Welcome to the UPF Digital Repository

Browsing Congressos (Departament de Traducció i Ciències del Llenguatge) by Author "Lazaridou, Angeliki"

Browsing Congressos (Departament de Traducció i Ciències del Llenguatge) by Author "Lazaridou, Angeliki"

Sort by: Order: Results:

  • Hubness and pollution: delving into cross-space mapping for zero-shot learning
    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 ...
  • Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model
    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 ...
  • “Look, some green circles!”: learning to quantify from images
    Boleda, Gemma; Sorodoc, Ionut-Teodor; Lazaridou, Angeliki; Herbelot, Aurélie; Pezzelle, Sandro; Bernardi, Raffaella (ACL (Association for Computational Linguistics), 2016)
    In this paper, we investigate whether a neural network model can learn the meaning of natural language quantifiers (no,some and all) from their use in visual contexts. We show that memory networks perform well in this ...
  • Multimodal semantic learning from child-directed input
    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 ...
  • The LAMBADA dataset: word prediction requiring a broad discourse context
    Boleda, Gemma; Paperno, Denis; Kruszewski, German; Lazaridou, Angeliki; Pham, Quan Ngoc; Bernardi, Raffaella; Pezzelle, Sandro; Baroni, Marco; Fernandez, Raquel (ACL (Association for Computational Linguistics), 2016)
    We introduce LAMBADA, a dataset to evaluate the capabilities of computational models for text understanding by means of a word prediction task. LAMBADA is a collection of narrative passages sharing the characteristic that ...
  • "The red one!": on learning to refer to things based on discriminative properties
    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 ...

Search DSpace


Advanced Search

Browse

My Account

In collaboration with Compliant to Partaking