no code implementations • EAMT 2020 • Sergi Alvarez, Antoni Oliver, Toni Badia
The recent improvements in machine translation (MT) have boosted the use of post-editing (PE) in the translation industry.
no code implementations • EAMT 2020 • Antoni Oliver, Sergi Alvarez, Toni Badia
There is currently an extended use of post-editing of machine translation (PEMT) in the translation industry.
no code implementations • ACL 2021 • Antonio Mart{\'\i}nez-Garc{\'\i}a, Toni Badia, Jeremy Barnes
Furthermore, POS tagging is more sensitive to morphological typology than sentiment analysis and, on this task, models perform much better on fusional languages than on the other typologies.
2 code implementations • COLING (PEOPLES) 2020 • Irean Navas Alejo, Toni Badia, Jeremy Barnes
Consequently, we explore cross-lingual transfer approaches for fine-grained emotion detection in Spanish and Catalan tweets.
1 code implementation • ACL 2019 • Lingxian Bao, Patrik Lambert, Toni Badia
Abstract Attention based deep learning systems have been demonstrated to be the state of the art approach for aspect-level sentiment analysis, however, end-to-end deep neural networks lack flexibility as one can not easily adjust the network to fix an obvious problem, especially when more training data is not available: e. g. when it always predicts \textit{positive} when seeing the word \textit{disappointed}.
Ranked #18 on Aspect-Based Sentiment Analysis (ABSA) on SemEval-2014 Task-4 (Restaurant (Acc) metric)
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • 13 Jun 2019 • Àlex R. Atrio, Toni Badia, Jeremy Barnes
Current state-of-the-art models for sentiment analysis make use of word order either explicitly by pre-training on a language modeling objective or implicitly by using recurrent neural networks (RNNs) or convolutional networks (CNNs).
Cross-Lingual Sentiment Classification General Classification +4
no code implementations • LREC 2018 • Jeremy Barnes, Patrik Lambert, Toni Badia
While sentiment analysis has become an established field in the NLP community, research into languages other than English has been hindered by the lack of resources.
no code implementations • COLING 2016 • Jeremy Barnes, Patrik Lambert, Toni Badia
Cross-lingual sentiment classification (CLSC) seeks to use resources from a source language in order to detect sentiment and classify text in a target language.
no code implementations • LREC 2014 • Roser Saur{\'\i}, Judith Domingo, Toni Badia
We present the NewSoMe (News and Social Media) Corpus, a set of subcorpora with annotations on opinion expressions across genres (news reports, blogs, product reviews and tweets) and covering multiple languages (English, Spanish, Catalan and Portuguese).
no code implementations • - 2012 • Roser Saurí, Toni Badia
The Spanish TimeBank Corpus contains 210 documents, which have been annotated with time and eventuality information according to the TimeML scheme, now accepted as an international cross-language ISO standard
no code implementations • Linguistic Data Consortium 2012 • Roser Saurí, Toni Badia
The Catalan TimeBank Corpus contains 210 documents (mostly news reports), which have been annotated with time and eventuality information according to the TimeML scheme (Pustejovsky et al., 2005), now accepted as an international cross-language ISO standard