Exploring the landscape of natural language processing research
As an efficient approach to understand, generate, and process natural language texts,
research in natural language processing (NLP) has exhibited a rapid spread and wide …
research in natural language processing (NLP) has exhibited a rapid spread and wide …
Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?
Compositionality is a pivotal property of symbolic reasoning. However, how well recent
neural models capture compositionality remains underexplored in the symbolic reasoning …
neural models capture compositionality remains underexplored in the symbolic reasoning …
Exploiting Relation-aware Attribute Representation Learning in Knowledge Graph Embedding for Numerical Reasoning
Numerical reasoning is an essential task for supporting machine learning applications, such
as recommendation and information retrieval. The reasoning task aims to compare two items …
as recommendation and information retrieval. The reasoning task aims to compare two items …
Improving compositional generalization for multi-step quantitative reasoning in question answering
A Nourbakhsh, C Jiao, S Shah… - Proceedings of the 2022 …, 2022 - aclanthology.org
Quantitative reasoning is an important aspect of question answering, especially when
numeric and verbal cues interact to indicate sophisticated, multi-step programs. In this …
numeric and verbal cues interact to indicate sophisticated, multi-step programs. In this …
Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question Answering
Numerical reasoning over text is a challenging subtask in question answering (QA) that
requires both the understanding of texts and numbers. However, existing language models …
requires both the understanding of texts and numbers. However, existing language models …
Towards preserving word order importance through Forced Invalidation
Large pre-trained language models such as BERT have been widely used as a framework
for natural language understanding (NLU) tasks. However, recent findings have revealed …
for natural language understanding (NLU) tasks. However, recent findings have revealed …
Empirical investigation of neural symbolic reasoning strategies
Neural reasoning accuracy improves when generating intermediate reasoning steps.
However, the source of this improvement is yet unclear. Here, we investigate and factorize …
However, the source of this improvement is yet unclear. Here, we investigate and factorize …
How Well Do Multi-hop Reading Comprehension Models Understand Date Information?
X Ho, S Sugawara, A Aizawa - arXiv preprint arXiv:2210.05208, 2022 - arxiv.org
Several multi-hop reading comprehension datasets have been proposed to resolve the
issue of reasoning shortcuts by which questions can be answered without performing multi …
issue of reasoning shortcuts by which questions can be answered without performing multi …
Knowledge and Pre-trained Language Models Inside and Out: a deep-dive into datasets and external knowledge
C Lyu - 2023 - doras.dcu.ie
Pre-trained Language Models (PLMs) have greatly advanced the performance of various
NLP tasks and have undoubtedly been serving as foundation models for this field. These pre …
NLP tasks and have undoubtedly been serving as foundation models for this field. These pre …
ChemAlgebra: Algebraic Reasoning on Chemical Reactions
While showing impressive performance on various kinds of learning tasks, it is yet unclear
whether deep learning models have the ability to robustly tackle reasoning tasks. Measuring …
whether deep learning models have the ability to robustly tackle reasoning tasks. Measuring …