2024

• “MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation” is released, check the new multimodal benchmark’s homepage
• “An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models” is accepted to ECCV 2024.
• “Improving Event Definition Following For Zero-Shot Event Detection” is accepted to ACL 2024.
• “PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain” is accepted to ACL 2024 Findings.
• “Distantly-Supervised Named Entity Recognition with Uncertainty-aware Teacher Learning and Student-student Collaborative Learning” is accepted to ACL 2024 Findings.
• “Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation” is accepted to NAACL 2024.
• “MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning” is accepted to ICLR 2024.

2023

• “Can We Edit Factual Knowledge by In-Context Learning?” is accepted to EMNLP 2023.
• “Coarse-to-Fine Dual Encoders are Better Frame Identification Learners” is accepted to EMNLP 2023 Findings.
• “Guiding AMR Parsing with Reverse Graph Linearization” is accepted to EMNLP 2023 Findings.
• “Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond” is accepted to Foundatation Model for Decision Making workshop @NeurIPS 2023.
• “On the Pareto Front of Multilingual Neural Machine Translation” is accepted to NeurIPS 2023.
• “SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition” is accepted to ACL 2023 Findings.
• “On the off-target problem of zero-shot multilingual neural machine translation” is accepted to ACL 2023 Findings.
• “Query your model with definitions in FrameNet: an effective method for frame semantic role labeling” is accepted to AAAI 2023.
• “TABLEIE: Capturing the Interactions Among Sub-Tasks in Information Extraction via Double Tables” is accepted to ICASSP 2023.

2022

• “A Span-based Target-aware Relation Model for Frame-semantic Parsing” is accepted to ACM Transactions on Asian and Low-Resource Language Information Processing.
• “Generating, Reasoning & Ranking: Multitask Learning Framework for Math Word Problem Generation” is accepted to CCL 2022.
• “Knowledge-integrated Joint Model For Multi-target Frame Semantic Parsing” is accepted to CCL 2022.
• “A Two-Stage Method for Chinese AMR Parsing” wins the second prize at CAMRP-2022.
• “SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER” is accepted to COLING 2022
• “From dense to sparse: Contrastive pruning for better pre-trained language model compression” is accepted to AAAI 2022.
• “Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance Rewriting” is accepted to NAACL 2022.
• “A double-graph based framework for frame semantic parsing” is accepted to NAACL 2022.
• “A two-stream AMR-enhanced model for document-level event argument extraction” is accepted to NAACL 2022.
• “ATP: AMRize then parse! enhancing AMR parsing with PseudoAMRs” is accepted to NAACL Findings 2022.
• “S4-Tuning: A Simple Cross-lingual Sub-network Tuning Method-Tuning: A Simple Cross-lingual Sub-network Tuning Method” is accepted to ACL 2022.
• “Hierarchical curriculum learning for amr parsing” is accepted to ACL 2022.
• “Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation” is accepted to ACL 2022.

2021

• “Raise a child in large language model: Towards effective and generalizable fine-tuning” is accepted to EMNLP 2021.
• “Chinese word segmentation of medical text based on dual-encoder” is accepted to CCL 2021.
• “Document-level event extraction via heterogeneous graph-based interaction model with a tracker” is acceoted to ACL 2021.
• “Joint multi-decoder framework with hierarchical pointer network for frame semantic parsing” is accepted to ACL Findings 2021.
• “SIRE: Separate intra-and inter-sentential reasoning for document-level relation extraction” is accepted to ACL Findings 2021.

Full publications can be found at Google Scholar