Autoregressive Structured Prediction with Language Models
Tianyu Liu, Yuchen Eleanor Jiang, Nicholas Monath, Ryan Cotterell, Mrinmaya Sachan
Abstract
Recent years have seen a paradigm shift in NLP towards using pretrained language models (PLM) for a wide range of tasks. However, there are many difficult design decisions to represent structures (e.g. tagged text, coreference chains) in a way such that they can be captured by PLMs. Prior work on structured prediction with PLMs typically flattens the structured output into a sequence, which limits the quality of structural information being learned and leads to inferior performance compared to classic discriminative models. In this work, we describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs, allowing in-structure dependencies to be learned without any loss. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at, namely, named entity recognition, end-to-end relation extraction, and coreference resolution.
BibTeX
@inproceedings{liu-etal-2022-autoregressive,
title = "Autoregressive Structured Prediction with Language Models",
author = "Liu, Tianyu and
Jiang, Yuchen Eleanor and
Monath, Nicholas and
Cotterell, Ryan and
Sachan, Mrinmaya",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.70/",
doi = "10.18653/v1/2022.findings-emnlp.70",
pages = "993--1005"
}