Generalizing Math Word Problem Solvers via Solution Diversification

نویسندگان

چکیده

Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-problem; one-solution) pairs, each of which is made a description and solution showing reasoning flow to get correct answer. However, one MWP naturally has multiple equations. The training an solver with pairs excludes other solutions, thus limits generalizability solver. One feasible this limitation augment solutions given problem. it difficult collect diverse accurate through human efforts. In paper, we design new framework for introducing buffer discriminator. includes generated encourage data diversity. discriminator controls quality buffered participate in training. Our flexibly applicable wide setting fully, semi-weakly weakly supervised all solvers. We conduct extensive experiments on benchmark dataset Math23k named Weak12k, show that our improves performance various under different settings generating solutions.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

MAWPS: A Math Word Problem Repository

Recent work across several AI subdisciplines has focused on automatically solving math word problems. In this paper we introduce MAWPS, an online repository of Math Word Problems, to provide a unified testbed to evaluate different algorithms. MAWPS allows for the automatic construction of datasets with particular characteristics, providing tools for tuning the lexical and template overlap of a ...

متن کامل

Generalizing Word Lattice Translation

Word lattice decoding has proven useful in spoken language translation; we argue that it provides a compelling model for translation of text genres, as well. We show that prior work in translating lattices using finite state techniques can be naturally extended to more expressive synchronous context-free grammarbased models. Additionally, we resolve a significant complication that non-linear wo...

متن کامل

Explanation Generation for a Math Word Problem Solver

Background Machine Reading (MR) aims to make the knowledge contained in the text available in forms that machines can use them for automated processing. That is, machines will learn to read from a few examples and they will read to learn what they need in order to answer questions or perform some reasoning task [1]. Since a domain-independent MR system is difficult to build, the Math Word Probl...

متن کامل

A Meaning-based Statistical English Math Word Problem Solver

We introduce MeSys, a meaning-based approach to solving English math word problems (MWPs) via understanding and reasoning in this paper. It first analyzes the text, transforms both body and question parts into their corresponding logic forms, and then performs inference on them. The associated context of each quantity is represented with proposed role-tags (e.g., nsubj, verb, etc.), which provi...

متن کامل

Characterizing Solution for Stock Portfolio Problem via Pythagorean Fuzzy Approach

The portfolio optimization is one of the fundamental problems in asset management that aims to reduce the risk of an investment by diversifying it into assets expected to fluctuate independently. A portfolio is a grouping of financial assets such as stocks, bonds, commodities, currencies and cash equivalents, as well as their funds counterparts, including mutual, exchange- traded and closed fun...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence

سال: 2023

ISSN: ['2159-5399', '2374-3468']

DOI: https://doi.org/10.1609/aaai.v37i11.26548