0

Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG

A new decoding method that leverages cross-attention from encoder-decoder models reduces semantic errors in generated text while maintaining high quality in language generation tasks.

Year
2021
Venue
INLG (ACL) 2021 8
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2109.07043ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Ever since neural models were adopted in data-to-text language generation, they have invariably been reliant on extrinsic components to improve their semantic accuracy, because the models normally do not exhibit the ability to generate text that reliably mentions all of the information provided in the input. In this paper, we propose a novel decoding method that extracts interpretable information from encoder-decoder models' cross-attention, and uses it to infer which attributes are mentioned in the generated text, which is subsequently used to rescore beam hypotheses. Using this decoding method with T5 and BART, we show on three datasets its ability to dramatically reduce semantic errors in the generated outputs, while maintaining their state-of-the-art quality.

Authors

2