A neural approach for detecting inline mathematical expressions from scientific documents

Madisetty, Sreekanth and Maurya, Kaushal Kumar and Aizawa, Akiko and Desarkar, Maunendra Sankar (2021) A neural approach for detecting inline mathematical expressions from scientific documents. Expert Systems, 38 (4). ISSN 0266-4720

Full text not available from this repository. (Request a copy)

Abstract

Scientific documents generally contain multiple mathematical expressions in them. Detecting inline mathematical expressions are one of the most important and challenging tasks in scientific text mining. Recent works that detect inline mathematical expressions in scientific documents have looked at the problem from an image processing perspective. There is little work that has targeted the problem from NLP perspective. Towards this, we define a few features and applied Conditional Random Fields (CRF) to detect inline mathematical expressions in scientific documents. Apart from this feature based approach, we also propose a hybrid algorithm that combines Bidirectional Long Short Term Memory networks (Bi-LSTM) and feature-based approach for this task. Experimental results suggest that this proposed hybrid method outperforms several baselines in the literature and also individual methods in the hybrid approach.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Madisetty, Sreekanth	UNSPECIFIED
Maurya, Kaushal Kumar	UNSPECIFIED
Desarkar, Maunendra Sankar	UNSPECIFIED

Item Type:

Article

Uncontrolled Keywords:

Conditional random field; Feature based approaches; Hybrid algorithms; Hybrid approach; Mathematical expressions; Scientific documents; Scientific texts; Short term memory;Image processing; Natural language processing systems; Random processes; Text mining

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

10 Aug 2021 04:13

Last Modified:

10 Aug 2021 04:13

URI:

http://raiithold.iith.ac.in/id/eprint/8777