Abstractive summarization with deep reinforcement learning using semantic similarity rewards

Beken Fikri, Figen and Oflazer, Kemal and Yanıkoğlu, Berrin (2024) Abstractive summarization with deep reinforcement learning using semantic similarity rewards. Natural Language Engineering, 30 (3). pp. 554-576. ISSN 1351-3249 (Print) 1469-8110 (Online)

This is the latest version of this item.

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

Abstract

Abstractive summarization is an approach to document summarization that is not limited to selecting sentences from the document but can generate new sentences as well. We address the two main challenges in abstractive summarization: how to evaluate the performance of a summarization model and what is a good training objective. We first introduce new evaluation measures based on the semantic similarity of the input and corresponding summary. The similarity scores are obtained by the fine-tuned BERTurk model using either the cross-encoder or a bi-encoder architecture. The fine-tuning is done on the Turkish Natural Language Inference and Semantic Textual Similarity benchmark datasets. We show that these measures have better correlations with human evaluations compared to Recall-Oriented Understudy for Gisting Evaluation (ROUGE) scores and BERTScore. We then introduce a deep reinforcement learning algorithm that uses the proposed semantic similarity measures as rewards, together with a mixed training objective, in order to generate more natural summaries in terms of human readability. We show that training with a mixed training objective function compared to only the maximum-likelihood objective improves similarity scores.
Item Type: Article
Uncontrolled Keywords: Abstractive summarization; Deep reinforcement learning; Evaluation metric; Natural Language Inference; Semantic textual similarity
Divisions: Center of Excellence in Data Analytics
Faculty of Engineering and Natural Sciences
Depositing User: Figen Beken Fikri
Date Deposited: 24 Sep 2024 22:46
Last Modified: 24 Sep 2024 22:46
URI: https://research.sabanciuniv.edu/id/eprint/50123

Available Versions of this Item

Actions (login required)

View Item
View Item