Papers by Bonnie Liu
The Effect of Data Partitioning Strategy on Model Generalizability: A Case Study of Morphological Segmentation (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent work to enhance data partitioning strategies for more realistic model evaluations faces challenges in providing a clear optimal choice. |
| Approach: | They analyze morphological segmentation and morphology of ten languages from 19 languages . they use multiple datasets and splits to evaluate models . |
| Outcome: | The proposed model training and evaluation sets and new test data show that models trained from random splits can achieve higher numerical scores and model rankings tend to generalize more consistently. |
Multi-token Mask-filling and Implicit Discourse Relations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing mask-filling methods were ambiguous and ambiguic . a new study extends existing mask-filled methods to a discourse-level task . |
| Approach: | They propose a multi-token mask-filling approach that supports the prediction of multi-tongue connectives in masked positions. |
| Outcome: | The proposed multi-token mask-filling outperforms the single-token approach in recognizing implicit discourse relations. |
NegPar: A parallel corpus annotated for negation (L18-1)
Copied to clipboard
| Challenge: | NegPar is the first parallel corpus annotated for negation in the narrative domain. |
| Approach: | They present NegPar, a parallel corpus annotated for negation in the narrative domain . they follow the annotation guidelines in the CONANDOYLE-NEG corpus . |
| Outcome: | The proposed corpus is based on the CONANDOYLE-NEG corpus and is reannotated to ensure more consistent and interpretable representations. |
Event Detection from Social Media for Epidemic Prediction (2024.naacl-long)
Copied to clipboard
Tanmay Parekh, Anh Mac, Jiarui Yu, Yuxuan Dong, Syed Shahriar, Bonnie Liu, Eric Yang, Kuan-Hao Huang, Wei Wang, Nanyun Peng, Kai-Wei Chang
| Challenge: | Social media is an easy-to-access platform providing timely updates about societal trends and events. |
| Approach: | They propose a framework to extract epidemic-related events from social media posts to provide early warnings. |
| Outcome: | The proposed framework can detect epidemic events for three unseen epidemics of Monkeypox, Zika, and Dengue while existing models fail miserably. |