Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks

Endri Kacupaj, Joan Plepi, Kuldeep Singh, Harsh Thakkar, Jens Lehmann, Maria Maleshkova


Abstract
This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baselines averaged on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase is more than 20% compared to state of the art (SotA).
Anthology ID:
2021.eacl-main.72
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
850–862
Language:
URL:
https://aclanthology.org/2021.eacl-main.72
DOI:
10.18653/v1/2021.eacl-main.72
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.72.pdf
Code
 endrikacupaj/LASAGNE
Data
CSQA