Papers by Shengqi Zhu
Show or Tell? Modeling the evolution of request-making in Human-LLM conversations (2026.findings-eacl)
Copied to clipboard
| Challenge: | a new framework to describe request-making segments user input into request content, roles assigned, query-specific context, and task-independent expressions. |
| Approach: | They propose a framework to describe request-making that segments user input into request content, roles assigned, query-specific context, and the remaining task-independent expressions. |
| Outcome: | The proposed framework reveals fundamental and habitual user-LLM interaction patterns beyond individual task completion. |
More than Classification: A Unified Framework for Event Temporal Relation Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for event temporal relation extraction ignore meaning of relations and wipe out their intrinsic dependency. |
| Approach: | They propose a unified event temporal relation extraction framework that transforms temporal relations into logical expressions of time points and completes the ETRE by predicting the relations between certain time points. |
| Outcome: | The proposed framework outperforms the state-of-the-art model on TB-Dense and MATRES by 0.3% on both datasets. |
Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction (2021.acl-short)
Copied to clipboard
| Challenge: | Document-level relation extraction (RE) is more challenging than sentence RE as it often requires reasoning over multiple sentences. |
| Approach: | They propose a method to heuristically select evidence sentences for document-level relation extraction. |
| Outcome: | The proposed method can be easily combined with BiLSTM to achieve good performance on benchmark datasets even better than fancy graph neural network based methods. |
Exploring Distantly-Labeled Rationales in Neural Network Models (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods focus on distantly-labeled rationales, ignoring the potential important non-rationale words and not distinguishing the importance of different rationale words. |
| Approach: | They propose two novel auxiliary loss functions to make better use of distantly-labeled rationales, which encourage models to maintain their focus on important words beyond labeled rationals (PINs) and alleviate redundant training on non-helpful rationale (NoIRs). |
| Outcome: | The proposed methods outperform existing methods on two representative classification tasks while maintaining the ability to spread focus to other unlabeled important words. |
“Get Their Hands Dirty, Not Mine”: On Researcher-Annotator Collaboration and the Agency of Annotators (2024.findings-acl)
Copied to clipboard
| Challenge: | Annotation quality is often framed as post-hoc cleanup of annotator-caused issues . authors argue that this narrative limits the scope of improving annotation . |
| Approach: | They propose to consider annotation as a procedural collaboration . they propose to capture the nuance and describe the full procedure to resolve issues . |
| Outcome: | The proposed study examines whether and why annotation quality is often framed as post-hoc cleanup of annotator-caused issues. |
What We Talk About When We Talk About LMs: Implicit Paradigm Shifts and the Ship of Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | a new study examines the evolution of language models as a time-specific collection of models of interest. |
| Approach: | They investigate the problem of "Ship of Language Models" where scientific evolution takes form of continuous retrofits of key *existing* terms. |
| Outcome: | The proposed model is based on recent NLP publications and is quantitatively analyzed. |
Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED (2022.acl-long)
Copied to clipboard
| Challenge: | Document-level relation extraction is a challenging task as it requires reasoning across multiple sentences. |
| Approach: | They propose to use a recommend-revise scheme to reduce the workload of annotators by providing them with candidate relation instances from distant supervision to supplement and remove relational facts. |
| Outcome: | The proposed dataset is the first large-scale and human-annotated dataset for relation extraction. |