Automated Utterance Generation
This addresses the need for automated utterance generation to reduce manual effort in conversational AI, though it appears incremental as it builds on existing techniques like summarization and paraphrasing.
The paper tackles the problem of generating relevant utterances from knowledge base articles to improve conversational AI assistants, proposing an automated system that uses extractive summarization, paraphrasing techniques, and a novel selection algorithm to create diverse candidate utterances.
Conversational AI assistants are becoming popular and question-answering is an important part of any conversational assistant. Using relevant utterances as features in question-answering has shown to improve both the precision and recall for retrieving the right answer by a conversational assistant. Hence, utterance generation has become an important problem with the goal of generating relevant utterances (sentences or phrases) from a knowledge base article that consists of a title and a description. However, generating good utterances usually requires a lot of manual effort, creating the need for an automated utterance generation. In this paper, we propose an utterance generation system which 1) uses extractive summarization to extract important sentences from the description, 2) uses multiple paraphrasing techniques to generate a diverse set of paraphrases of the title and summary sentences, and 3) selects good candidate paraphrases with the help of a novel candidate selection algorithm.