activity
20192021
most citedFindings of the First Shared Task on Machine Translation Robustness

9 citations · 17 across the 5 of their papers we have counts for

collaborators

8 papers

cs.CL20212 cited

Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data

Wei-Jen Ko, Ahmed El-Kishky, Adithya Renduchintala +6

The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are lin…

cs.CL20216 cited

Evaluating Saliency Methods for Neural Language Models

Shuoyang Ding, Philipp Koehn

Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same predicti…

cs.CL2021

XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment

Ahmed El-Kishky, Adithya Renduchintala, James Cross +2

Cross-lingual named-entity lexica are an important resource to multilingual NLP tasks such as machine translation and cross-lingual wikification. While knowledge bases contain a la…

cs.CL2021

Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora

Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

Large web-crawled corpora represent an excellent resource for improving the performance of Neural Machine Translation (NMT) systems across several language pairs. However, since th…

cs.CL2021

Learning Policies for Multilingual Training of Neural Machine Translation Systems

Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resour…

cs.CL2021

Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation

Haoran Xu, Philipp Koehn

Linear embedding transformation has been shown to be effective for zero-shot cross-lingual transfer tasks and achieve surprisingly promising results. However, cross-lingual embeddi…