Constraining word alignments with posterior regularization for label transfer

Kevin Jose, Thomas Gueudre


Abstract
Unsupervised word alignments offer a lightweight and interpretable method to transfer labels from high- to low-resource languages, as long as semantically related words have the same label across languages. But such an assumption is often not true in industrial NLP pipelines, where multilingual annotation guidelines are complex and deviate from semantic consistency due to various factors (such as annotation difficulty, conflicting ontology, upcoming feature launches etc.);We address this difficulty by constraining the alignments models to remain consistent with both source and target annotation guidelines , leveraging posterior regularization and labeled examples. We illustrate the overall approach using IBM 2 (fast_align) as a base model, and report results on both internal and external annotated datasets. We measure consistent accuracy improvements on the MultiATIS++ dataset over AWESoME, a popular transformer-based alignment model, in the label projection task (+2.7% at word-level and +15% at sentence-level), and show how even a small amount of target language annotations help substantially.
Anthology ID:
2022.naacl-industry.15
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track
Month:
July
Year:
2022
Address:
Hybrid: Seattle, Washington + Online
Editors:
Anastassia Loukina, Rashmi Gangadharaiah, Bonan Min
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
121–129
Language:
URL:
https://aclanthology.org/2022.naacl-industry.15
DOI:
10.18653/v1/2022.naacl-industry.15
Bibkey:
Cite (ACL):
Kevin Jose and Thomas Gueudre. 2022. Constraining word alignments with posterior regularization for label transfer. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, pages 121–129, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
Cite (Informal):
Constraining word alignments with posterior regularization for label transfer (Jose & Gueudre, NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-industry.15.pdf
Video:
 https://aclanthology.org/2022.naacl-industry.15.mp4
Code
 amazon-research/fast_label