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.

We present a new dataset of TED-talks annotated with the questions they evoke and, where available, the answers to these questions. Evoked questions represent a hitherto mostly unexplored type of linguistic data, which promises to open up important new lines of research, especially related to the Question Under Discussion (QUD)-based approach to discourse structure. In this paper we introduce the method and open the first installment of our data to the public. We summarize and explore the current dataset, illustrate its potential by providing new evidence for the relation between predictability and implicitness – capitalizing on the already existing PDTB-style annotations for the texts we use – and outline its potential for future research. The dataset should be of interest, at its current scale, to researchers on formal and experimental pragmatics, discourse coherence, information structure, discourse expectations and processing. Our data-gathering procedure is designed to scale up, relying on crowdsourcing by non-expert annotators, with its utility for Natural Language Processing in mind (e.g., dialogue systems, conversational question answering).

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.

We take a close look at a recent dataset of TED-talks annotated with the questions they implicitly evoke, TED-Q (Westera et al., 2020). We test to what extent the relation between a discourse and the questions it evokes is merely one of similarity or association, as opposed to deeper semantic/pragmatic interpretation. We do so by turning the TED-Q dataset into a binary classification task, constructing an analogous task from explicit questions we extract from the BookCorpus (Zhu et al., 2015), and fitting a BERT-based classifier alongside models based on different notions of similarity. The BERT-based classifier, achieving close to human performance, outperforms all similarity-based models, suggesting that there is more to identifying true evoked questions than plain similarity.

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.

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.

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.