Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

Callin, Jimmy; Hardmeier, Christian; Tiedemann, Jörg

doi:10.18653/v1/w15-2508

Cited by 7 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…UU-TIEDEMANN (Tiedemann, 2015) used a linear support vector machine with local features and simple surface features derived from preceding noun phrases. WHATELLES (Callin et al, 2015) used a neural network classifier based on work by Hardmeier et al (2013b), but replacing all (explicit or latent) anaphora resolution with information extracted from preceding noun phrases. The IDIAP system (Luong et al, 2015) used a Naïve Bayes classifier and extracted features from both preceding and following noun phrases to account for the possibility of cataphoric references.…”

Section: Submitted Systemsmentioning

confidence: 99%

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Hardmeier¹,

Nakov²,

Stymne³

et al. 2015

Proceedings of the Second Workshop on Discourse in Machine Translation

Self Cite

View full text Add to dashboard Cite

We describe the design, the evaluation setup, and the results of the DiscoMT 2015 shared task, which included two subtasks, relevant to both the machine translation (MT) and the discourse communities: (i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learning task in its own right. We focused on the English-French language pair, for which MT output is generally of high quality, but has visible issues with pronoun translation due to differences in the pronoun systems of the two languages. Six groups participated in the pronoun-focused translation task and eight groups in the cross-lingual pronoun prediction task.

show abstract

Section: Submitted Systemsmentioning

confidence: 99%

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Hardmeier¹,

Nakov²,

Stymne³

et al. 2015

Proceedings of the Second Workshop on Discourse in Machine Translation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some of the best systems developed for these tasks avoided, in fact, the direct use of anaphora resolution (with the exception of Luong et al (2015)). For example, Callin et al (2015) designed a classifier based on a feed-forward neural network, which considered as features the preceding nouns and determiners along with their part-of-speech tags. The winning systems of the 2016 task used deep neural networks: Luotolahti et al (2016) and Dabre et al (2016) summarized the preceding and following contexts of the pronoun to predict and passed them to a recurrent neural network.…”

Section: Coreference-aware Machine Translationmentioning

confidence: 99%

Using Coreference Links to Improve Spanish-to-English Machine Translation

Werlen¹,

Popescu-Belis²

2017

Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017)

View full text Add to dashboard Cite

In this paper, we present a proof-ofconcept of a coreference-aware decoder for document-level machine translation. We consider that better translations should have coreference links that are closer to those in the source text, and implement this criterion in two ways. First, we define a similarity measure between source and target coreference structures, by projecting the target ones onto the source ones, and then reusing existing monolingual coreference metrics. Based on this similarity measure, we re-rank the translation hypotheses of a baseline MT system for each sentence. Alternatively, to address the lack of diversity of mentions among the MT hypotheses, we focus on mention pairs and integrate their coreference scores with MT ones, resulting in post-editing decisions. Experiments with Spanish-to-English MT on the AnCora-ES corpus show that our second approach yields a substantial increase in the accuracy of pronoun translation, while BLEU scores remain constant.

show abstract

“…Several systems developed for this task avoid direct use of anaphora resolution, but still reach competitive performance. Callin et al (2015) designed a classifier based on a feed-forward neural network, which considered as features the preceding nouns and determiners along with their partsof-speech. Stymne (2016) combined the local context surrounding the source and target pronouns (lemmas and POS tags) together with source-side dependency heads.…”

Section: Related Workmentioning

confidence: 99%

Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities

Luong¹,

Popescu-Belis²,

Gonzales

et al. 2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 2

View full text Add to dashboard Cite

We implement a fully probabilistic model to combine the hypotheses of a Spanish anaphora resolution system with those of a Spanish-English machine translation system. The probabilities over antecedents are converted into probabilities for the features of translated pronouns, and are integrated with phrase-based MT using an additional translation model for pronouns. The system improves the translation of several Spanish personal and possessive pronouns into English, by solving translation divergencies such as ella → she | it or su → his | her | its | their. On a test set with 2,286 pronouns, a baseline system correctly translates 1,055 of them, while ours improves this by 41. Moreover, with oracle antecedents, possessives are translated with an accuracy of 83%.

show abstract

Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

Cited by 7 publications

References 4 publications

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Using Coreference Links to Improve Spanish-to-English Machine Translation

Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities

Contact Info

Product

Resources

About