# Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation

Authors: Leshem Choshen, Omri Abend
Venue: Proceedings of the 23rd Conference on Computational Natural Language Learning, CoNLL 2019, Hong Kong, China, November 3-4, 2019 (2019)

## Abstract
We show that the state-of-the-art Transformer MT model is not biased towards monotonic reordering (unlike previous recurrent neural network models), but that nevertheless, long-distance dependencies remain a challenge for the model. Since most dependencies are short-distance, common evaluation metrics will be little influenced by how well systems perform on them. We therefore propose an automatic approach for extracting challenge sets rich with long-distance dependencies, and argue that evaluation using this methodology provides a complementary perspective on system performance. To support our claim, we compile challenge sets for English-German and German-English, which are much larger than any previously released challenge set for MT. The extracted sets are large enough to allow reliable automatic evaluation, which makes the proposed approach a scalable and practical solution for evaluating MT performance on the long-tail of syntactic phenomena.

## Links
- arXiv: https://arxiv.org/abs/1909.06814
- PDF: https://arxiv.org/pdf/1909.06814
- HTML: https://ar5iv.labs.arxiv.org/html/1909.06814
- Hugging Face: https://huggingface.co/papers/1909.06814
- alphaXiv: https://www.alphaxiv.org/abs/1909.06814
- DOI: https://doi.org/10.18653/V1/K19-1028
- ACL Anthology: https://aclanthology.org/K19-1028/
- Semantic Scholar: https://www.semanticscholar.org/paper/202577206
- Publisher: https://doi.org/10.18653/v1/K19-1028

## How to cite
@inproceedings{DBLP:conf/conll/ChoshenA19,
author       = {Leshem Choshen and
                  Omri Abend},
  editor       = {Mohit Bansal and
                  Aline Villavicencio},
  title        = {Automatically Extracting Challenge Sets for Non-Local Phenomena in
                  Neural Machine Translation},
  booktitle    = {Proceedings of the 23rd Conference on Computational Natural Language
                  Learning, CoNLL 2019, Hong Kong, China, November 3-4, 2019},
  pages        = {291--303},
  publisher    = {Association for Computational Linguistics},
  year         = {2019},
  url          = {https://doi.org/10.18653/v1/K19-1028},
  doi          = {10.18653/V1/K19-1028},
  timestamp    = {Thu, 05 Aug 2021 17:36:17 +0200},
  biburl       = {https://dblp.org/rec/conf/conll/ChoshenA19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}