Investigating Math Word Problems using Pretrained Multilingual Language Models
By Minghuan Tan, Lei Wang, Lingxiao Jiang, Jing Jiang. 2021
36 citations recorded by the source corpus.
In this paper, we revisit math word problems (MWPs) from the cross-lingual and multilingual perspective. We construct our MWP solvers over pretrained multilingual language models using the sequence-to-sequence model with copy mechanism. We compare how the MWP solvers perform in cross-lingual and multilingual scenarios. To facilitate the comparison of cross-lingual performance, we first adapt the large-scale English dataset MathQA as a counterpart of the Chinese dataset Math23K. Then we extend several English datasets to bilingual datasets through machine translation plus human annotation. Our experiments show that the MWP solvers may not be transferred to a different language even if the target expressions share the same numerical constants and operator set. However, it can be better generalized if problem types exist on both source language and target language.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Natural Language Processing
Citations in the corpus
- MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers (2021, methodology): “, 2021), multilingual pre-trained based methods (Tan et al., 2021), and solvers using external information and signals (Liang and Zhang; Wu et al.”
- Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, methodology): “GroupAttn (Li et al., 2019) 69.5 66.9 mBERT-LSTM (Tan et al., 2021) 75.1 - BERT-BERT (Lan et al., 2021) - 76.6 Roberta-Roberta (Lan et al., 2021) - 76.9 S 2 T / G 2 T GTS (Xie and Sun, 2019) 75.6 74.3 KA-S2T† (Wu et al., 2020) 76.3 - MultiE&D (Shen and Jin, 2020) 78.4 76.9 Graph2Tree (Zhang et al.,…”
- Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems (2021, unknown): “For brevity, we denote these node embeddings as ( e, e + , e − ) and the contrastive learning loss becomes: The "MathQA † " is the adapted MathQA dataset by following Tan et al. (2021). where sim ( · ) is the cosine similarity, and the η is a margin hyper-parameter.”