Sentence Segmentation and Disfluency Detection in Narrative Transcripts from Neuropsychological Tests

Treviso, Marcos; Aluísio, Sandra Maria

doi:10.1007/978-3-319-99722-3_41

Cited by 2 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our biggest departure from previous approaches lies in the parallel nature of inference and the deep bidirectional information flow of our model (for more detail, see Devlin et al 2019). This is in contrast with the vast majority of previous approaches which use a variant of Recurrent Neural Network architecture (Tundik et al, 2017;Vandeghinste et al, 2018;Ballesteros and Wanner, 2016;Alumäe et al, 2019;Szaszák, 2019;Öktem, 2018;Xu et al, 2016;Pahuja et al, 2017;Tundik and Szaszak, 2018;Tündik et al, 2017;Tilk and Alumae, 2015;Zelasko et al, 2018;Treviso and Aluísio, 2018). This includes those that incorporate acoustic information (B.…”

Section: Related Workmentioning

confidence: 96%

Efficient Automatic Punctuation Restoration Using Bidirectional Transformers with Robust Inference

Courtland¹,

Faulkner²,

McElvain³

2020

Proceedings of the 17th International Conference on Spoken Language Translation

View full text Add to dashboard Cite

Though people rarely speak in complete sentences, punctuation confers many benefits to the readers of transcribed speech. Unfortunately, most ASR systems do not produce punctuated output. To address this, we propose a solution for automatic punctuation that is both cost efficient and easy to train. Our solution benefits from the recent trend in fine-tuning transformer-based language models. We also modify the typical framing of this task by predicting punctuation for sequences rather than individual tokens, which makes for more efficient training and inference. Finally, we find that aggregating predictions across multiple context windows improves accuracy even further. Our best model achieves a new state of the art on benchmark data (TED Talks) with a combined F1 of 83.9, representing a 48.7% relative improvement (15.3 absolute) over the previous state of the art.

show abstract

Section: Related Workmentioning

confidence: 96%

Efficient Automatic Punctuation Restoration Using Bidirectional Transformers with Robust Inference

Courtland¹,

Faulkner²,

McElvain³

2020

Proceedings of the 17th International Conference on Spoken Language Translation

View full text Add to dashboard Cite

show abstract

“…Gillick [119] classified sentence boundary based on trigram, only incorporating a type-based method for difficult instances, which is less computationally expensive. Treviso et al [354] suggested word embedding as a more effective alternative for 𝑛-gram and type-based approaches, bypassing feature engineering. Furthering this direction, Knoll et al [169] utilized word-level and character-level neural networks to automatically extract morpholexical features.…”

Section: Discussionmentioning

confidence: 99%

“…All of the aforementioned SBD systems, with the exception of [166,167], use 𝑛-gram based technique to extract textual information, which leads to sparse vector space problems. To address this, Treviso et al [354] suggested word embedding as an alternative.…”

Section: Word-based Approachmentioning

confidence: 99%

Disentangling syntactics, semantics, and pragmatics in natural language processing

Zhang

View full text Add to dashboard Cite

It has been my utmost privilege to be given this opportunity to pursue a Ph.D degree.First, I would like to express my sincere gratitude to my supervisor, Prof. Erik Cambria for his support and guidance throughout my Ph.D candidature. It is with his warm encouragement that I found the courage and confidence to pursue a Ph.D degree.Next, I would like to thank my co-supervisor, Dr Rui Mao, for his patient guidance.His insights and advice played a vital role in orientating my research direction and raising the quality of my works. I deeply appreciate his efforts in helping me with my Ph.D project.I would also like to thank my fellow Sentic Team members Mengshi Ge, Luyao Zhu, Jinjie Ni, Zonglin Yang, Kai He, Tom Yang, etc., for their friendship.Last but not the least, I owe enormous gratitude to my parents. The achievements in this thesis would not have come to be if not for their love, care, and encouragement. Special thanks goes to my long-time friends Wenrui Li, Qiyu Zhong, and Zhixin Xu, who lifted my spirit in times of stress and anxiety with compassion and killer memes.

show abstract

Sentence Segmentation and Disfluency Detection in Narrative Transcripts from Neuropsychological Tests

Cited by 2 publications

References 15 publications

Efficient Automatic Punctuation Restoration Using Bidirectional Transformers with Robust Inference

Efficient Automatic Punctuation Restoration Using Bidirectional Transformers with Robust Inference

Disentangling syntactics, semantics, and pragmatics in natural language processing

Contact Info

Product

Resources

About