ZWZeqiu Wu
Zeqiu Wu
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zeqiu Wu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Bo-Ru Lu
University of Washington ♡ Microsoft Research ♥ Allstate ♣ University of Hong Kong ♢ Allen Institute for AI
1 shared publicationChia-Hsuan Lee
University of Washington ♡ Microsoft Research ♥ Allstate ♣ University of Hong Kong ♢ Allen Institute for AI
1 shared publication- Hao Cheng
University of Washington Microsoft Research University of Washington
1 shared publication Jean Utke
University of Washington ♡ Microsoft Research ♥ Allstate ♣ University of Hong Kong ♢ Allen Institute for AI
1 shared publication- Mari Ostendorf
University of Washington ♡ Microsoft Research ♥ Allstate ♣ University of Hong Kong ♢ Allen Institute for AI
1 shared publication Nikita Haduong
University of Washington ♡ Microsoft Research ♥ Allstate ♣ University of Hong Kong ♢ Allen Institute for AI
1 shared publication
Latest Publications
- Open Access
Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?
The capabilities of pretrained language models have opened opportunities to explore new application areas, but applications involving human-human interaction are limited by the fact that most data is protected from public release for privacy reasons. Problem-solving human dialogues in real applications can be much more complex than existing Wizard-of-Oz collections, preventing successful domain transfer. To support information extraction (IE) for a private call center dataset, we introduce a human-in-the-loop dialogue generation framework capable of synthesizing realistic dialogues. In IE experiments with auto insurance call center dialogues, we observe 25\% relative improvement in $F_1$ after augmenting a small set of real human conversations with synthetic data. We release code and our synthetic dataset to illustrate the complexity of real-world call center conversations and encourage development of complex dialogue datasets that are more representative of natural data.Open AccessDoes Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?
The capabilities of pretrained language models have opened opportunities to explore new application areas, but applications involving human-human interaction are limited by the fact that most data is protected from public release for privacy reasons. Problem-solving human dialogues in real applications can be much more complex than existing Wizard-of-Oz collections, preventing successful domain transfer. To support information extraction (IE) for a private call center dataset, we introduce a human-in-the-loop dialogue generation framework capable of synthesizing realistic dialogues. In IE experiments with auto insurance call center dialogues, we observe 25\% relative improvement in $F_1$ after augmenting a small set of real human conversations with synthetic data. We release code and our synthetic dataset to illustrate the complexity of real-world call center conversations and encourage development of complex dialogue datasets that are more representative of natural data.