← Back to papers
2022 COLING COLING 2022

Noun-MWP: Math Word Problems Meet Noun Answers

Abstract

AbstractWe introduce a new type of problems for math word problem (MWP) solvers, named Noun-MWPs, whose answer is a non-numerical string containing a noun from the problem text. We present a novel method to empower existing MWP solvers to handle Noun-MWPs, and apply the method on Expression-Pointer Transformer (EPT). Our model, N-EPT, solves Noun-MWPs significantly better than other models, and at the same time, solves conventional MWPs as well. Solving Noun-MWPs may lead to bridging MWP solvers and traditional question-answering NLP models.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Deep Learning and Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — expression pointer
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Taehun Cha , Jaeheun Jung , Donghun Lee

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Question Answering Machine Learning > Learning Types > Multi-Task Learning Artificial Intelligence > Core AI > Reasoning Machine Learning > Learning Types > Deep Learning

Keywords

question answering named entity recognition natural language understanding sequence-to-sequence learning named entity math word problem expression pointer expression-pointer transformer
Download PDF

Related papers

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation 2022
The Role of Context and Uncertainty in Shallow Discourse Parsing 2022
SelfMix: Robust Learning against Textual Label Noise with Self-Mixup Training 2022
Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification 2022
Repo4QA: Answering Coding Questions via Dense Retrieval on GitHub Repositories 2022