全部年份
研究成果
按年份整理实验室近年来发表的代表性论文与会议成果。
2026
- IJCAI
DeepMed Search: An Open-Source Agentic Platform for Medical Deep Research with Introspective Verification
- ACL
BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation
- KSEM
QAlign-RAG: Causal-Aware Pseudo-Question Generation and Debate-Driven Verification for Medical RAG
- IPM
HeterMV: Multi-view reasoning over source-aware heterogeneous evidence graph for multi-source fact verification
- NEUCO
MoE-TextDiffuser: Fine-grained control of font and color in visual text rendering
2025
- TALLIP
Mixed Information Bottleneck for Location Metonymy Resolution Using Pre-trained Language Models
- ARTI
Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping
- ICIP
Reading between the lines: How eye-tracking data can inform reading strategies for large language models
- ICIP
FC-RENDER: Adaptive Font- and Color-Aware Text Ddiffusion Model
- CogSci
Cognitive Insights into Document Comprehension: The Role of Reading Order and Visual Attention in Human and Large Language Models
- ICDAR
InfoDesignLM: An LLM for Interactive and Controllable Infographic Designing Through Text
- ICDAR
HiDReader: Human-Inspired Document Reading Agent via Reinforcement Learning
- ESWA
Exploring multi-granularity contextual semantics for fully inductive knowledge graph completion
2024
- CCPE
Open-domain event schema induction via weighted attentive hypergraph neural network
- COLING
Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents
2023
- JSEKE
Enhancing Answer Selection via Ad-Hoc Knowledge Extraction from Unstructured Web Texts
- EMNLP
Vision-Enhanced Semantic Entity Recognition in Document images via Visually-Asymmetric Consistency Learning
- EMNLP
DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading
- SEKE
Few-Shot Link Prediction using Variational Heterogeneous Attention Networks
- NLE
An end-to-end neural framework using coarse-to-fine-grained attention for overlapping relational triple extraction
2022
- NCAA
Joint semantic embedding with structural knowledge and entity description for knowledge representation learning
- NLE
An empirical study of incorporating syntactic constraints into BERT-based location metonymy resolution
- PRICAI
Dual-VIE: dual-level graph attention network for visual information extraction
2021
- ES
MIFAS: multi‐source heterogeneous information fusion with adaptive importance sampling for link prediction
- PAKDD
Back to prior knowledge: joint event causality extraction via convolutional semantic infusion
- ICTAI
Causal event extraction using iterated dilated convolutions with semantic convolutional filters
- CCPE
Chinese causal event extraction using causality‐associated graph neural network
2020
- TALLIP
An extensible framework of leveraging syntactic skeleton for semantic relation classification
- CCPE
An uncertain future: Predicting events using conditional event evolutionary graph
- ES
Improving answer selection with global features
- ICONIP
Open Event Trigger Recognition Using Distant Supervision with Hierarchical Self-attentive Neural Network
- CCPE
Improving taxonomic relation learning via incorporating relation descriptions into word embeddings
- JWE
Abstract concept instantiation with context relevance measurement
2019
- ICTAI
Enhancing relation extraction using syntactic indicators and sentential contexts
- ICTAI
Multi-task learning for relation extraction