Papers by Dongqi Wang
Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | Contemporary leading-edge systems for abstractive (long) text summarization employ Transformer encoderdecoder architectures that only consider the nuclearity annotation . |
| Approach: | They propose to incorporate Rhetorical Structure Theory into a novel summarization model that incorporates both the types and uncertainty of rhetorical relations. |
| Outcome: | The proposed model outperforms state-of-the-art models on automatic metrics and human evaluation. |
SciNews: From Scholarly Complexities to Public Narratives – a Dataset for Scientific News Report Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Scientific news reports are a bridge between academic and scientific publications . however, the pursuit of automated news reports faces challenges due to the insufficient availability of parallel corpora. |
| Approach: | They propose to use a corpus of scientific news reports to facilitate this paradigm development . they highlight the divergences in readability and brevity between scientific news narratives and academic manuscripts . |
| Outcome: | The proposed corpus includes academic publications and scientific news reports across nine disciplines. |
PhyVer: Physics-Grounded Material Claim Verification with Multi-Fidelity Physical Evidence (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing claim verification pipelines operate over text, producing ungrounded judgments. |
| Approach: | They propose a physics-grounded material claim verification system that can be used to verify claims with physical evidence. |
| Outcome: | The proposed system reduces MAE and sign-offs with experts over text-only GPT-5.1. |
How to Make LMs Strong Node Classifiers? (2026.findings-eacl)
Copied to clipboard
Zhe Xu, Kaveh Hassani, Si Zhang, Hanqing Zeng, Michihiro Yasunaga, Limei Wang, Dongqi Fu, Ning Yao, Bo Long, Hanghang Tong
| Challenge: | Language Models (LMs) are increasingly challenging the dominance of domain-specific models, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs). |
| Approach: | They propose a novel approach that empowers off-the-shelf LMs to achieve performance comparable to state-of-the art (SOTA) GNNs on node classification tasks without requiring any architectural modifications. |
| Outcome: | The proposed approach outperforms existing GNNs on node classification tasks and is open-source upon publication. |
Disco-RAG: Discourse-Aware Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang, Jian Li, Jiangning Zhang, Yabiao Wang
| Challenge: | Existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents. |
| Approach: | They propose a framework that explicitly injects discourse signals into the generation process. |
| Outcome: | Experiments on question answering and long-document summarization benchmarks show the efficacy of the proposed framework. |
Non-Autoregressive Translation by Learning Target Categorical Codes (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing non-autoregressive text generation models still fall behind in translation quality . authors propose a model that learns implicitly categorical codes as latent variables . |
| Approach: | They propose a non-autoregressive Transformer model that implicitly categorizes latent variables into decoding . they find it improves translation quality by introducing more informative decoder inputs . |
| Outcome: | The proposed model achieves comparable or better performance in machine translation tasks than strong baselines. |
latent-GLAT: Glancing at Latent Variables for Parallel Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Recent advances in text generation have limited applications due to multimodality problem. |
| Approach: | They propose a method which uses latent variables to capture word categorical information and invoke an advanced curriculum learning technique to overcome multi-modality problem. |
| Outcome: | The proposed method outperforms strong baselines without an autoregressive model, which further broadens the application scenarios of the parallel decoding paradigm. |