Table Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction

Pankaj Gupta, Hinrich Schütze, Bernt Andrassy


Abstract
This paper proposes a novel context-aware joint entity and word-level relation extraction approach through semantic composition of words, introducing a Table Filling Multi-Task Recurrent Neural Network (TF-MTRNN) model that reduces the entity recognition and relation classification tasks to a table-filling problem and models their interdependencies. The proposed neural network architecture is capable of modeling multiple relation instances without knowing the corresponding relation arguments in a sentence. The experimental results show that a simple approach of piggybacking candidate entities to model the label dependencies from relations to entities improves performance. We present state-of-the-art results with improvements of 2.0% and 2.7% for entity recognition and relation classification, respectively on CoNLL04 dataset.
Anthology ID:
C16-1239
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
2537–2547
Language:
URL:
https://aclanthology.org/C16-1239
DOI:
Bibkey:
Cite (ACL):
Pankaj Gupta, Hinrich Schütze, and Bernt Andrassy. 2016. Table Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2537–2547, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Table Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction (Gupta et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/C16-1239.pdf
Code
 pgcool/TF-MTRNN