Induction of Word and Phrase Alignments for Automatic Document Summarization

TL;DR

This paper introduces an unsupervised hidden Markov model approach to automatically align words and phrases between documents and their abstracts, aiming to enhance the development of linguistically informed summarization models.

Contribution

It presents a novel unsupervised model for word and phrase alignment in document-abstract pairs, facilitating richer training data for advanced summarization algorithms.

Findings

Model reliably identifies word-level alignments

Model effectively captures phrase correspondences

Alignments improve summarization training data quality

Abstract

Current research in automatic single document summarization is dominated by two effective, yet naive approaches: summarization by sentence extraction, and headline generation via bag-of-words models. While successful in some tasks, neither of these models is able to adequately capture the large set of linguistic devices utilized by humans when they produce summaries. One possible explanation for the widespread use of these models is that good techniques have been developed to extract appropriate training data for them from existing document/abstract and document/headline corpora. We believe that future progress in automatic summarization will be driven both by the development of more sophisticated, linguistically informed models, as well as a more effective leveraging of document/abstract corpora. In order to open the doors to simultaneously achieving both of these goals, we have developed techniques for automatically producing word-to-word and phrase-to-phrase alignments between documents and their human-written abstracts. These alignments make explicit the correspondences that exist in such document/abstract pairs, and create a potentially rich data source from which complex summarization algorithms may learn. This paper describes experiments we have carried out to analyze the ability of humans to perform such alignments, and based on these analyses, we describe experiments for creating them automatically. Our model for the alignment task is based on an extension of the standard hidden Markov model, and learns to create alignments in a completely unsupervised fashion. We describe our model in detail and present experimental results that show that our model is able to learn to reliably identify word- and phrase-level alignments in a corpus of <document,abstract> pairs.