Transformer-based Lexically Constrained Headline Generation

TL;DR

This paper introduces a Transformer-based approach for lexically constrained headline generation that guarantees inclusion of a specified phrase, improving controllability and maintaining high-quality output.

Contribution

It proposes a novel Transformer method ensuring phrase inclusion and a new generation strategy, advancing controllable headline generation techniques.

Findings

Guaranteed phrase inclusion in headlines.

Comparable ROUGE scores to existing methods.

Improved generation strategy performance.

Abstract

This paper explores a variant of automatic headline generation methods, where a generated headline is required to include a given phrase such as a company or a product name. Previous methods using Transformer-based models generate a headline including a given phrase by providing the encoder with additional information corresponding to the given phrase. However, these methods cannot always include the phrase in the generated headline. Inspired by previous RNN-based methods generating token sequences in backward and forward directions from the given phrase, we propose a simple Transformer-based method that guarantees to include the given phrase in the high-quality generated headline. We also consider a new headline generation strategy that takes advantage of the controllable generation order of Transformer. Our experiments with the Japanese News Corpus demonstrate that our methods, which are guaranteed to include the phrase in the generated headline, achieve ROUGE scores comparable to previous Transformer-based methods. We also show that our generation strategy performs better than previous strategies.