Searching for Mathematical Formulas Based on Graph Representation Learning

Song, Yujin; Chen, Xiaoyu

doi:10.1007/978-3-030-81097-9_11

Cited by 4 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, data-driven approaches which incorporate classic word embeddings (Gao et al, 2017;Mansouri et al, 2019), GNN (Song and Chen, 2021) or transformer models Reusch et al, 2021a,b) have also been proposed for the MIR domain. By observing token co-occurrence during training, these models can easily discover synonyms, equivalent mathematically transformed formulas, or high-level semantic similarities, making them a good enhancement for structure search approaches.…”

Section: Data-driven Methodsmentioning

confidence: 99%

Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval

Wang¹,

Yang²,

Lin³

2022

Preprint

View full text Add to dashboard Cite

With the recent success of dense retrieval methods based on bi-encoders, a number of studies have applied this approach to various interesting downstream retrieval tasks with good efficiency and in-domain effectiveness. Recently, we have also seen the presence of dense retrieval models in Math Information Retrieval (MIR) tasks, but the most effective systems remain "classic" retrieval methods that consider rich structure features. In this work, we try to combine the best of both worlds: a well-defined structure search method for effective formula search and biencoder dense retrieval models to capture contextual similarities in mathematical documents. Specifically, we have evaluated two representative bi-encoder models (ColBERT and DPR) for token-level and passage-level dense retrieval on recent MIR tasks. To our best knowledge, this is the first time a DPR model has been evaluated in the MIR domain. Our result shows that bi-encoder models are complementary to existing structure search methods, and we are able to advance the state of the art on a recent MIR dataset. We have made our model checkpoints and source code publicly available for the reproduction of our results. 1

show abstract

Section: Data-driven Methodsmentioning

confidence: 99%

Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval

Wang¹,

Yang²,

Lin³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For math word problems, RNN [3] and Transformer [18] have been utilized to encode the mathematical text and generate the math equation. For mathematical information retrieval, graph neural networks [30] have been adopted to learn meaningful representations over the structured formulas. Recently, the success of PLMs [22,24] pushes forward the understanding and modeling of mathematical texts, due to the excellent capacity of language modeling.…”

Section: Related Workmentioning

confidence: 99%

JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding

Zhao,

Zhou,

Gong

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model (PLM) for effectively understanding and representing mathematical problems. Unlike other standard NLP tasks, mathematical texts are difficult to understand, since they involve mathematical terminology, symbols and formulas in the problem statement. Typically, it requires complex mathematical logic and background knowledge for solving mathematical problems.

show abstract

JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding

Zhao¹,

Zhou²,

Gong³

et al. 2022

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Searching for Mathematical Formulas Based on Graph Representation Learning

Cited by 4 publications

References 22 publications

Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval

Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval

JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding

JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding

Contact Info

Product

Resources

About