Subsentence Extraction from Text Using Coverage-Based Deep Learning Language Models

TL;DR

This paper introduces a coverage-based deep learning method for subsentence extraction that improves sentiment prediction accuracy and can enhance various NLP tasks, supported by extensive experiments and shared resources.

Contribution

The paper presents a novel coverage-based deep learning approach for subsentence extraction, significantly outperforming existing methods in sentiment prediction tasks.

Findings

Outperforms state-of-the-art in subsentence prediction with higher Jaccard scores

Demonstrates effectiveness across multiple rigorous experiments

Provides publicly available datasets and software for reproducibility

Abstract

Sentiment prediction remains a challenging and unresolved task in various research fields, including psychology, neuroscience, and computer science. This stems from its high degree of subjectivity and limited input sources that can effectively capture the actual sentiment. This can be even more challenging with only text-based input. Meanwhile, the rise of deep learning and an unprecedented large volume of data have paved the way for artificial intelligence to perform impressively accurate predictions or even human-level reasoning. Drawing inspiration from this, we propose a coverage-based sentiment and subsentence extraction system that estimates a span of input text and recursively feeds this information back to the networks. The predicted subsentence consists of auxiliary information expressing a sentiment. This is an important building block for enabling vivid and epic sentiment delivery (within the scope of this paper) and for other natural language processing tasks such as text summarisation and Q&A. Our approach outperforms the state-of-the-art approaches by a large margin in subsentence prediction (i.e., Average Jaccard scores from 0.72 to 0.89). For the evaluation, we designed rigorous experiments consisting of 24 ablation studies. Finally, our learned lessons are returned to the community by sharing software packages and a public dataset that can reproduce the results presented in this paper.