Papers by Mingming Sun
OIE@OIA: an Adaptable and Efficient Open Information Extraction Framework (2022.acl-long)
Copied to clipboard
| Challenge: | Different Open Information Extraction (OIE) tasks require different types of information. |
| Approach: | They propose to adapt an OIE Graph to different OIE tasks with simple rules . they implement an end-to-end OIA generator and make it open-accessible . |
| Outcome: | The proposed system achieves new SOTA performance on three popular OIE tasks. |
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction (2023.acl-long)
Copied to clipboard
Jun Zhao, WenYu Zhan, Xin Zhao, Qi Zhang, Tao Gui, Zhongyu Wei, Junzhe Wang, Minlong Peng, Mingming Sun
| Challenge: | Existing methods for zero-shot relation extraction lack explicit modeling of matching pattern . et al. (2018) show that our method achieves higher matching accuracy and faster inference speed . |
| Approach: | They propose a fine-grained semantic matching method tailored for zero-shot relation extraction . they decompose sentence-level similarity score into entity matching score and context matching score . |
| Outcome: | The proposed method achieves higher matching accuracy and faster inference speed than state-of-the-art methods. |
Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing multilingual video corpus moment retrieval methods are based on a two-stream structure. |
| Approach: | They propose a multilingual video corpus moment retrieval task that uses a two-stream structure to generate a query-visual similarity and a subtitle stream exploits the query-subtitle similarity. |
| Outcome: | The proposed method improves accuracy on a large-scale video corpus moment retrieval dataset. |
Reinforced Product Metadata Selection for Helpfulness Assessment of Customer Reviews (D19-1)
Copied to clipboard
| Challenge: | a helpful review is largely concerned with the metadata of its target product . a selector learns from both the key-value product metadata and one of its reviews to take an action . |
| Approach: | They propose a framework that uses product metadata to assess helpfulness of free-text reviews . they use two real-world datasets from amazon.com and Yelp.com to test the framework . |
| Outcome: | The proposed framework can achieve state-of-the-art performance with substantial improvements . it uses two real-world datasets from Amazon.com and Yelp.com . |
FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing models generate explanations that appear coherent while containing unfaithful intermediate steps. |
| Approach: | They propose a causality-inspired framework for evaluating CoT quality using controlled perturbations as an instrumental signal to separate genuine step-to-step dependence from bias-driven artifacts. |
| Outcome: | Experiments on GSM8K, MATH, and CommonsenseQA show that FACT-E improves reasoning-trajectory selection and yields stronger in-context learning exemplars. |
Multi-Hop Open-Domain Question Answering over Structured and Unstructured Knowledge (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing open-domain question answering systems only select one source to generate answer or conduct reasoning on structured information. |
| Approach: | They propose a Document-Entity Heterogeneous Graph Network to integrate different sources of information and conduct reasoning on heterogeneous information. |
| Outcome: | The proposed model outperforms the state-of-the-art methods on a HybirdQA dataset. |
Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain (D18-1)
Copied to clipboard
| Challenge: | Experimental results reveal dual structure between OIE and OIN tasks helps to build better OIE agents and OINE agents. |
| Approach: | They propose an Open-Domain Information Narration task as the reverse task of Open Information Extraction (OIE) they then propose an OIN task as an OIE agent and an OIR agent to implement the dual structure . |
| Outcome: | The proposed task is the reverse task of Open Information Extraction (OIE) The proposed system is able to implement the dual structure with a reinforcement learning paradigm. |
NormNet: Normalize Noun Phrases for More Robust NLP (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to debunk false features in deep NLP models are inadequate . previous work suggests that models learn spurious features instead of the true signals of the task . |
| Approach: | They propose a normalization strategy to eliminate false features caused by the textual surfaces of noun phrases. |
| Outcome: | The proposed normalization strategy eliminates false features caused by the textual surfaces of noun phrases. |
Connectivity Patterns are Task Embeddings (2023.findings-acl)
Copied to clipboard
Zhiheng Xi, Rui Zheng, Yuansen Zhang, Xuanjing Huang, Zhongyu Wei, Minlong Peng, Mingming Sun, Qi Zhang, Tao Gui
| Challenge: | Existing methods for predicting inter-task transferability are sparse and task-specific. |
| Approach: | They propose a method that uses connectivity patterns of neurons as a unique identifier associated with a task. |
| Outcome: | The proposed method outperforms baselines in predicting inter-task transferability across data regimes and transfer settings while keeping high efficiency in computation and storage. |
RD-MCSA: A Multi-Class Sentiment Analysis Approach Integrating In-Context Classification Rationales and Demonstrations (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for multi-class sentiment analysis (MCSA) are difficult due to subtle semantic differences between adjacent sentiment levels and the scarcity of high-quality annotated data. |
| Approach: | They propose a framework to integrate classification rationales with adaptively selected demonstrations to enhance MCSA performance under limited supervision. |
| Outcome: | The proposed framework outperforms baseline and standard ICL methods on five benchmark datasets. |
Actively Supervised Clustering for Open Relation Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Open Relation Extraction (OpenRE) use a two-stage pipeline, which learns relation representations and assignments in the first stage, then manually labels relation for each cluster. |
| Approach: | They propose a method that performs relation learning and relation labeling simultaneously without a significant increase in human effort. |
| Outcome: | The proposed method improves existing SOTA methods by 13.8% and 10.6% on two datasets. |
One2Set + Large Language Model: Best Partners for Keyphrase Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing selection methods make redundant selections, causing poor recall and accuracy. |
| Approach: | They propose a framework to generate keyphrases from a one2set-based model and an LLM as selector. |
| Outcome: | The proposed framework surpasses state-of-the-art models in absent keyphrase prediction. |
Lingua-Graph: A Unified Representation of Cross-Task Common Substructures for Analytic Language Processing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing structural-analytic tasks are fragmented by inconsistent task requirements . we propose a solution for the representation layer, called Lingua-Graph . |
| Approach: | They propose a representation-then-decision paradigm for structural-analytic tasks . they propose Graph-based representations that capture entities, facts, and relations . |
| Outcome: | The proposed model improves interpretability and higher hostability of entities, facts, and relations . the proposed model is available on github.com/rudaoshi/Lingua . |
MQuinE: a Cure for “Z-paradox” in Knowledge Graph Embedding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge graph embedding models suffer from Z-paradox, a deficiency in expressiveness . Embedding-based models map each entity and relation into a vector or matrix . |
| Approach: | They propose a new knowledge graph embedding model that does not suffer from Z-paradox while preserves strong expressiveness to model various relation patterns with theoretical justification. |
| Outcome: | The proposed model outperforms existing models on link prediction tasks while maintaining strong expressiveness. |
A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing OIE (Open Information Extraction) algorithms are redundant and not reusable. |
| Approach: | They propose a pipeline where an Open-domain Information eXpression task provides a platform for all OIE strategies. |
| Outcome: | The proposed pipeline provides a platform for all OIE strategies. |
Learning Interpretable Relationships between Entities, Relations and Concepts via Bayesian Structure Learning on Open Domain Facts (2020.acl-main)
Copied to clipboard
| Challenge: | Concept graphs are created as universal taxonomies for text understanding in the open domain knowledge. |
| Approach: | They propose to learn interpretable relationships from open-domain facts to enrich concept graphs. |
| Outcome: | The proposed method improves the identification of concepts for entities based on relations between entities on public English and Chinese datasets. |
A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing parsers that capture dependency graphs are lacking in capturing explicit dependencies . graph-based parsing is a popular choice for capturing dependency relationships between words . |
| Approach: | They propose a semi-autoregressive dependency parser that generates dependency graphs by adding nodes and edge groups autoregressively while pouring out all group elements in parallel. |
| Outcome: | The proposed method outperforms baselines on Enhanced Universal Dependencies of multiple languages. |