A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Accurate Word Alignment Induction from Neural Machine Translation
2020
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
unpublished
Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights DO capture accurate word alignments and propose two novel word alignment induction methods SHIFT-ATT and SHIFT-AET. The main idea is to induce alignments at the step when the to-be-aligned target token is the decoder input rather than the decoder output as in previous work.
doi:10.18653/v1/2020.emnlp-main.42
fatcat:kclz2q7i7fdmboj3nblqmytrfy