2016 INTERSPEECH INTERSPEECH 2016

Beyond Utterance Extraction: Summary Recombination for Speech Summarization

Abstract

This paper describes a template filling approach for creating conversation summaries. The templates are generated from generalized summary fragments from a training corpus. Necessary pieces of information for filling them are extracted automatically from the conversation transcripts given linguistic features, and drive the fragment selection process. The approach obtains ROUGE-2 scores of 0.08471 on the RATP-DECODA corpus, which represents a significant improvement over extractive baselines and hand-written templates.

🚀 Conference Pioneer — INTERSPEECH 2016
🧭 Keyword Pioneer — speech summarization
🐣 Hot Topic Early Bird — natural language generation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio