Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization

TL;DR

This paper introduces SemSentSum, a data-driven model that constructs sentence semantic relation graphs using universal and domain-specific embeddings, improving multi-document summarization without relying on hand-crafted features or extra annotated data.

Contribution

The paper presents the first use of multiple sentence embeddings for multi-document summarization, enabling a fully data-driven approach that is adaptable and does not require additional annotated data.

Findings

Achieves competitive summarization results on benchmark datasets.

Eliminates the need for hand-crafted features and annotated data.

Demonstrates adaptability to other tasks.

Abstract

Linking facts across documents is a challenging task, as the language used to express the same information in a sentence can vary significantly, which complicates the task of multi-document summarization. Consequently, existing approaches heavily rely on hand-crafted features, which are domain-dependent and hard to craft, or additional annotated data, which is costly to gather. To overcome these limitations, we present a novel method, which makes use of two types of sentence embeddings: universal embeddings, which are trained on a large unrelated corpus, and domain-specific embeddings, which are learned during training. To this end, we develop SemSentSum, a fully data-driven model able to leverage both types of sentence embeddings by building a sentence semantic relation graph. SemSentSum achieves competitive results on two types of summary, consisting of 665 bytes and 100 words. Unlike other state-of-the-art models, neither hand-crafted features nor additional annotated data are necessary, and the method is easily adaptable for other tasks. To our knowledge, we are the first to use multiple sentence embeddings for the task of multi-document summarization.