2026-07-24T11:44:01Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:14577 2024-03-06T10:31:29Z ddc:004 open_access

Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning Hong, Suk Joon Bennett, Brandon Commonsense Reasoning Winograd Schema Challenge Knowledge-based Reasoning Machine Learning Semantics 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. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Suk Joon Hong and Brandon Bennett 2021 Is Part Of OASIcs, Volume 93, 3rd Conference on Language, Data and Knowledge (LDK 2021) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.LDK.2021.41 urn:nbn:de:0030-drops-145779 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.LDK.2021.41 eng https://creativecommons.org/licenses/by/4.0/legalcode