Projects per year
Self-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing and disfluency detection in speech transcripts. Since the contextualized word embeddings are pre-trained on a large amount of unlabeled data, using additional unlabeled data to train a neural model might seem redundant. However, we show that self-training - a semi-supervised technique for incorporating unlabeled data - sets a new state-of-the-art for the self-attentive parser on disfluency detection, demonstrating that self-training provides benefits orthogonal to the pre-trained contextualized word representations. We also show that ensembling self-trained parsers provides further gains for disfluency detection.
|Title of host publication
|The 58th Annual Meeting of the Association for Computational Linguistics
|Subtitle of host publication
|Proceedings of the Conference
|Place of Publication
|Association for Computational Linguistics (ACL)
|Number of pages
|Published - 2020
|58th Annual Meeting of the Association for Computational Linguistics (ACL) -
Duration: 5 Jul 2020 → 10 Jul 2020
|58th Annual Meeting of the Association for Computational Linguistics (ACL)
|5/07/20 → 10/07/20
Bibliographical noteVersion archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.
FingerprintDive into the research topics of 'Improving disfluency detection by self-training a self-attentive model'. Together they form a unique fingerprint.
- 1 Finished