Welcome to the UPF Digital Repository

Congressos (Departament de Traducció i Ciències del Llenguatge)

Congressos (Departament de Traducció i Ciències del Llenguatge)

 

Actes de congressos de recerca, en accés obert, del Departament de Traducció i Ciències del Llenguatge de la UPF.

Recent Submissions

  • McNally, Louise, 1965-; Gehrke, Berit (Universidad del País Vasco, 2014)
    Adverbially-interpreted temporal frequency adjectives (FAs) such as frequent, sporadic, and daily, are usually restricted to modifying event-denoting nominals (e.g. The house underwent frequent cleanings = Frequently, the ...
  • Baroni, Marco; Kilgarriff, Adam (ACL (Association for Computational Linguistics), 2006)
    The Web contains vast amounts of linguistic data. One key issue for linguists and language technologists is how to access it. Commercial search engines give highly compromised access. An alternative is to crawl the Web ...
  • Baroni, Marco; Lenci, Alessandro (ACL (Association for Computational Linguistics), 2009)
    Mitchell et al. (2008) demonstrated that corpus-extracted models of semantic knowledge can predict neural activation patterns recorded using fMRI. This could be a very powerful technique for evaluating conceptual models ...
  • Ritter, Samuel; Long, Cotie; Paperno, Denis; Baroni, Marco; Botvinick, Matthew; Goldberg, Adele (ACL (Association for Computational Linguistics), 2015)
    Complex interactions among the meanings of words are important factors in the function that maps word meanings to phrase meanings. Recently, compositional distributional semantics models (CDSM) have been designed with the ...
  • Pham, Nghia The; Kruszewski, German; Lazaridou, Angeliki; Baroni, Marco (ACL (Association for Computational Linguistics), 2015)
    We introduce C-PHRASE, a distributional semantic model that learns word representations by optimizing context prediction for phrases at all levels in a syntactic tree, from single words to full sentences. C-PHRASE outperforms ...
  • Lazaridou, Angeliki; Dinu, Georgiana; Baroni, Marco (ACL (Association for Computational Linguistics), 2015)
    Zero-shot methods in language, vision and other domains rely on a cross-space mapping function that projects vectors from the relevant feature space (e.g., visualfeature-based image representations) to a large semantic ...
  • Lazaridou, Angeliki; Chrupała, Grzegorz; Fernández, Raquel; Baroni, Marco (ACL (Association for Computational Linguistics), 2016)
    Children learn the meaning of words by being exposed to perceptually rich situations (linguistic discourse, visual scenes, etc). Current computational learning models typically simulate these rich situations through ...
  • Herbelot, Aurélie; Baroni, Marco (ACL (Association for Computational Linguistics), 2018)
    Distributional semantics models are known to struggle with small data. It is generally accepted that in order to learn ‘a good vector’ for a word, a model must have sufficient examples of its usage. This contradicts the ...
  • Conneau, Alexis; Kruszewski, German; Lample, Guillaume; Barrault, Loïc; Baroni, Marco (ACL (Association for Computational Linguistics), 2018)
    Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. “Downstream” tasks, often based on sentence classification, are ...
  • Lazaridou, Angeliki; Pham, Nghia The; Baroni, Marco (ACL (Association for Computational Linguistics), 2016)
    As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (CAT) and a context (SOFA), identifies their discriminative ...
  • Blasi, Damian; Cotterell, Ryan; Wolf-Sonkin, Lawrence; Stoll, Sabine; Bickel, Balthasar; Baroni, Marco (ACL (Association for Computational Linguistics), 2019)
    Embedding a clause inside another (“the girl [who likes cars [that run fast]] has arrived”) is a fundamental resource that has been argued to be a key driver of linguistic expressiveness. As such, it plays a central role ...
  • Gulordava, Kristina; Aina, Laura; Boleda, Gemma (ACL (Association for Computational Linguistics), 2018)
    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 ...
  • Sorodoc, Ionut-Teodor; Pezzelle, Sandro; Bernardi, Raffaella (ACL (Association for Computational Linguistics), 2018)
    The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. ...
  • 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 ...
  • Boleda, Gemma; Del Tredici, Marco; Fernández, Raquel (ACL (Association for Computational Linguistics), 2019)
    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 ...
  • Boleda, Gemma; Gulordava, Kristina; Aina, Laura (ACL (Association for Computational Linguistics), 2019)
    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 ...
  • Westera, Matthijs (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 ...
  • Wentland, Wolodja; Silberer, Carina; Hartung, Matthias (ELRA (European Language Resources Association), 2008)
    In this paper, we present HeiNER, the multilingual Heidelberg Named Entity Resource. HeiNER contains 1,547,586 disambiguated English Named Entities together with translations and transliterations to 15 languages. Our work ...
  • Silberer, Carina; Ponzetto, Simone Paolo (ACL (Association for Computational Linguistics), 2010)
    We describe the University of Heidelberg (UHD) system for the Cross-LingualWord Sense Disambiguation SemEval-2010 task (CL-WSD). The system performs CLWSD by applying graph algorithms previously developed for monolingual ...
  • Silberer, Carina; Lapata, Mirella (ACL (Association for Computational Linguistics), 2012)
    A popular tradition of studying semantic representation has been driven by the assumption that word meaning can be learned from the linguistic environment, despite ample evidence suggesting that language is grounded in ...

View more