Scholarship and Biography
Nianwen Xue is a Professor in the Computer Science Department and the Language & Linguistics Program at Brandeis University. His research interests include developing linguistic corpora annotated with syntactic, semantic, and discourse structures, as well as machine learning approaches to syntactic, semantic and discourse parsing. He was the editor-in-chief of the ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), and he also serves on the editorial boards of Computational Linguistics and Language Resources and Evaluation (LRE).
His research interests include:
Syntactic Analysis: Development of large-scale annotated resources such as the Chinese Treebank, supporting syntactic parsing (both statistical and neural) for Chinese and other languages.
Deep Semantic Understanding: Design and learning of structured meaning representations, including semantic role labeling, Abstract Meaning Representation (AMR) parsing, and Uniform Meaning Representation (UMR) parsing, to capture predicate–argument structure, modality, and cross-lingual semantics for interpretable NLP.
Discourse Relations: Modeling discourse structure and relations, including contributions to discourse parsing and annotation frameworks for capturing coherence beyond the sentence level.
Event-Based Temporal Modeling: Representation and extraction of events and their temporal relations, including document-level temporal dependencies and cross-sentence event linking.
Cross-Document Event Coreference: Identification and clustering of event mentions across documents that refer to the same underlying real-world event, enabling aggregation of information and construction of coherent event-centric representations.
Event-Based Computational Framing: Analysis of how events are framed across texts, including contrastive framing, causal attribution, and the use of structured event representations to support balanced interpretation and generation of narratives.
AI and Computer Science Education: Investigation of the impact of generative AI on CS education, including how AI tools reshape student learning, help-seeking behavior, and curriculum design, with an emphasis on developing pedagogical strategies that promote effective and responsible use of AI.