XMQAs: Constructing Complex-Modified Question-Answering Dataset for Robust Question Understanding
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 …
Question Answering (KBQA) system. However, the existing study does not pay enough …
Towards robust numerical question answering: Diagnosing numerical capabilities of NLP systems
Numerical Question Answering is the task of answering questions that require numerical
capabilities. Previous works introduce general adversarial attacks to Numerical Question …
capabilities. Previous works introduce general adversarial attacks to Numerical Question …
DGR: Decomposition Graph Reconstruction for Question Understanding
To tackle the understanding of complex questions, Question Decomposition Meaning
Representation (QDMR) decomposes a complex question into a sequence of atomic simple …
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 …
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 …
Models (LLMs), numerical reasoning for machine reading comprehension remains a difficult …