论文信息 - Predicting Pronouns with a Convolutional Network and an N-gram Model - 字舞流文

Predicting Pronouns with a Convolutional Network and an N-gram Model

This paper describes the UU-Hardmeier system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The system is an ensemble of convolutional neural networks combined with a source-aware n-gram language model.

Christian Hardmeier

[1] Preslav Nakov,et al. Findings of the 2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction , 2017, DiscoMT@EMNLP.

[2] Andreas Stolcke,et al. SRILM at Sixteen: Update and Outlook , 2011 .

[3] Christian Hardmeier. Pronoun Prediction with Latent Anaphora Resolution , 2016, WMT.

[4] Kenneth Heafield,et al. KenLM: Faster and Smaller Language Model Queries , 2011, WMT@EMNLP.

[5] Jörg Tiedemann,et al. Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction , 2013, EMNLP.

[6] Marcello Federico,et al. Modelling pronominal anaphora in statistical machine translation , 2010, IWSLT.

[7] F ChenStanley,et al. An Empirical Study of Smoothing Techniques for Language Modeling , 1996, ACL.

[8] Filip Ginter,et al. Cross-Lingual Pronoun Prediction with Deep Recurrent Neural Networks , 2016, WMT.

[9] Christian Hardmeier,et al. Discourse in Statistical Machine Translation , 2014 .

[10] Sharid Loáiciga,et al. It-disambiguation and source-aware language models for cross-lingual pronoun prediction , 2016, WMT.