Jie Chi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jie Chi has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Maureen de Seyssel
University of Edinburgh Apple MLR
2 shared publications - Natalie Schluter
University of Edinburgh Apple MLR
2 shared publications Bonnie Webber
Institute for Language Cognition and Computation University of Edinburgh
1 shared publication- Laurie Burchell
Institute for Language, Cognition, and Computation School of Informatics University of Edinburgh 10 Crichton Street EH8 9AB Edinburgh UK
1 shared publication - Nina Markl
University of Essex, Colchester, United Kingdom
1 shared publication Peter Bell
Centre for Speech Technology Research University of Edinburgh UK
1 shared publication
Latest Publications
- Open Access
The Role of Prosody in Spoken Question Answering
Spoken language understanding research to date has generally carried a heavy text perspective. Most datasets are derived from text, which is then subsequently synthesized into speech, and most models typically rely on automatic transcriptions of speech. This is to the detriment of prosody--additional information carried by the speech signal beyond the phonetics of the words themselves and difficult to recover from text alone. In this work, we investigate the role of prosody in Spoken Question Answering. By isolating prosodic and lexical information on the SLUE-SQA-5 dataset, which consists of natural speech, we demonstrate that models trained on prosodic information alone can perform reasonably well by utilizing prosodic cues. However, we find that when lexical information is available, models tend to predominantly rely on it. Our findings suggest that while prosodic cues provide valuable supplementary information, more effective integration methods are required to ensure prosody contributes more significantly alongside lexical features.
Open AccessThe Role of Prosody in Spoken Question Answering
Spoken language understanding research to date has generally carried a heavy text perspective. Most datasets are derived from text, which is then subsequently synthesized into speech, and most models typically rely on automatic transcriptions of speech. This is to the detriment of prosody--additional information carried by the speech signal beyond the phonetics of the words themselves and difficult to recover from text alone. In this work, we investigate the role of prosody in Spoken Question Answering. By isolating prosodic and lexical information on the SLUE-SQA-5 dataset, which consists of natural speech, we demonstrate that models trained on prosodic information alone can perform reasonably well by utilizing prosodic cues. However, we find that when lexical information is available, models tend to predominantly rely on it. Our findings suggest that while prosodic cues provide valuable supplementary information, more effective integration methods are required to ensure prosody contributes more significantly alongside lexical features.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 8468-8479
The Role of Prosody in Spoken Question Answering
Jie Chi, Maureen de Seyssel, Natalie Schluter. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 8468-8479
Open AccessThe Role of Prosody in Spoken Question Answering
Jie Chi, Maureen de Seyssel, Natalie Schluter. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1712-1721
Analyzing the Role of Part-of-Speech in Code-Switching: A Corpus-Based Study
Jie Chi, Peter Bell. Findings of the Association for Computational Linguistics: EACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1712-1721
Open AccessAnalyzing the Role of Part-of-Speech in Code-Switching: A Corpus-Based Study
Jie Chi, Peter Bell. Findings of the Association for Computational Linguistics: EACL 2024. 2024.
- Open Access
Querent Intent in Multi-Sentence Questions
Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit. Following Rhetorical Structure Theory (RST), we recognise that different "question discourse relations" between the subparts of MSQs reflect different speaker intents, and consequently elicit different answering strategies. Correctly identifying these relations is therefore a crucial step in automatically answering MSQs. We identify five different types of MSQs in English, and define five novel relations to describe them. We extract over 162,000 MSQs from Stack Exchange to enable future research. Finally, we implement a high-precision baseline classifier based on surface features.
Open AccessQuerent Intent in Multi-Sentence Questions
Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit. Following Rhetorical Structure Theory (RST), we recognise that different "question discourse relations" between the subparts of MSQs reflect different speaker intents, and consequently elicit different answering strategies. Correctly identifying these relations is therefore a crucial step in automatically answering MSQs. We identify five different types of MSQs in English, and define five novel relations to describe them. We extract over 162,000 MSQs from Stack Exchange to enable future research. Finally, we implement a high-precision baseline classifier based on surface features.