James Cross


2020

bib
A Survey of Qualitative Error Analysis for Neural Machine Translation Systems
Denise Díaz | James Cross | Vishrav Chaudhary | Ahmed Kishky | Philipp Koehn
Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 2: User Track)

pdf bib
Proceedings of the First Workshop on Automatic Simultaneous Translation
Hua Wu | Collin Cherry | Liang Huang | Zhongjun He | Mark Liberman | James Cross | Yang Liu
Proceedings of the First Workshop on Automatic Simultaneous Translation

2018

pdf bib
Simple Fusion: Return of the Language Model
Felix Stahlberg | James Cross | Veselin Stoyanov
Proceedings of the Third Conference on Machine Translation: Research Papers

Neural Machine Translation (NMT) typically leverages monolingual data in training through backtranslation. We investigate an alternative simple method to use monolingual data for NMT training: We combine the scores of a pre-trained and fixed language model (LM) with the scores of a translation model (TM) while the TM is trained from scratch. To achieve that, we train the translation model to predict the residual probability of the training data added to the prediction of the LM. This enables the TM to focus its capacity on modeling the source sentence since it can rely on the LM for fluency. We show that our method outperforms previous approaches to integrate LMs into NMT while the architecture is simpler as it does not require gating networks to balance TM and LM. We observe gains of between +0.24 and +2.36 BLEU on all four test sets (English-Turkish, Turkish-English, Estonian-English, Xhosa-English) on top of ensembles without LM. We compare our method with alternative ways to utilize monolingual data such as backtranslation, shallow fusion, and cold fusion.

2016

pdf bib
Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles
James Cross | Liang Huang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Incremental Parsing with Minimal Features Using Bi-Directional LSTM
James Cross | Liang Huang
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2013

pdf bib
Optimal Incremental Parsing via Best-First Dynamic Programming
Kai Zhao | James Cross | Liang Huang
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing