Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Geng, Saibo, Josifoski, Martin, Peyrard, Maxime, West, Robert
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929213600169984
author Geng, Saibo
Josifoski, Martin
Peyrard, Maxime
West, Robert
author_facet Geng, Saibo
Josifoski, Martin
Peyrard, Maxime
West, Robert
contents Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained decoding (GCD) can be used to control the generation of LMs, guaranteeing that the output follows a given structure. Most existing GCD methods are, however, limited to specific tasks, such as parsing or code generation. In this work, we demonstrate that formal grammars can describe the output space for a much wider range of tasks and argue that GCD can serve as a unified framework for structured NLP tasks in general. For increased flexibility, we introduce input-dependent grammars, which allow the grammar to depend on the input and thus enable the generation of different output structures for different inputs. We then empirically demonstrate the power and flexibility of GCD-enhanced LMs on (1) information extraction, (2) entity disambiguation, and (3) constituency parsing. Our results indicate that grammar-constrained LMs substantially outperform unconstrained LMs or even beat task-specific finetuned models. Grammar constraints thus hold great promise for harnessing off-the-shelf LMs for a wide range of structured NLP tasks, especially where training data is scarce or finetuning is expensive. Code and data: https://github.com/epfl-dlab/GCD.
format Preprint
id arxiv_https___arxiv_org_abs_2305_13971
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
Geng, Saibo
Josifoski, Martin
Peyrard, Maxime
West, Robert
Computation and Language
Artificial Intelligence
Machine Learning
Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained decoding (GCD) can be used to control the generation of LMs, guaranteeing that the output follows a given structure. Most existing GCD methods are, however, limited to specific tasks, such as parsing or code generation. In this work, we demonstrate that formal grammars can describe the output space for a much wider range of tasks and argue that GCD can serve as a unified framework for structured NLP tasks in general. For increased flexibility, we introduce input-dependent grammars, which allow the grammar to depend on the input and thus enable the generation of different output structures for different inputs. We then empirically demonstrate the power and flexibility of GCD-enhanced LMs on (1) information extraction, (2) entity disambiguation, and (3) constituency parsing. Our results indicate that grammar-constrained LMs substantially outperform unconstrained LMs or even beat task-specific finetuned models. Grammar constraints thus hold great promise for harnessing off-the-shelf LMs for a wide range of structured NLP tasks, especially where training data is scarce or finetuning is expensive. Code and data: https://github.com/epfl-dlab/GCD.
title Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2305.13971