XMQAs: Constructing Complex-Modified Question-Answering Dataset for Robust Question Understanding

Y Chen, Y Xiao, Z Li, B Liu - IEEE Transactions on Knowledge …, 2023 - ieeexplore.ieee.org
Question understanding is an important issue to the success of a Knowledge-based
Question Answering (KBQA) system. However, the existing study does not pay enough …

Towards robust numerical question answering: Diagnosing numerical capabilities of NLP systems

J Xu, M Zhou, X He, S Han, D Zhang - arXiv preprint arXiv:2211.07455, 2022 - arxiv.org
Numerical Question Answering is the task of answering questions that require numerical
capabilities. Previous works introduce general adversarial attacks to Numerical Question …

DGR: Decomposition Graph Reconstruction for Question Understanding

W Han, J Huang, Q Xie, M Peng - 2022 International Joint …, 2022 - ieeexplore.ieee.org
To tackle the understanding of complex questions, Question Decomposition Meaning
Representation (QDMR) decomposes a complex question into a sequence of atomic simple …

Learning to Reason over Natural Language via Accessing Diverse Knowledge Resources

X Yang - 2022 - search.proquest.com
Abstract Reasoning is the capability of drawing new conclusions from existing information or
knowledge, and it has been a central topic in artificial intelligence. Developing intelligent …

[PDF][PDF] Augmenting Large Language Models with Symbolic Rule Learning for Robust Numerical Reasoning

H Al-Negheimish, P Madhyastha… - The 3rd Workshop on … - mathai2023.github.io
While some prompting strategies have been proposed to elicit reasoning in Large Language
Models (LLMs), numerical reasoning for machine reading comprehension remains a difficult …