Papers by Changzhi Sun

17 papers
Causal Intervention Improves Implicit Sentiment Analysis (2022.coling-1)

Copied to clipboard

Challenge: Existing neural models struggle with implicit sentiment analysis because they latch onto spurious correlations, resulting in poor generalization and robustness.
Approach: They propose a CausaL intervention model for implicit sEntiment ANalysis using instrumental variable to eliminate confounding causal effects and extract the pure causal effect between sentence and sentiment.
Outcome: The proposed model extracts the pure causal effect between sentence and sentiment using instrumental variable.
Pre-training Entity Relation Encoder with Intra-span and Inter-span Information (2020.emnlp-main)

Copied to clipboard

Challenge: Existing pre-trained models do not handle text spans and relation among text span pairs.
Approach: They propose to integrate span-related information into pre-trained encoder for entity relation extraction task.
Outcome: The proposed pre-training method outperforms distantly supervised pre-trained models on two entity relation extraction benchmark datasets.
UniRE: A Unified Label Space for Entity Relation Extraction (2021.acl-long)

Copied to clipboard

Challenge: Existing joint entity relation extraction models setup two separate label spaces for the two sub-tasks .
Approach: They propose to eliminate the different treatment on the two sub-tasks’ label spaces by applying a unified classifier to predict each cell’s label.
Outcome: The proposed model achieves competitive accuracy with the best extractor and is faster.
E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning (2022.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks to test word analogy do not reveal the underneath process of analogical reasoning of neural models.
Approach: They propose an explanation benchmark for analogical reasoning using a Civil Service exam . they use a free-text explanation scheme to explain whether an analogy should be drawn .
Outcome: The proposed benchmark is very challenging for state-of-the-art models, it is found.
Learning Logic Rules for Document-Level Relation Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models for document-level relation extraction relied on implicitly powerful representations, which makes the model less transparent.
Approach: They propose a probabilistic model for document-level relation extraction by learning logic rules.
Outcome: The proposed model outperforms baseline models in relation performance and logical consistency.
ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base (2024.acl-long)

Copied to clipboard

Challenge: ANALOGYKB is a million-scale analogy knowledge base based on existing knowledge graphs (KGs) based upon relational knowledge triples, we can discover new analogies using the corresponding relations between concepts.
Approach: They propose a million-scale analogy knowledge base derived from existing knowledge graphs (KGs) ANALOGYKB identifies analogies of the same relations and analogies from analogous relations .
Outcome: The proposed model enables both smaller LMs and LLMs to gain better analogical reasoning capabilities.
TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies have shown that LoRA introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning.
Approach: They propose a method that leverages importance information from the pretrained model’s weights to mitigate LoRA redundancy.
Outcome: The proposed method significantly reduces the number of trainable parameters required for task adaptation while providing a task-aligned perspective for LoRA redundancy reduction.
Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies have revealed that Large Vision-Language Models suffer from hallucinations in practice, including object hallucines, spatial hallucinos, attribute hallucinications, etc.
Approach: They propose to use CLIP model to mitigate object hallucinations by using a data augmentation method to create negative samples with a variety of hallucinian issues.
Outcome: The proposed method mitigates object hallucinations and can be used as a visual encoder, effectively alleviating the object halluination issue in LVLMs.
Probabilistic Graph Reasoning for Natural Proof Generation (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches to reasoning over formal representations do not explicitly consider inter-dependency between answers and proofs.
Approach: They propose a novel approach for joint answer prediction and proof generation using an induced graphical model.
Outcome: The proposed approach achieves 10%-30% improvement on QA accuracy in evaluations under diverse conditions.
CERD: A Comprehensive Chinese Rhetoric Dataset for Rhetorical Understanding and Generation in Essays (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing rhetorical understanding and generation datasets focus on single coarse-grained categories or fine-grain categories, neglecting the intrinsic connections between different rhetorical devices.
Approach: They propose a Chinese Essay Rhetoric Dataset with four coarse-grained categories . they propose to treat these categories as separate sub-tasks, thereby improving writing skills .
Outcome: The proposed dataset improves the author's writing proficiency and language usage skills by recognizing and generating rhetorical sentences under given conditions.
Joint Type Inference on Entities and Relations via Graph Convolutional Networks (P19-1)

Copied to clipboard

Challenge: a novel graph convolutional network (GCN) is proposed for the task of joint entity relation extraction.
Approach: They propose a graph convolutional network running on an entity-relation bipartite graph . they propose combining two different methods to perform joint entity relation extraction .
Outcome: The proposed model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance.
Few Clean Instances Help Denoising Distant Supervision (2022.coling-1)

Copied to clipboard

Challenge: Existing distantly supervised entity relation extractors rely on noisy data for training and evaluation.
Approach: They propose a criterion for clean instance selection based on influence functions to collect sample-level evidence for recognizing good instances.
Outcome: The proposed method shows strong performance on real and synthetic noisy datasets.
Logic-Regularized Verifier Elicits Reasoning from LLMs (2025.acl-long)

Copied to clipboard

Challenge: Typical verifiers require resource-intensive supervised dataset construction, which is costly and faces limitations in data diversity.
Approach: They propose an unsupervised verifier regularized by logical rules that uses internal activations and logical constraints on multiple reasoning paths.
Outcome: Experiments on 10 datasets show that the proposed verifier outperforms baselines and is comparable to the supervised verifier.
Is “hot pizza” Positive or Negative? Mining Target-aware Sentiment Lexicons (2021.eacl-main)

Copied to clipboard

Challenge: Existing sentiment lexicons assume words’ sentiments are invariant within a domain, but this assumption is weak for fine-granularity analyses of text sentiments.
Approach: They propose a "perturb-and-see" method to extract commonsense sentiments from large-scale datasets by binding a word's sentiment to its collocation words instead of domain labels.
Outcome: The proposed framework is able to achieve highly competitive performances on the unsupervised opinion relation extraction task.
Extracting Entities and Relations with Joint Minimum Risk Training (D18-1)

Copied to clipboard

Challenge: Existing methods for detecting entities and relations are limited by the complexity of the joint learning paradigm.
Approach: They propose a joint learning paradigm based on minimum risk training . they implement a strong and simple neural network to execute the MRT .
Outcome: The proposed model is able to achieve state-of-the-art in the extraction task on ACE05 and NYT datasets.
Generation with Dynamic Vocabulary (2024.emnlp-main)

Copied to clipboard

Challenge: Using static vocabulary, vocabulary is ignored in advanced generation tasks.
Approach: They propose a dynamic vocabulary that can involve arbitrary text spans during generation.
Outcome: The proposed vocabulary can be deployed in a plug-and-play way, thus is attractive for various downstream applications.
ENPAR:Enhancing Entity and Entity Pair Representations for Joint Entity Relation Extraction (2021.eacl-main)

Copied to clipboard

Challenge: Existing methods for joint entity relation extraction use multitask learning frameworks, but annotations for additional tasks are hard to obtain.
Approach: They propose a pre-training method to improve the joint extraction performance with just extra entity annotations.
Outcome: The proposed method outperforms existing methods on ACE05, SciERC, and NYT and outperformed BERT on other tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations