paper-with-me

Papers

Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems

2020-10-14 · EMNLP 2020 11 · Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, Liang Lin

A practical automatic textual math word problems (MWPs) solver should be able to solve various textual MWPs while most existing works only focused on one-unknown linear MWPs. Herein, we propose a simple but efficient method called Universal Expression Tree (UET) to make the first attempt to represent the equations of various MWPs uniformly. Then a semantically-aligned universal tree-structured solver (SAU-Solver) based on an encoder-decoder framework is proposed to resolve multiple types of MWPs in a unified model, benefiting from our UET representation. Our SAU-Solver generates a universal expression tree explicitly by deciding which symbol to generate according to the generated symbols' semantic meanings like human solving MWPs. Besides, our SAU-Solver also includes a novel subtree-level semanticallyaligned regularization to further enforce the semantic constraints and rationality of the generated expression tree by aligning with the contextual information. Finally, to validate the universality of our solver and extend the research boundary of MWPs, we introduce a new challenging Hybrid Math Word Problems dataset (HMWP), consisting of three types of MWPs. Experimental results on several MWPs datasets show that our model can solve universal types of MWPs and outperforms several state-of-the-art models.

📄 PDF Abstract BibTeX arXiv:2010.06823

Code (1)

QinJinghui/SAU-Solver 공식 구현 pytorch

Tasks

DecoderMathMath Word Problem Solving

Similar Papers 제목 키워드 기반

Accelerating Materials Discovery: Learning a Universal Representation of Chemical Processes for Cross-Domain Property Prediction

2025-11-26 · Mikhail Tsitsvero, Atsuyuki Nakao, Hisaki Ikebata arxiv

Experimental validation of chemical processes is slow and costly, limiting exploration in materials discovery. Machine learning can prioritize promising candidates, but existing data in patents and literature is heteroge…

Graph Neural Network

GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision

2026-03-10 · Lang Sun, Ronghao Fu, Zhuoran Duan, Haoran Liu 외 arxiv

While Vision-Language Models (VLMs) have significantly advanced remote sensing interpretation, enabling them to perform complex, step-by-step reasoning remains highly challenging. Recent efforts to introduce Chain-of-Tho…

Reinforcement Learning

The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank

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

Treebanks have traditionally included only text and were derived from written sources such as newspapers or the web. We introduce the Aligned Multimodal Movie Treebank, an English language treebank derived from naturalis…

Aligning the Norwegian UD Treebank with Entity and Coreference Information

2023-05-22 · Tollef Emil Jørgensen, Andre Kåsen

This paper presents a merged collection of entity and coreference annotated data grounded in the Universal Dependencies (UD) treebanks for the two written forms of Norwegian: Bokm{\aa}l and Nynorsk. The aligned and conve…

Expletives in Universal Dependency Treebanks

2018-11-01 · WS 2018 11 · Gosse Bouma, Jan Hajic, Dag Haug, Joakim Nivre 외

Although treebanks annotated according to the guidelines of Universal Dependencies (UD) now exist for many languages, the goal of annotating the same phenomena in a cross-linguistically consistent fashion is not always m…

Coreference ResolutionQuestion Answering