← Authors

Xiaodong Shi

27 papers · 2012–2026 · 6 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (13) 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (7) πŸ—ΊοΈ Taxonomy Completionist (64) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🀝 Dynamic Duo (18) ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (125) πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (26)

Conferences

ACL (10) EMNLP (6) AAAI (4) COLING (3) IJCNLP (2) NAACL (2)

Top co-authors

Yidong Chen (19) Biao Fu (10) Jinsong Su (7) Liang Zhang (5) Kai Fan (4) Minpeng Liao (4) Boli Wang (3) Zhixing Tan (3) Hui Wu (3) Shuangtao Li (3)

Keywords

large language model (5) relation extraction (3) speech translation (3) semantic representation (3) neural machine translation (3) knowledge distillation (2) entity pair (2) simultaneous translation (2) document-level relation extraction (2) singing voice synthesis (2) syntactic representation (2) adversarial training (2) document understanding (2) acoustic model (2) sign language translation (2) compositional generalization (2) data augmentation (1) few-shot learning (1) attention mechanism (1) prototype learning (1)

Papers

Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture AAAI 2026
LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline ACL 2025
LLMΓ—MapReduce: Simplified Long-Sequence Processing using Large Language Models ACL 2025
Representation Purification for End-to-End Speech Translation COLING 2025
From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment ACL 2025
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization ACL 2024
Adaptive Simultaneous Sign Language Translation with Confident Translation Length Estimation COLING 2024
FT-GAN: Fine-Grained Tune Modeling for Chinese Opera Synthesis AAAI 2024
wav2vec-S: Adapting Pre-trained Speech Models for Streaming ACL 2024
Layer-Wise Representation Fusion for Compositional Generalization AAAI 2024
Signer Diversity-driven Data Augmentation for Signer-Independent Sign Language Translation NAACL 2024
Exploring Self-Distillation Based Relational Reasoning Training for Document-Level Relation Extraction AAAI 2023
Consistent Prototype Learning for Few-Shot Continual Relation Extraction ACL 2023
Improving Chinese Pop Song and Hokkien Gezi Opera Singing Voice Synthesis by Enhancing Local Modeling EMNLP 2023
Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference EMNLP 2023
Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization EMNLP 2023
Towards Better Document-level Relation Extraction via Iterative Inference EMNLP 2022
Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis ACL 2022
A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information IJCNLP 2021
Synchronous Dual Network with Cross-Type Attention for Joint Entity and Relation Extraction EMNLP 2021
XMU’s Simultaneous Translation System at NAACL 2021 NAACL 2021
A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information ACL 2021
A Document-Level Neural Machine Translation Model with Dynamic Caching Guided by Theme-Rheme Information COLING 2020
XMU Neural Machine Translation Online Service IJCNLP 2017
Improving Implicit Discourse Relation Recognition with Discourse-specific Word Embeddings ACL 2017
Bilingually-constrained Synthetic Data for Implicit Discourse Relation Recognition EMNLP 2016
Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information ACL 2012