Open Information Extraction via Chunks

Page view(s)
18
Checked on May 30, 2024
Open Information Extraction via Chunks
Title:
Open Information Extraction via Chunks
Journal Title:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Keywords:
Publication Date:
10 December 2023
Citation:
Dong, K., Sun, A., Kim, J., & Li, X. (2023). Open Information Extraction via Chunks. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2023.emnlp-main.951
Abstract:
Open Information Extraction (OIE) aims to extract relational tuples from open-domain sentences. Existing OIE systems split a sentence into tokens and recognize token spans as tuple relations and arguments. We instead propose Sentence as Chunk sequence (SaC) and recognize chunk spans as tuple relations and arguments. We argue that SaC has better properties for OIE than sentence as token sequence, and evaluate four choices of chunks (i.e., CoNLL chunks, OIA simple phrases, noun phrases, and spans from SpanOIE). Also, we propose a simple end-to-end BERT-based model, Chunk-OIE, for sentence chunking and tuple extraction on top of SaC. Chunk-OIE achieves state-of-the-art results on multiple OIE datasets, showing that SaC benefits the OIE task.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Fund
Grant Reference no. : A18A2b0046

This research / project is supported by the A*STAR - AME Programmatic Fund
Grant Reference no. : A19E2b0098
Description:
ISBN:
979-8-89176-060