@inproceedings{rajpoot-parikh-2023-nearest,
title = "Nearest Neighbor Search over Vectorized Lexico-Syntactic Patterns for Relation Extraction from Financial Documents",
author = "Rajpoot, Pawan and
Parikh, Ankur",
editor = "Surdeanu, Mihai and
Riloff, Ellen and
Chiticariu, Laura and
Frietag, Dayne and
Hahn-Powell, Gus and
Morrison, Clayton T. and
Noriega-Atala, Enrique and
Sharp, Rebecca and
Valenzuela-Escarcega, Marco",
booktitle = "Proceedings of the 2nd Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.pandl-1.1",
doi = "10.18653/v1/2023.pandl-1.1",
pages = "1--5",
abstract = "Relation extraction (RE) has achieved remarkable progress with the help of pre-trained language models. However, existing RE models are usually incapable of handling two situations: implicit expressions and long-tail relation classes, caused by language complexity and data sparsity. Further, these approaches and models are largely inaccessible to users who don{'}t have direct access to large language models (LLMs) and/or infrastructure for supervised training or fine-tuning. Rule-based systems also struggle with implicit expressions. Apart from this, Real world financial documents such as various 10-X reports (including 10-K, 10-Q, etc.) of publicly traded companies pose another challenge to rule-based systems in terms of longer and complex sentences. In this paper, we introduce a simple approach that consults training relations at test time through a nearest-neighbor search over dense vectors of lexico-syntactic patterns and provides a simple yet effective means to tackle the above issues. We evaluate our approach on REFinD and show that our method achieves state-of-the-art performance. We further show that it can provide a good start for human in the loop setup when a small number of annotations are available and it is also beneficial when domain experts can provide high quality patterns. Our code is available at 1.",
}
Markdown (Informal)
[Nearest Neighbor Search over Vectorized Lexico-Syntactic Patterns for Relation Extraction from Financial Documents](https://aclanthology.org/2023.pandl-1.1) (Rajpoot & Parikh, PANDL-WS 2023)
ACL