paper-with-me

Papers

How does BERT process disfluency?

2021-07-01 · SIGDIAL (ACL) 2021 7 · Ye Tian, Tim Nieradzik, Sepehr Jalali, Da-Shan Shiu

Natural conversations are filled with disfluencies. This study investigates if and how BERT understands disfluency with three experiments: (1) a behavioural study using a downstream task, (2) an analysis of sentence embeddings and (3) an analysis of the attention mechanism on disfluency. The behavioural study shows that without fine-tuning on disfluent data, BERT does not suffer significant performance loss when presented disfluent compared to fluent inputs (exp1). Analysis on sentence embeddings of disfluent and fluent sentence pairs reveals that the deeper the layer, the more similar their representation (exp2). This indicates that deep layers of BERT become relatively invariant to disfluency. We pinpoint attention as a potential mechanism that could explain this phenomenon (exp3). Overall, the study suggests that BERT has knowledge of disfluency structure. We emphasise the potential of using BERT to understand natural utterances without disfluency removal.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSentence EmbeddingsTask 2

Similar Papers 제목 키워드 기반

Disfluency Detection for Vietnamese

2022-10-01 · COLING (WNUT) 2022 10 · Mai Dao, Thinh Hung Truong, Dat Quoc Nguyen

In this paper, we present the first empirical study for Vietnamese disfluency detection. To conduct this study, we first create a disfluency detection dataset for Vietnamese, with manual annotations over two disfluency t…

Vietnamese Word SegmentationXLM-R

Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection

2022-05-02 · NAACL 2022 7 · Angelica Chen, Vicky Zayats, Daniel D. Walker, Dirk Padfield

In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed. This post-processing step is crucial for producing clean transcripts and high performance…

Machine Translation

Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In modern interactive speech-based systems speech is consumed and transcribed incrementally prior to having disfluencies removed. While this post-processing step is crucial for producing clean transcripts and high perfor…

Machine TranslationTranslation

Disfluency Detection with Unlabeled Data and Small BERT Models

2021-04-21 · Johann C. Rocholl, Vicky Zayats, Daniel D. Walker, Noah B. Murad 외

Disfluency detection models now approach high accuracy on English text. However, little exploration has been done in improving the size and inference time of the model. At the same time, automatic speech recognition (ASR…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationDomain Adaptation+2

Streaming Joint Speech Recognition and Disfluency Detection

2022-11-16 · Hayato Futami, Emiru Tsunoo, Kentaro Shibata, Yosuke Kashiwagi 외

Disfluency detection has mainly been solved in a pipeline approach, as post-processing of speech recognition. In this study, we propose Transformer-based encoder-decoder models that jointly solve speech recognition and d…

DecoderLanguage Modellingspeech-recognitionSpeech Recognition