Papers › Fusing Context Into Knowledge Graph for Commonsense Question Answering

Fusing Context Into Knowledge Graph for Commonsense Question Answering

9 Dec 2020Findings (ACL) 2021 8arXiv:2012.04808archive 2025-07-28

Yichong Xu, Chenguang Zhu, Ruochen Xu, Yang Liu, Michael Zeng, Xuedong Huang

Commonsense question answering (QA) requires a model to grasp commonsense and factual knowledge to answer questions about world events. Many prior methods couple language modeling with knowledge graphs (KG). However, although a KG contains rich structural information, it lacks the context to provide a more precise understanding of the concepts. This creates a gap when fusing knowledge graphs into language modeling, especially when there is insufficient labeled data. Thus, we propose to employ external entity descriptions to provide contextual information for knowledge understanding. We retrieve descriptions of related concepts from Wiktionary and feed them as additional input to pre-trained language models. The resulting model achieves state-of-the-art result in the CommonsenseQA dataset and the best result among non-generative models in OpenBookQA.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

microsoft/DEKCOR-CommonsenseQA officialmentioned in papermentioned on GitHubpytorch report
microsoft/kear mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Common Sense ReasoningKnowledge GraphsLanguage ModelingLanguage ModellingQuestion AnsweringRelational Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Common Sense Reasoning CommonsenseQA DEKCOR Accuracy 83.3 #5 of 38 Archive leaderboard report
Question Answering OpenBookQA TTTTT 3B Accuracy 83.2 #18 of 45 Archive leaderboard report
Question Answering OpenBookQA DEKCOR Accuracy 82.4 #22 of 45 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections