SMDDH: Singleton Mention detection using Deep Learning in Hindi Text

TL;DR

This paper introduces a deep learning-based module for detecting singleton mentions in Hindi text, which enhances coreference resolution by filtering non-coreferential mentions.

Contribution

It presents a novel singleton mention detection approach using neural networks tailored for Hindi, incorporating hand-crafted features and context information.

Findings

Achieved high precision, recall, and F-measure in experiments.

Utilized a Hindi dataset with 3.6K sentences and 78K tokens.

Improved coreference resolution performance by filtering singleton mentions.

Abstract

Mention detection is an important component of coreference resolution system, where mentions such as name, nominal, and pronominals are identified. These mentions can be purely coreferential mentions or singleton mentions (non-coreferential mentions). Coreferential mentions are those mentions in a text that refer to the same entities in a real world. Whereas, singleton mentions are mentioned only once in the text and do not participate in the coreference as they are not mentioned again in the following text. Filtering of these singleton mentions can substantially improve the performance of a coreference resolution process. This paper proposes a singleton mention detection module based on a fully connected network and a Convolutional neural network for Hindi text. This model utilizes a few hand-crafted features and context information, and word embedding for words. The coreference annotated Hindi dataset comprising of 3.6K sentences, and 78K tokens are used for the task. In terms of Precision, Recall, and F-measure, the experimental findings obtained are excellent.