DPR at SemEval-2021 Task 8: Dynamic Path Reasoning for Measurement Relation Extraction

Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen


Abstract
Scientific documents are replete with measurements mentioned in various formats and styles. As such, in a document with multiple quantities and measured entities, the task of associating each quantity to its corresponding measured entity is challenging. Thus, it is necessary to have a method to efficiently extract all measurements and attributes related to them. To this end, in this paper, we propose a novel model for the task of measurement relation extraction (MRE) whose goal is to recognize the relation between measured entities, quantities, and conditions mentioned in a document. Our model employs a deep translation-based architecture to dynamically induce the important words in the document to classify the relation between a pair of entities. Furthermore, we introduce a novel regularization technique based on Information Bottleneck (IB) to filter out the noisy information from the induced set of important words. Our experiments on the recent SemEval 2021 Task 8 datasets reveal the effectiveness of the proposed model.
Anthology ID:
2021.semeval-1.47
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
397–403
Language:
URL:
https://aclanthology.org/2021.semeval-1.47
DOI:
10.18653/v1/2021.semeval-1.47
Bibkey:
Cite (ACL):
Amir Pouran Ben Veyseh, Franck Dernoncourt, and Thien Huu Nguyen. 2021. DPR at SemEval-2021 Task 8: Dynamic Path Reasoning for Measurement Relation Extraction. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 397–403, Online. Association for Computational Linguistics.
Cite (Informal):
DPR at SemEval-2021 Task 8: Dynamic Path Reasoning for Measurement Relation Extraction (Pouran Ben Veyseh et al., SemEval 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2021.semeval-1.47.pdf