Dense Paraphrasing for Textual Enrichment
This addresses the challenge of textual understanding for NLP applications, but it appears incremental as it builds on existing paraphrasing and enrichment techniques.
The paper tackles the problem of improving inferencing and question answering by introducing Dense Paraphrasing (DP), a method to rewrite text to reduce ambiguity and make implicit semantics explicit, and presents results showing it enhances performance on these tasks.
Understanding inferences and answering questions from text requires more than merely recovering surface arguments, adjuncts, or strings associated with the query terms. As humans, we interpret sentences as contextualized components of a narrative or discourse, by both filling in missing information, and reasoning about event consequences. In this paper, we define the process of rewriting a textual expression (lexeme or phrase) such that it reduces ambiguity while also making explicit the underlying semantics that is not (necessarily) expressed in the economy of sentence structure as Dense Paraphrasing (DP). We build the first complete DP dataset, provide the scope and design of the annotation task, and present results demonstrating how this DP process can enrich a source text to improve inferencing and QA task performance. The data and the source code will be publicly available.