Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization
This addresses the problem of costly and domain-dependent feature engineering in multi-document summarization for researchers and practitioners, though it is incremental as it builds on existing embedding techniques.
The paper tackles the challenge of linking facts across documents for multi-document summarization by introducing SemSentSum, a data-driven model that uses universal and domain-specific sentence embeddings to build semantic relation graphs, achieving competitive results on summaries of 665 bytes and 100 words without hand-crafted features or additional annotated data.
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.