Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs

Wan-Hsuan Lin, Chun-Shien Lu


Abstract
This paper proposes a novel miscellaneous-context-based method to convert a sentence into a knowledge embedding in the form of a directed graph. We adopt the idea of conceptual graphs to frame for the miscellaneous textual information into conceptual compactness. We first empirically observe that this graph representation method can (1) accommodate the slot-filling challenges in typical question answering and (2) access to the sentence-level graph structure in order to explicitly capture the neighbouring connections of reference concept nodes. Secondly, we propose a task-agnostic semantics-measured module, which cooperates with the graph representation method, in order to (3) project an edge of a sentence-level graph to the space of semantic relevance with respect to the corresponding concept nodes. As a result of experiments on the QA-type relation extraction, the combination of the graph representation and the semantics-measured module achieves the high accuracy of answer prediction and offers human-comprehensible graphical interpretation for every well-formed sample. To our knowledge, our approach is the first towards the interpretable process of learning vocabulary representations with the experimental evidence.
Anthology ID:
2020.coling-main.240
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2665–2675
Language:
URL:
https://aclanthology.org/2020.coling-main.240
DOI:
10.18653/v1/2020.coling-main.240
Bibkey:
Cite (ACL):
Wan-Hsuan Lin and Chun-Shien Lu. 2020. Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2665–2675, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs (Lin & Lu, COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.240.pdf
Data
FrameNetQA-SRLWikiReadingdecaNLP