paper-with-me

홈 › Papers

Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection

2021-09-13 · EMNLP 2021 11 · Priyanka Sen, Amir Saffari, Armin Oliya

End-to-end question answering using a differentiable knowledge graph is a promising technique that requires only weak supervision, produces interpretable results, and is fully differentiable. Previous implementations of this technique (Cohen et al., 2020) have focused on single-entity questions using a relation following operation. In this paper, we propose a model that explicitly handles multiple-entity questions by implementing a new intersection operation, which identifies the shared elements between two sets of entities. We find that introducing intersection improves performance over a baseline model on two datasets, WebQuestionsSP (69.6% to 73.3% Hits@1) and ComplexWebQuestions (39.8% to 48.7% Hits@1), and in particular, improves performance on questions with multiple entities by over 14% on WebQuestionsSP and by 19% on ComplexWebQuestions.

📄 PDF Abstract BibTeX arXiv:2109.05808

Code (1)

sid-sundrani/differentiable-kb-qa pytorch

Tasks

Knowledge GraphsQuestion Answering

Similar Papers 제목 키워드 기반

End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs

2021-09-13 · EMNLP 2021 11 · Armin Oliya, Amir Saffari, Priyanka Sen, Tom Ayoola

Recently, end-to-end (E2E) trained models for question answering over knowledge graphs (KGQA) have delivered promising results using only a weakly supervised dataset. However, these models are trained and evaluated in a …

Entity ResolutionKnowledge GraphsQuestion Answering

SABET-QA: Temporal Knowledge Graph Question Answering

2026-08-20 · Brahim Touayouch, Mirette Moawad, Dmitry Akulov arxiv

Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines. We pro…

Graph Question AnsweringKnowledge Graphs

Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering

2021-06-01 · NAACL 2021 4 · Kiran Ramnath, Leda Sari, Mark Hasegawa-Johnson, Chang Yoo

Although Question-Answering has long been of research interest, its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies. Towards these ends, we…

Knowledge GraphsQuestion AnsweringSpeech-to-TextSpoken Language Understanding+1

NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

2026-02-17 · Rong Fu, Yang Li, Zeyu Zhang, Jiekai Wu 외 arxiv

Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowledge-intensive queries that require precise, structured multi-hop inference. Kno…

Graph Question AnsweringKnowledge Graphs

Empowering Language Models with Knowledge Graph Reasoning for Question Answering

2022-11-15 · Ziniu Hu, Yichong Xu, Wenhao Yu, Shuohang Wang 외

Answering open-domain questions requires world knowledge about in-context entities. As pre-trained Language Models (LMs) lack the power to store all required knowledge, external knowledge sources, such as knowledge graph…

Knowledge GraphsLanguage ModelingLanguage ModellingQuestion Answering+1