License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.LDK.2021.41
URN: urn:nbn:de:0030-drops-145779
URL: https://drops.dagstuhl.de/opus/volltexte/2021/14577/
Go to the corresponding OASIcs Volume Portal


Hong, Suk Joon ; Bennett, Brandon

Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning

pdf-format:
OASIcs-LDK-2021-41.pdf (0.6 MB)


Abstract

The Winograd Schema Challenge (WSC) is a commonsense reasoning task that requires background knowledge. In this paper, we contribute to tackling WSC in four ways. Firstly, we suggest a keyword method to define a restricted domain where distinctive high-level semantic patterns can be found. A thanking domain was defined by keywords, and the data set in this domain is used in our experiments. Secondly, we develop a high-level knowledge-based reasoning method using semantic roles which is based on the method of Sharma [Sharma, 2019]. Thirdly, we propose an ensemble method to combine knowledge-based reasoning and machine learning which shows the best performance in our experiments. As a machine learning method, we used Bidirectional Encoder Representations from Transformers (BERT) [Jacob Devlin et al., 2018; Vid Kocijan et al., 2019]. Lastly, in terms of evaluation, we suggest a "robust" accuracy measurement by modifying that of Trichelair et al. [Trichelair et al., 2018]. As with their switching method, we evaluate a model by considering its performance on trivial variants of each sentence in the test set.

BibTeX - Entry

@InProceedings{hong_et_al:OASIcs.LDK.2021.41,
  author =	{Hong, Suk Joon and Bennett, Brandon},
  title =	{{Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning}},
  booktitle =	{3rd Conference on Language, Data and Knowledge (LDK 2021)},
  pages =	{41:1--41:13},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-199-3},
  ISSN =	{2190-6807},
  year =	{2021},
  volume =	{93},
  editor =	{Gromann, Dagmar and S\'{e}rasset, Gilles and Declerck, Thierry and McCrae, John P. and Gracia, Jorge and Bosque-Gil, Julia and Bobillo, Fernando and Heinisch, Barbara},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2021/14577},
  URN =		{urn:nbn:de:0030-drops-145779},
  doi =		{10.4230/OASIcs.LDK.2021.41},
  annote =	{Keywords: Commonsense Reasoning, Winograd Schema Challenge, Knowledge-based Reasoning, Machine Learning, Semantics}
}

Keywords: Commonsense Reasoning, Winograd Schema Challenge, Knowledge-based Reasoning, Machine Learning, Semantics
Collection: 3rd Conference on Language, Data and Knowledge (LDK 2021)
Issue Date: 2021
Date of publication: 30.08.2021
Supplementary Material: Software (Source Code): https://github.com/hsjplus/high-level-kb-reasoning archived at: https://archive.softwareheritage.org/swh:1:dir:bf9138cbf3a41a02809ac1de2dea41d499b9198e


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI