Greaselm: Graph reasoning enhanced language models for question answering

X Zhang, A Bosselut, M Yasunaga, H Ren… - arXiv preprint arXiv …, 2022 - arxiv.org
Answering complex questions about textual narratives requires reasoning over both stated
context and the world knowledge that underlies it. However, pretrained language models …

Representation learning for knowledge fusion and reasoning in Cyber–Physical–Social Systems: Survey and perspectives

J Yang, LT Yang, H Wang, Y Gao, Y Zhao, X Xie, Y Lu - Information Fusion, 2023 - Elsevier
The digital deep integration of cyber space, physical space and social space facilitates the
formation of Cyber–Physical–Social Systems (CPSS). Knowledge empowers CPSS to be …

Scienceworld: Is your agent smarter than a 5th grader?

R Wang, P Jansen, MA Côté… - arXiv preprint arXiv …, 2022 - arxiv.org
We present ScienceWorld, a benchmark to test agents' scientific reasoning abilities in a new
interactive text environment at the level of a standard elementary school science curriculum …

Hierarchy-aware multi-hop question answering over knowledge graphs

J Dong, Q Zhang, X Huang, K Duan, Q Tan… - Proceedings of the ACM …, 2023 - dl.acm.org
Knowledge graphs (KGs) have been widely used to enhance complex question answering
(QA). To understand complex questions, existing studies employ language models (LMs) to …

Joint reasoning with knowledge subgraphs for Multiple Choice Question Answering

Q Zhang, S Chen, M Fang, X Chen - Information Processing & …, 2023 - Elsevier
Humans are able to reason from multiple sources to arrive at the correct answer. In the
context of Multiple Choice Question Answering (MCQA), knowledge graphs can provide …

Interpretable AMR-based question decomposition for multi-hop question answering

Z Deng, Y Zhu, Y Chen, M Witbrock… - arXiv preprint arXiv …, 2022 - arxiv.org
Effective multi-hop question answering (QA) requires reasoning over multiple scattered
paragraphs and providing explanations for answers. Most existing approaches cannot …

A siamese neural network for learning semantically-informed sentence embeddings

N Bölücü, B Can, H Artuner - Expert Systems with Applications, 2023 - Elsevier
Semantic representation is a way of expressing the meaning of a text that can be processed
by a machine to serve a particular natural language processing (NLP) task that usually …

Emotion classification in texts over graph neural networks: Semantic representation is better than syntactic

I Ameer, N Bölücü, G Sidorov, B Can - IEEE Access, 2023 - ieeexplore.ieee.org
Social media is a widely used platform that provides a huge amount of user-generated
content that can be processed to extract information about users' emotions. This has …

Assessing the Cross-linguistic Utility of Abstract Meaning Representation

S Wein, N Schneider - Computational Linguistics, 2024 - direct.mit.edu
Semantic representations capture the meaning of a text. Abstract Meaning Representation
(AMR), a type of semantic representation, focuses on predicate-argument structure and …

Exploiting reasoning chains for multi-hop science question answering

W Xu, Y Deng, H Zhang, D Cai, W Lam - arXiv preprint arXiv:2109.02905, 2021 - arxiv.org
We propose a novel Chain Guided Retriever-reader ({\tt CGR}) framework to model the
reasoning chain for multi-hop Science Question Answering. Our framework is capable of …