Mining Paraphrasal Typed Templates from a Plain Text Corpus

Abstract

Finding paraphrases in text is an important task with implications for generation, summarization and question answering, among other applications. Of particular interest to those applications is the specific formulation of the task where the paraphrases are templated, which provides an easy way to lexicalize one message in multiple ways by simply plugging in the relevant entities. Previous work has focused on mining paraphrases from parallel and comparable corpora, or mining very short sub-sentence synonyms and paraphrases. In this paper we present an approach which combines distributional and KB-driven methods to allow robust mining of sentence-level paraphrasal templates, utilizing a rich type system for the slots, from a plain text corpus.

How to Make Neural Natural Language Generation as Reliable as Templates in Task-Oriented Dialogue

“…An alternate approach, which we did not compare with, is automatic template generation (Biran et al, 2016;Wiseman et al, 2018). However, as with neural generation, when applied to the E2E task it has issues with reliability.…”

Siamese Networks for Semantic Pattern Similarity

“…In addition to work on the STS task, which is briefly surveyed in the previous section, some relevent work exists in the context of paraphrasing. [12] mine paraphrasal templates -groups of concrete textual templates which would be paraphrases if filled with the same entities -from Wikipedia. Their approach relies on first finding and removing entities, and then clustering the remaining templates in a lexical vector space.…”

Monolingual Phrase Alignment on Parse Forests

“…Due to the large amount of sentence-level paraphrases collected (Dolan et al, 2004;Cohn et al, 2008;Heilman and Smith, 2010;Yin and Schütze, 2015;Biran et al, 2016), researchers can identify phrasal correspondences for natural language inferences (MacCartney et al, 2008;Thadani et al, 2012;Yao et al, 2013). Current methods extend word alignments to phrases in accordance with the methods in statistical machine translation.…”