mlsanityData to 14 Oct 2026

Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data

arXiv 2210.17122 ↗First posted 31 Oct 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Inspired by early research on exploring naturally annotated data for Chinese word segmentation (CWS), and also by recent research on integration of speech and text processing, this work for the first time proposes to mine word boundaries from parallel speech/text data. First we collect parallel speech/text data from two Internet sources that are related with CWS data used in our experiments. Then, we obtain character-level alignments and design simple heuristic rules for determining word boundaries according to pause duration between adjacent characters. Finally, we present an effective complete-then-train strategy that can better utilize extra naturally annotated data for model training. Experiments demonstrate our approach can significantly boost CWS performance in both cross-domain and low-resource scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 39 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

14 of 39 references.

References · 14

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  7. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 546
  8. 2020End-to-end Named Entity Recognition from English Speechcited by 36
  9. 2021Why does CTC result in peaky behavior?cited by 33
  10. 2022AISHELL-NER: Named Entity Recognition from Chinese Speechcited by 19
  11. 2019Toward Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learningcited by 11
  12. 2018State-of-the-art Chinese Word Segmentation with Bi-LSTMscited by 10
2 more
  1. 2022Towards Relation Extraction From Speechcited by 10
  2. 2021Masked Conditional Random Fields for Sequence Labelingcited by 6

Built on by

Not cited yet.