Yiming Wang
Author directoryOther people with similar names: Yiming Wang, Yiming Wang, Yiming Wang
Unverified author pages with similar names: Yiming Wang
2026
PERIBENCH: A Protocol-Aware Benchmark for Dynamic Perioperative Risk Prediction from Numerical Models to Language Interfaces
Xiaohui Zhao | Xiangyu Meng | Jinjin Chi | Yongcheng Jing | Yiming Wang | Yibing Zhan | Hang Sun | Dacheng Tao
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Xiaohui Zhao | Xiangyu Meng | Jinjin Chi | Yongcheng Jing | Yiming Wang | Yibing Zhan | Hang Sun | Dacheng Tao
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Dynamic perioperative risk prediction requires models to anticipate evolving physiological deterioration under strict prediction-time information boundaries. We introduce PERIBENCH, a protocol-aware benchmark built from high-frequency intraoperative signals. PERIBENCH defines 18 clinically motivated tasks spanning future risk classification, persistent deterioration prediction, continuous vital-sign regression, and case-level prognosis, and evaluates 37 systems across numerical predictors, deep sequential models, time-series foundation models, and LLM-oriented language interfaces. Rather than using a single undifferentiated leaderboard, PERIBENCH separates supervised or adapted prediction, direct pretrained transfer, and prompt-based language-interface inference into protocol-compatible pools. Experiments show that model sophistication does not translate monotonically into better perioperative prediction: tree-based references remain strong on many classification endpoints, deep sequential models are competitive on selected physiological tasks, direct foundation-model transfer is heterogeneous, and language interfaces capture useful classification signals but remain less reliable for regression, calibration, alert burden, and abnormal-region prediction. PERIBENCH provides a structured benchmark for studying dynamic perioperative prediction from numerical models to language interfaces under shared task semantics and explicit protocol boundaries. Code is available at https://github.com/Kdyyh/PERIBENCH.
2021
Extracting Topics with Simultaneous Word Co-occurrence and Semantic Correlation Graphs: Neural Topic Modeling for Short Texts
Yiming Wang | Ximing Li | Xiaotang Zhou | Jihong Ouyang
Findings of the Association for Computational Linguistics: EMNLP 2021
Yiming Wang | Ximing Li | Xiaotang Zhou | Jihong Ouyang
Findings of the Association for Computational Linguistics: EMNLP 2021
Short text nowadays has become a more fashionable form of text data, e.g., Twitter posts, news titles, and product reviews. Extracting semantic topics from short texts plays a significant role in a wide spectrum of NLP applications, and neural topic modeling is now a major tool to achieve it. Motivated by learning more coherent and semantic topics, in this paper we develop a novel neural topic model named Dual Word Graph Topic Model (DWGTM), which extracts topics from simultaneous word co-occurrence and semantic correlation graphs. To be specific, we learn word features from the global word co-occurrence graph, so as to ingest rich word co-occurrence information; we then generate text features with word features, and feed them into an encoder network to get topic proportions per-text; finally, we reconstruct texts and word co-occurrence graph with topical distributions and word features, respectively. Besides, to capture semantics of words, we also apply word features to reconstruct a word semantic correlation graph computed by pre-trained word embeddings. Upon those ideas, we formulate DWGTM in an auto-encoding paradigm and efficiently train it with the spirit of neural variational inference. Empirical results validate that DWGTM can generate more semantically coherent topics than baseline topic models.
Search