Browsing by Author "Westera, Matthijs"

Sort by: Order: Results:

  • A closer look at scalar diversity using contextualized semantic similarity
    Westera, Matthijs; Boleda, Gemma (University of Konstanz, 2020)
    We take a closer look at van Tiel et al.’s (2016) experimental results on diversity in scalar inference rates. In contrast to their finding that semantic similarity had no significant effect on scalar inference rates, ...
  • AMORE-UPF at SemEval-2018 Task 4: BiLSTM with entity library
    Boleda, Gemma; Aina, Laura; Silberer, Carina; Sorodoc, Ionut-Teodor; Westera, Matthijs (ACL (Association for Computational Linguistics), 2018)
    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 ...
  • Distributional models of category concepts based on names of category members
    Westera, Matthijs; Gupta, Abhijee; Boleda, Gemma; Padó, Sebastian (Wiley, 2021)
    Cognitive scientists have long used distributional semantic representations of categories. The predominant approach uses distributional representations of category-denoting nouns, such as “city” for the category city. We ...
  • Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution
    Aina, Laura; Liao, Xixian; Boleda, Gemma; Westera, Matthijs (ACL (Association for Computational Linguistics), 2021)
    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 ...
  • Don’t blame distributional semantics if it can’t do entailment
    Westera, Matthijs; Boleda, Gemma (ACL (Association for Computational Linguistics), 2019)
    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 ...
  • Humans meet models on object naming: a new dataset and analysis
    Silberer, Carina; Zarrieß, Sina; Westera, Matthijs; Boleda, Gemma (ACL (Association for Computational Linguistics), 2020)
    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 ...
  • Implying or implicating not both in declaratives and interrogatives
    Westera, Matthijs (Osnabrück University, 2020)
    Both disjunctive assertions and disjunctive questions can imply “not both”, i.e., that only one of the disjuncts is true. For assertions this is known to be part of what the speaker means (e.g., an implicature), whereas ...
  • Meanings of tones and tunes
    Westera, Matthijs; Goodhue, Daniel; Gussenhoven, Carlos (Oxford University Press, 2021)
    Theories of intonational meaning can be organized into two broad categories. Specialist theories aim to capture the meaning of a particular type of intonation contour, or even just a particular usage of that contour, ...
  • QUDs, brevity, and the asymmetry of alternatives
    Westera, Matthijs (Institute for Logic, Language and Computation (ILLC), 2017)
    Exhaustivity is typically explained in terms of the exclusion of unmentioned alternatives. For this to work, the set of alternatives must be asymmetrical, lest both a proposition and its negation get excluded, yielding a ...
  • Rising declaratives of the quality-suspending kind
    Westera, Matthijs (Ubiquity Press, 2018)
    The theory of Intonational Compliance Marking (ICM) maintains that speakers of English use final rising intonation to indicate a suspension (potential violation) of a conversational maxim (Westera 2013; 2014). This paper ...
  • Similarity or deeper understanding?: analyzing the TED-Q dataset of evoked questions
    Westera, Matthijs; Amidei, Jacopo; Mayol, Laia (ACL (Association for Computational Linguistics), 2020)
    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 ...
  • TED-Q: TED talks and the questions they evoke
    Westera, Matthijs; Mayol, Laia; Rohde, Hannah (ACL (Association for Computational Linguistics), 2020)
    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 ...
  • ​What do entity-centric models learn? Insights from entity linking in multi-party dialogue
    Boleda, Gemma; Aina, Laura; Silberer, Carina; Sorodoc, Ionut-Teodor; Westera, Matthijs (ACL (Association for Computational Linguistics), 2019)
    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 ...