Exploring Sentence Vector Spaces through Automatic Summarization
This work provides insights into sentence embeddings for summarization, with potential applications in broader uses of sentence embeddings, but it is incremental as it builds on existing methods for sentence vector computation.
The paper tackles the problem of understanding the internal structure and properties of sentence vectors in automatic summarization, showing that cosine similarity between sentence and document vectors correlates with sentence importance and that vector semantics can identify and correct gaps in summaries, with specific dimensions linked to effective summaries.
Given vector representations for individual words, it is necessary to compute vector representations of sentences for many applications in a compositional manner, often using artificial neural networks. Relatively little work has explored the internal structure and properties of such sentence vectors. In this paper, we explore the properties of sentence vectors in the context of automatic summarization. In particular, we show that cosine similarity between sentence vectors and document vectors is strongly correlated with sentence importance and that vector semantics can identify and correct gaps between the sentences chosen so far and the document. In addition, we identify specific dimensions which are linked to effective summaries. To our knowledge, this is the first time specific dimensions of sentence embeddings have been connected to sentence properties. We also compare the features of different methods of sentence embeddings. Many of these insights have applications in uses of sentence embeddings far beyond summarization.