A Semantic Approach to Summarization
This addresses the problem of producing more intuitive and semantically rich summaries for users in natural language processing, though it appears incremental as it builds on existing semantic resources.
The paper tackles the limitations of sentence extraction in text summarization by introducing a semantic approach that uses WordNet and semantic role labeling to generate summaries, achieving evaluation against human-composed summaries.
Sentence extraction based summarization methods has some limitations as it doesn't go into the semantics of the document. Also, it lacks the capability of sentence generation which is intuitive to humans. Here we present a novel method to summarize text documents taking the process to semantic levels with the use of WordNet and other resources, and using a technique for sentence generation. We involve semantic role labeling to get the semantic representation of text and use of segmentation to form clusters of the related pieces of text. Picking out the centroids and sentence generation completes the task. We evaluate our system against human composed summaries and also present an evaluation done by humans to measure the quality attributes of our summaries.