Using Pause Information for More Accurate Entity Recognition
Not on the map. Why?
Abstract (arXiv)
Entity tags in human-machine dialog are integral to natural language understanding (NLU) tasks in conversational assistants. However, current systems struggle to accurately parse spoken queries with the typical use of text input alone, and often fail to understand the user intent. Previous work in linguistics has identified a cross-language tendency for longer speech pauses surrounding nouns as compared to verbs. We demonstrate that the linguistic observation on pauses can be used to improve accuracy in machine-learnt language understanding tasks. Analysis of pauses in French and English utterances from a commercial voice assistant shows the statistically significant difference in pause duration around multi-token entity span boundaries compared to within entity spans. Additionally, in contrast to text-based NLU, we apply pause duration to enrich contextual embeddings to improve shallow parsing of entities. Results show that our proposed novel embeddings improve the relative error rate by up to 8% consistently across three domains for French, without any added annotation or alignment costs to the parser.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 20 references that are in the map. First posted on arXiv 27 Sep 2021.
Builds on
13 of 20 references.
References · 13
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
- 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 198
- 2018From Audio to Semantics: Approaches to end-to-end spoken language understandingcited by 63
- 2020Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representationcited by 59
- 2019Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognitioncited by 15
- 2019SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answeringcited by 11
- 2019BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognitioncited by 10
- 2020Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networkscited by 7
- 2020Noise Robust Named Entity Understanding for Voice Assistantscited by 5
- 2020SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understandingcited by 5
- 2017Sound-Word2Vec: Learning Word Representations Grounded in Soundscited by 4
1 more
Built on by
Citing papers per year: 2023: 1.
1 paper.