Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact Extraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Jianhao, Ouyang, Haoyuan, Ren, Junyang, Ding, Wentao, Hu, Wei, Qu, Yuzhong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909226703519744
author Chen, Jianhao
Ouyang, Haoyuan
Ren, Junyang
Ding, Wentao
Hu, Wei
Qu, Yuzhong
author_facet Chen, Jianhao
Ouyang, Haoyuan
Ren, Junyang
Ding, Wentao
Hu, Wei
Qu, Yuzhong
contents Facts extraction is pivotal for constructing knowledge graphs. Recently, the increasing demand for temporal facts in downstream tasks has led to the emergence of the task of temporal fact extraction. In this paper, we specifically address the extraction of temporal facts from natural language text. Previous studies fail to handle the challenge of establishing time-to-fact correspondences in complex sentences. To overcome this hurdle, we propose a timeline-based sentence decomposition strategy using large language models (LLMs) with in-context learning, ensuring a fine-grained understanding of the timeline associated with various facts. In addition, we evaluate the performance of LLMs for direct temporal fact extraction and get unsatisfactory results. To this end, we introduce TSDRE, a method that incorporates the decomposition capabilities of LLMs into the traditional fine-tuning of smaller pre-trained language models (PLMs). To support the evaluation, we construct ComplexTRED, a complex temporal fact extraction dataset. Our experiments show that TSDRE achieves state-of-the-art results on both HyperRED-Temporal and ComplexTRED datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10288
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact Extraction
Chen, Jianhao
Ouyang, Haoyuan
Ren, Junyang
Ding, Wentao
Hu, Wei
Qu, Yuzhong
Computation and Language
Artificial Intelligence
Facts extraction is pivotal for constructing knowledge graphs. Recently, the increasing demand for temporal facts in downstream tasks has led to the emergence of the task of temporal fact extraction. In this paper, we specifically address the extraction of temporal facts from natural language text. Previous studies fail to handle the challenge of establishing time-to-fact correspondences in complex sentences. To overcome this hurdle, we propose a timeline-based sentence decomposition strategy using large language models (LLMs) with in-context learning, ensuring a fine-grained understanding of the timeline associated with various facts. In addition, we evaluate the performance of LLMs for direct temporal fact extraction and get unsatisfactory results. To this end, we introduce TSDRE, a method that incorporates the decomposition capabilities of LLMs into the traditional fine-tuning of smaller pre-trained language models (PLMs). To support the evaluation, we construct ComplexTRED, a complex temporal fact extraction dataset. Our experiments show that TSDRE achieves state-of-the-art results on both HyperRED-Temporal and ComplexTRED datasets.
title Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact Extraction
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.10288