A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering
Tahira Naseem, Srinivas Ravishankar, Nandana Mihindukulasooriya, Ibrahim Abdelaziz, Young-Suk Lee, Pavan Kapanipathi, Salim Roukos, Alfio Gliozzo
Abstract
Relation linking is a crucial component of Knowledge Base Question Answering systems. Existing systems use a wide variety of heuristics, or ensembles of multiple systems, heavily relying on the surface question text. However, the explicit semantic parse of the question is a rich source of relation information that is not taken advantage of. We propose a simple transformer-based neural model for relation linking that leverages the AMR semantic parse of a sentence. Our system significantly outperforms the state-of-the-art on 4 popular benchmark datasets. These are based on either DBpedia or Wikidata, demonstrating that our approach is effective across KGs.
BibTeX
@inproceedings{naseem-etal-2021-semantics,
title = "A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering",
author = "Naseem, Tahira and
Ravishankar, Srinivas and
Mihindukulasooriya, Nandana and
Abdelaziz, Ibrahim and
Lee, Young-Suk and
Kapanipathi, Pavan and
Roukos, Salim and
Gliozzo, Alfio and
Gray, Alexander",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.34/",
doi = "10.18653/v1/2021.acl-short.34",
pages = "256--262"
}