Vicky Zayats
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Vicky Zayats has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Mari Ostendorf
University of Washington Microsoft Research University of Washington
3 shared publications Courtney Mansfield
Linguistics Department University of Washington
1 shared publication- Hannaneh Hajishirzi
University of Washington
1 shared publication - Richard Wright
Department of Linguistics, University of Washington, Seattle, WA 98195, USA
1 shared publication Trang Tran
Electrical & Computer Engineering Department University of Washington
1 shared publication
Latest Publications
- Open Access
Disfluencies and Human Speech Transcription Errors
This paper explores contexts associated with errors in transcrip-tion of spontaneous speech, shedding light on human perceptionof disfluencies and other conversational speech phenomena. Anew version of the Switchboard corpus is provided with disfluency annotations for careful speech transcripts, together with results showing the impact of transcription errors on evaluation of automatic disfluency detection.
Open AccessDisfluencies and Human Speech Transcription Errors
This paper explores contexts associated with errors in transcrip-tion of spontaneous speech, shedding light on human perceptionof disfluencies and other conversational speech phenomena. Anew version of the Switchboard corpus is provided with disfluency annotations for careful speech transcripts, together with results showing the impact of transcription errors on evaluation of automatic disfluency detection.
- Open Access
Robust cross-domain disfluency detection with pattern match networks
In this paper we introduce a novel pattern match neural network architecture that uses neighbor similarity scores as features, eliminating the need for feature engineering in a disfluency detection task. We evaluate the approach in disfluency detection for four different speech genres, showing that the approach is as effective as hand-engineered pattern match features when used on in-domain data and achieves superior performance in cross-domain scenarios.
Open AccessRobust cross-domain disfluency detection with pattern match networks
In this paper we introduce a novel pattern match neural network architecture that uses neighbor similarity scores as features, eliminating the need for feature engineering in a disfluency detection task. We evaluate the approach in disfluency detection for four different speech genres, showing that the approach is as effective as hand-engineered pattern match features when used on in-domain data and achieves superior performance in cross-domain scenarios.
- Open Access
Disfluency Detection using a Bidirectional LSTM
We introduce a new approach for disfluency detection using a Bidirectional Long-Short Term Memory neural network (BLSTM). In addition to the word sequence, the model takes as input pattern match features that were developed to reduce sensitivity to vocabulary size in training, which lead to improved performance over the word sequence alone. The BLSTM takes advantage of explicit repair states in addition to the standard reparandum states. The final output leverages integer linear programming to incorporate constraints of disfluency structure. In experiments on the Switchboard corpus, the model achieves state-of-the-art performance for both the standard disfluency detection task and the correction detection task. Analysis shows that the model has better detection of non-repetition disfluencies, which tend to be much harder to detect.
Open AccessDisfluency Detection using a Bidirectional LSTM
We introduce a new approach for disfluency detection using a Bidirectional Long-Short Term Memory neural network (BLSTM). In addition to the word sequence, the model takes as input pattern match features that were developed to reduce sensitivity to vocabulary size in training, which lead to improved performance over the word sequence alone. The BLSTM takes advantage of explicit repair states in addition to the standard reparandum states. The final output leverages integer linear programming to incorporate constraints of disfluency structure. In experiments on the Switchboard corpus, the model achieves state-of-the-art performance for both the standard disfluency detection task and the correction detection task. Analysis shows that the model has better detection of non-repetition disfluencies, which tend to be much harder to detect.