and analysis on a coreference annotated corpus. The Transformer outperforms the LSTM in all analyses. Our results suggest that language models are more successful at learning grammatical constraints than they are at learning truly referential information, in the sense of capturing the fact that we use language to refer to entities in the world. However, we find traces of the latter aspect, too.

In neural network models of language, words are commonly represented using context-invariant representations (word embeddings) which are then put in context in the hidden layers. Since words are often ambiguous, representing the contextually relevant information is not trivial. We investigate how an LSTM language model deals with lexical ambiguity in English, designing a method to probe its hidden representations for lexical and contextual information about words. We find that both types of information are represented to a large extent, but also that there is room for improvement for contextual information.

Distributional semantics has had enormous empirical success in Computational Linguistics and Cognitive Science in modeling various semantic phenomena, such as semantic similarity, and distributional models are widely used in state-of-the-art Natural Language Processing systems. However, the theoretical status of distributional semantics within a broader theory of language and cognition is still unclear: What does distributional semantics model? Can it be, on its own, a fully adequate model of the meanings of linguistic expressions? The standard answer is that distributional semantics is not fully adequate in this regard, because it falls short on some of the central aspects of formal semantic approaches: truth conditions, entailment, reference, and certain aspects of compositionality. We argue that this standard answer rests on a misconception: These aspects do not belong in a theory of expression meaning, they are instead aspects of speaker meaning, i.e., communicative intentions in a particular context. In a slogan: words do not refer, speakers do. Clearing this up enables us to argue that distributional semantics on its own is an adequate model of expression meaning. Our proposal sheds light on the role of distributional semantics in a broader theory of language and cognition, its relationship to formal semantics, and its place in computational models.

We present the first exploration of meaning shift over short periods of time in online communities using distributional representations. We create a small annotated dataset and use it to assess the performance of a standard model for meaning shift detection on short-term meaning shift. We find that the model has problems distinguishing meaning shift from referential phenomena, and propose a measure of contextual variability to remedy this.

Humans use language to refer to entities in the external world. Motivated by this, in recent years several models that incorporate a bias towards learning entity representations have been proposed. Such entity-centric models have shown empirical success, but we still know little about why. In this paper we analyze the behavior of two recently proposed entity-centric models in a referential task, Entity Linking in Multi-party Dialogue (SemEval 2018 Task 4). We show that these models outperform the state of the art on this task, and that they do better on lower frequency entities than a counterpart model that is not entity-centric, with the same model size. We argue that making models entity-centric naturally fosters good architectural decisions. However, we also show that these models do not really build entity representations and that they make poor use of linguistic context. These negative results underscore the need for model analysis, to test whether the motivations for particular architectures are borne out in how models behave when deployed.

Recent state-of-the-art neural language models share the representations of words given by the input and output mappings. We propose a simple modification to these architectures that decouples the hidden state from the word embedding prediction. Our architecture leads to comparable or better results compared to previous tied models and models without tying, with a much smaller number of parameters. We also extend our proposal to word2vec models, showing that tying is appropriate for general word prediction tasks.

This paper describes our winning contribution to SemEval 2018 Task 4: Character Identification on Multiparty Dialogues. It is a simple, standard model with one key innovation, an entity library. Our results show that this innovation greatly facilitates the identification of infrequent characters. Because of the generic nature of our model, this finding is potentially relevant to any task that requires the effective learning from sparse or imbalanced data.

Word embeddings are supposed to provide easy access to semantic relations such as “male of” (man–woman). While this claim has been investigated for concepts, little is known about the distributional behavior of relations of (Named) Entities. We describe two word embedding-based models that predict values for relational attributes of entities, and analyse them. The task is challenging, with major performance differences between relations. Contrary to many NLP tasks, high difficulty for a relation does not result from low frequency, but from (a) one-to-many mappings; and (b) lack of context patterns expressing the relation that are easy to pick up by word embeddings.

We use language to talk about the world, and so reference is a crucial property of language. However, modeling reference is particularly difficult, as it involves both continuous and discrete as-pects of language. For instance, referring expressions like “the big mug” or “it” typically contain content words (“big”, “mug”), which are notoriously fuzzy or vague in their meaning, and also fun-ction words (“the”, “it”) that largely serve as discrete pointers. Data-driven, distributed models based on distributional semantics or deep learning excel at the former, but struggle with the latter, and the reverse is true for symbolic models. I present ongoing work on modeling reference with a distribu-ted model aimed at capturing both aspects, and learns to refer directly from reference acts.

Instances (“Mozart”) are ontologically distinct from concepts or classes (“composer”). Natural language encompasses both, but instances have received comparatively little attention in distributional semantics. Our results show that instances and concepts differ in their distributional properties. We also establish that instantiation detection (“Mozart – composer”) is generally easier than hypernymy detection (“chemist – scientist”), and that results on the influence of input representation do not transfer from hyponymy to instantiation.

This article presents a new freely available trilingual corpus (Catalan, Spanish, English) that contains large portions of the Wikipedia and has been automatically enriched with linguistic information. To our knowledge, this is the largest such corpus that is freely available to the community: In its present version, it contains over 750 million words. The corpora have been annotated with lemma and part of speech information using the open source library FreeLing. Also, they have been sense annotated with the state of the art Word Sense Disambiguation algorithm UKB. As UKB assigns WordNet senses, and WordNet has been aligned across languages via the InterLingual Index, this sort of annotation opens the way to massive explorations in lexical semantics that were not possible before. We present a first attempt at creating a trilingual lexical resource from the sense-tagged Wikipedia corpora, namely, WikiNet. Moreover, we present two by-products of the project that are of use for the NLP community: An open source Java-based parser for Wikipedia pages developed for the construction of the corpus, and the integration of the WSD algorithm UKB in FreeLing.

This paper presents the ADN-Classifier, an Automatic classification system of Spanish Deverbal Nominalizations aimed at identifying its semantic denotation (i.e. event, result, underspecified, or lexicalized). The classifier can be used for NLP tasks such as coreference resolution or paraphrase detection. To our knowledge, the ADN-Classifier is the first effort in acquisition of denotations for nominalizations using Machine Learning.We compare the results of the classifier when using a decreasing number of Knowledge Sources, namely (1) the complete nominal lexicon (AnCora-Nom) that includes sense distictions, (2) the nominal lexicon (AnCora-Nom) removing the sense-specific information, (3) nominalizations’ context information obtained from a treebank corpus (AnCora-Es) and (4) the combination of the previous linguistic resources. In a realistic scenario, that is, without sense distinction, the best results achieved are those taking into account the information declared in the lexicon (89.40% accuracy). This shows that the lexicon contains crucial information (such as argument structure) that corpus-derived features cannot substitute for.

We present the Database of Catalan Adjectives (DCA), a database with 2,296 adjective lemmata enriched with morphological, syntactic and semantic information. This set of adjectives has been collected from a fragment of the Corpus Textual Informatitzat de la Llengua Catalana of the Institut d’Estudis Catalans and constitutes a representative sample of the adjective class in Catalan as a whole. The database includes both manually coded and automatically extracted information regarding the most prominent properties used in the literature regarding the semantics of adjectives, such as morphological origin, suffix (if any), predicativity, gradability, adjective position with respect to the head noun, adjective modifiers, or semantic class. The DCA can be useful for NLP applications using adjectives (from POS-taggers to Opinion Mining applications) and for linguistic analysis regarding the morphological, syntactic, and semantic properties of adjectives. We now make it available to the research community under a Creative Commons Attribution Share Alike 3.0 Spain license.

In this article we describe two different strategies for the automatic tagging of a Spanish diachronic corpus involving the adaptation of existing NLP tools developed for modern Spanish. In the initial approach we follow a state-of-the-art strategy, which consists on standardizing the spelling and the lexicon. This approach boosts POS-tagging accuracy to 90, which represents a raw improvement of over 20% with respect to the results obtained without any pre-processing. In order to enable non-expert users in NLP to use this new resource, the corpus has been integrated into IAC (Corpora Interface Access). We discuss the shortcomings of the initial approach and propose a new one, which does not consist in adapting the source texts to the tagger, but rather in modifying the tagger for the direct treatment of the old variants.This second strategy addresses some important shortcomings in the previous approach and is likely to be useful not only in the creation of diachronic linguistic resources but also for the treatment of dialectal or non-standard variants of synchronic languages as well.

In this paper, we present a brief snapshot of the state of affairs in computational processing of Catalan and the initiatives that are starting to take place in an effort to bring the field a step forward, by making a better and more efficient use of the already existing resources and tools, by bridging the gap between research and market, and by establishing periodical meeting points for the community. In particular, we present the results of the First Workshop on the Computational Processing of Catalan, which succeeded in putting together a fair representation of the research in the area, and received attention from both the industry and the administration. Aside from facilitating communication among researchers and between developers and users, the Workshop provided the organizers with valuable information about existing resources, tools, developers and providers. This information has allowed us to go a step further by setting up a “harvesting” procedure which will hopefully build the seed of a portal-catalogue-observatory of language resources and technologies in Catalan.

In this paper we describe the METIS-II system and its evaluation on each of the language pairs: Dutch, German, Greek, and Spanish to English. The METIS-II system envisaged developing a data-driven approach in which no parallel corpus is required, and in which no full parser or extensive rule sets are needed. We describe evalution on a development test set and on a test set coming from Europarl, and compare our results with SYSTRAN. We also provide some further analysis, researching the impact of the number and source of the reference translations and analysing the results according to test text type. The results are expectably lower for the METIS system, but not at an unatainable distance from a mature system like SYSTRAN.