Lemao Liu

Instance Weighting for Neural Machine Translation Domain Adaptation

2017

Instance weighting has been widely applied to phrase-based machine translation domain adaptation. However, it is challenging to be applied to Neural Machine Translation (NMT) directly, because NMT is not a linear model.

Target Foresight Based Attention for Neural Machine Translation

2018

Xintong Li, Lemao Liu, Zhaopeng Tu, Shuming Shi, Max Meng. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Graph Based Translation Memory for Neural Machine Translation

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

A translation memory (TM) is proved to be helpful to improve neural machine translation (NMT). Existing approaches either pursue the decoding efficiency by merely accessing local information in a TM or encode the global information …

TranSmart: A Practical Interactive Machine Translation System

2021 · arXiv (Cornell University)

Automatic machine translation is super efficient to produce translations yet their quality is not guaranteed. This technique report introduces TranSmart, a practical human-machine interactive translation system that is able to trade off translation quality and …

Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer

2023 · arXiv (Cornell University)

Nearest Neighbor Machine Translation ($k$NN-MT) has achieved great success in domain adaptation tasks by integrating pre-trained Neural Machine Translation (NMT) models with domain-specific token-level retrieval. However, the reasons underlying its success have not been thoroughly …

SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives

2023 · arXiv (Cornell University)

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative pairs affects the model's …

Rethinking Word-Level Auto-Completion in Computer-Aided Translation

2023 · arXiv (Cornell University)

Word-Level Auto-Completion (WLAC) plays a crucial role in Computer-Assisted Translation. It aims at providing word-level auto-completion suggestions for human translators. While previous studies have primarily focused on designing complex model architectures, this paper takes a …

Rethinking Targeted Adversarial Attacks For Neural Machine Translation

2024 · arXiv (Cornell University)

Targeted adversarial attacks are widely used to evaluate the robustness of neural machine translation systems. Unfortunately, this paper first identifies a critical issue in the existing settings of NMT targeted adversarial attacks, where their attacking …

On the Word Alignment from Neural Machine Translation

2019

Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, this paper finds attention may almost fail to capture word alignment for some NMT models. This paper thereby proposes …