Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs

Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes


Abstract
Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extractively select portions of web text as input to Sequence-to-Sequence models using methods such as TF-IDF ranking. We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy. We show that by linearizing the graph into a structured input sequence, models can encode the graph representations within a standard Sequence-to-Sequence setting. For two generative tasks with very long text input, long-form question answering and multi-document summarization, feeding graph representations as input can achieve better performance than using retrieved text portions.
Anthology ID:
D19-1428
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4186–4196
Language:
URL:
https://aclanthology.org/D19-1428
DOI:
10.18653/v1/D19-1428
Bibkey:
Cite (ACL):
Angela Fan, Claire Gardent, Chloé Braud, and Antoine Bordes. 2019. Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4186–4196, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs (Fan et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/D19-1428.pdf
Attachment:
 D19-1428.Attachment.zip
Data
ELI5WebTextWikiSum