paper-with-me

홈 › Papers

Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models

2021-12-12 · Yu Feng, Jing Zhang, Xiaokang Zhang, Lemao Liu, Cuiping Li, Hong Chen

Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions. This paper proposes a new embedding-based KBQA framework which particularly takes numerical reasoning into account. We present NumericalTransformer on top of NSM, a state-of-the-art embedding-based KBQA model, to create NT-NSM. To enable better training, we propose two pre-training tasks with explicit numerical-oriented loss functions on two generated training datasets and a template-based data augmentation method for enriching ordinal constrained QA dataset. Extensive experiments on KBQA benchmarks demonstrate that with the help of our training algorithm, NT-NSM is empowered with numerical reasoning skills and substantially outperforms the baselines in answering ordinal constrained questions.

📄 PDF Abstract BibTeX arXiv:2112.06109

Code (1)

ruckbreasoning/numkbqa pytorch

Tasks

Data AugmentationKnowledge Base Question AnsweringQuestion Answering

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Injecting Numerical Reasoning Skills into Language Models

2020-04-09 · ACL 2020 6 · Mor Geva, Ankit Gupta, Jonathan Berant

Large pre-trained language models (LMs) are known to encode substantial amounts of linguistic information. However, high-level reasoning skills, such as numerical reasoning, are difficult to learn from a language-modelin…

Data AugmentationDecoderLanguage ModelingLanguage Modelling+2

ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples

2022-10-22 · Yilun Zhao, Linyong Nan, Zhenting Qi, Rui Zhang 외

Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training methods perform well on understanding t…

Fact VerificationQuestion AnsweringSemantic ParsingTable-based Fact Verification+2

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation

2026-01-16 · Pingzhi Tang, Yiding Wang, Muhan Zhang arxiv

Large Language Models (LLMs) face the "knowledge cutoff" challenge, where their frozen parametric memory prevents direct internalization of new information. While Supervised Fine-Tuning (SFT) is commonly used to update m…

Reinforcement LearningQuestion Answering

MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving

2021-07-28 · Findings (NAACL) 2022 7 · Zhenwen Liang, Jipeng Zhang, Lei Wang, Wei Qin 외

Math word problem (MWP) solving faces a dilemma in number representation learning. In order to avoid the number representation issue and reduce the search space of feasible solutions, existing works striving for MWP solv…

Common Sense ReasoningLanguage ModelingLanguage ModellingMath+3

MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Math word problem (MWP) solving faces a dilemma in number representation learning. In order to avoid the number representation issue and reduce the search space of feasible solutions, existing works striving for MWP solv…

Language ModelingLanguage ModellingMathMath Word Problem Solving+2