• Challenges in including extra-linguistic context in pre-trained language models

  Sorodoc, Ionut-Teodor; Aina, Laura; Boleda, Gemma (ACL (Association for Computational Linguistics), 2022)

  To successfully account for language, computational models need to take into account both the linguistic context (the content of the utterances) and the extra-linguistic context (for instance, the participants in a dialogue). ...
• How universal is metonymy? Results from a large-scale multilingual analysis

  Khishigsuren, Temuulen; Bella, Gábor; Brochhagen, Thomas; Marav, Daariimaa; Giunchiglia, Fausto; Batsuren, Khuyagbaatar (ACL (Association for Computational Linguistics), 2022)
• Introducing QuBERT: a large monolingual corpus and BERT model for Southern Quechua

  Zevallos, Rodolfo; Ortega, John E.; Chen, William; Castro, Richard; Bel Rafecas, Núria; Yoshikawa, Cesar; Ventura, Renzo; Aradiel, Hilario; Melgarejo, Nelsi (ACL (Association for Computational Linguistics), 2022)

  The lack of resources for languages in the Americas has proven to be a problem for the creation of digital systems such as machine translation, search engines, chat bots, and more. The scarceness of digital resources for ...
• Data augmentation for low-resource Quechua ASR improvement

  Zevallos, Rodolfo; Bel Rafecas, Núria; Cámbara Ruiz, Guillermo; Farrús, Mireia; Luque, Jordi (International Speech Communication Association (ISCA), 2022)

  Automatic Speech Recognition (ASR) is a key element in new services that helps users to interact with an automated system. Deep learning methods have made it possible to deploy systems with word error rates below 5% for ...
• Metaphorical measure expressions

  Sutton, Peter R.; Filip, Hana; Snider, Todd; Windhearn, Mia (University of Konstanz, 2021)

  We present an analysis of measure phrases such as heap/ounce of information in which the measure expression receives a non-literal, metaphorical interpretation. We present evidence that these metaphorical measure ...
• Restrictions on copredication: a situation theoretic approach

  Sutton, Peter R. (Cornell University, Linguistic Society of America, 2022)

  This paper proposes a situation theoretic account of polysemy: polysemous nouns denote situations that witness (i.e. contain) multiple entities of different types. For instance, lunch denotes situations that contain an ...
• Communication breakdown: on the low mutual intelligibility between human and neural captioning

  Dessì, Roberto; Gualdoni, Eleonora; Franzon, Francesca; Boleda, Gemma; Baroni, Marco (ACL (Association for Computational Linguistics), 2022)

  We compare the 0-shot performance of a neural caption-based image retriever when given as input either human-produced captions or captions generated by a neural captioner. We conduct this comparison on the recently ...
• Emergent language generalization and acquisition speed are not tied to compositionality

  Kharitonov, Eugene; Baroni, Marco (ACL (Association for Computational Linguistics), 2020)

  Studies of discrete languages emerging when neural agents communicate to solve a joint task often look for evidence of compositional structure. This stems for the expectation that such a structure would allow languages ...
• CNNs found to jump around more skillfully than RNNs: compositional generalization in seq2seq convolutional networks

  Dessi, Roberto; Baroni, Marco (ACL (Association for Computational Linguistics), 2019)

  Lake and Baroni (2018) introduced the SCAN dataset probing the ability of seq2seq models to capture compositional generalizations, such as inferring the meaning of “jump around” 0- shot from the component words. ...
• Obligatory clitic expression, clitic omission, and the morphology-syntax interface

  Alsina i Keith, Àlex (CSLI Publications, 2020)

  In the Romance language Catalan, some verbs and some argument-structure configurations normally require the reflexive clitic; however, in certain constructions, the expected reflexive clitic is optionally missing; and, ...
• Interpretable agent communication from scratch (with a generic visual processor emerging on the side)

  Dessì, Roberto; Kharitonov, Eugene; Baroni, Marco (Neural Information Processing Systems (NeurIPS), 2021)

  As deep networks begin to be deployed as autonomous agents, the issue of how they can communicate with each other becomes important. Here, we train two deep nets from scratch to perform large-scale referent identification ...
• Controlled tasks for model analysis: retrieving discrete information from sequences

  Sorodoc, Ionut-Teodor; Boleda, Gemma; Baroni, Marco (ACL (Association for Computational Linguistics), 2021)

  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 ...
• Accesibilidad en las plataformas de vídeo actuales: Repaso de la oferta de servicios en España

  Arias Badia, Blanca (HispaTAV - Congreso Hispanoamericano de Traducción Audiovisual, 2020-11)

  Infografía presentada en la jornada HispaTAV, en la que se recoge la oferta de servicios de accesibilidad en lengua española y lengua de signos española en las plataformas Netflix, HBO, Disney+, AppleTV, Filmin, PrimeVideo ...
• Deep daxes: mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks

  Gulordava, Kristina; Brochhagen, Thomas; Boleda, Gemma (Cognitive Science Society, 2020)

  Children’s tendency to associate novel words with novel referents has been taken to reflect a bias toward mutual exclusivity. This tendency may be advantageous both as (1) an ad-hoc referent selection heuristic to single ...
• Modeling word interpretation with deep language models: the interaction between expectations and lexical information

  Aina, Laura; Brochhagen, Thomas; Boleda, Gemma (Cognitive Science Society, 2020)

  How a word is interpreted depends on the context it appears in. We study word interpretation leveraging deep language models, tracing the contribution and interaction of two sources of information that have been shown to ...
• Constraining expletives in English

  Alsina i Keith, Àlex; Yang, Fengrong (CSLI Publications, 2019)

  This paper aims to present a theory of expletives1 in English within LFG in which the distribution of expletives follows from general principles and from the lexical entries of the relevant expletives. Consequently, ...
• Catalan intransitive verbs and argument realization

  Alsina i Keith, Àlex; Yang, Fengrong (CSLI Publications, 2018)

  The goal of this paper is to analyze the behavior of the single direct argument of intransitive verbs in Catalan, including its encoding as a grammatical function, verbal agreement, case assignment, and expression by means ...
• Linguistic profiles of translation manuscripts and edited translations

  Serbina, Tatiana; Bisiada, Mario; Neumann, Stella (ACL (Association for Computational Linguistics), 2021)

  A range of studies have pointed to the importance of considering the influence of editors in studies of translated language. Those studies have concentrated on particular features, which allowed them to study those features ...
• The arText prototype: an automatic system for writing specialized texts

  da Cunha Fanego, Iria; Montané March, M. Amor; Hysa, Luis (ACL (Association for Computational Linguistics), 2017)

  This article describes an automatic system for writing specialized texts in Spanish. The arText prototype is a free online text editor that includes different types of linguistic information. It is designed for a variety ...
• 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 ...

View more