Papers by Chenwei Zhang

25 papers
SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for relation extraction use heuristics or distant-supervised annotations, but distant supervised methods make strong assumptions on entity cooccurrence without sufficient contexts.
Approach: They propose a framework that exploits weak, self-supervised signals by leveraging large pretrained language models for adaptive clustering on contextualized relational features.
Outcome: The proposed framework exploits weak, self-supervised signals on open-domain Relation Extraction . it bootstraps the self-supervised signals by improving contextualized features in relation classification .
Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce Catalog (2023.acl-industry)

Copied to clipboard

Challenge: Existing methods for analyzing textual attributes in product catalogs are not effective on structured tabular data since they are trained on free-form natural language texts.
Approach: They propose a model to handle error detection over tabular data following a pre-training paradigm.
Outcome: The proposed model improves on a real-world Amazon Product Catalog table by 16% over state-of-the-art methods and by 11% on PR AUC over attribute value validation task.
HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to extract relational feature signals from natural language sentences use self-supervised clustering and classification that cause gradual drift problems.
Approach: They propose a framework that derives hierarchical signals from relational feature space using cross hierarchy attention and effectively optimizes relation representation of sentences under exemplar-wise contrastive learning.
Outcome: The proposed framework can extract the relationship between entities from natural language sentences without prior knowledge on relation scope or distribution.
Leveraging LLM Reasoning Enhances Personalized Recommender Systems (2024.findings-acl)

Copied to clipboard

Challenge: Recent advances have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting.
Approach: They propose to use Large Language Models to perform tasks with subjectivity and personalized preferences as inputs to RecSys.
Outcome: The proposed framework aligns with real human judgment on the coherence and faithfulness of LLM reasoning responses.
ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations (2025.naacl-long)

Copied to clipboard

Challenge: Existing benchmarks for recommendation explanation evaluation lack item diversity and user preferences data.
Approach: They propose a model-agnostic recommendation explanation evaluation benchmark based on Amazon e-commerce categories with implicit preferences . they propose two novel automatic evaluators that enable scalable and human-preference aligned evaluation of explanations .
Outcome: The proposed model-agnostic evaluation benchmark outperforms existing methods in a variety of domains.
Stronger, Lighter, Better: Towards Life-Long Attribute Value Extraction for E-Commerce Products (2024.findings-acl)

Copied to clipboard

Challenge: Existing models for attribute value extraction struggle for parameter efficiency and reliability due to data contamination and catastrophic forgetting.
Approach: They propose to decouple product type and attribute to promote de-contamination and parameter efficiency while scaling up.
Outcome: The proposed model achieves state-of-the-art performance with affordable parameter size, least historical knowledge forgetting, and greatest robustness against noises.
PV2TEA: Patching Visual Modality to Textual-Established Information Extraction (2023.findings-acl)

Copied to clipboard

Challenge: Empirical results show up to 11.74% absolute (20.97% relative) increase over unimodal baselines.
Approach: They propose to patch the visual modality to the textual-established attribute in- formation extractor.
Outcome: Empirical results show up to 11.74% absolute (29.9% relative) increase over unimodal baselines.
GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks (2023.findings-acl)

Copied to clipboard

Challenge: Existing work adopts data augmentation techniques to generate pseudo-annotated sentences . existing methods neither preserve semantic consistency of original sentences nor preserve syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations.
Approach: They propose a dedicated augmentation technique for relational texts, named GDA, which uses two complementary modules to preserve both semantic consistency and syntax structures.
Outcome: The proposed technique can bring 2.0% F1 improvements in three datasets under low-resource setting.
Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for AVE are limited on rare attributes due to poor generalization ability.
Approach: They propose to leverage pretraining and transfer learning to address weaknesses in existing methods.
Outcome: The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources.
Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to embed knowledge graphs have ignored the fact that they contain two fundamentally different views: high-level ontology-view concepts and fine-grained instance-view entities.
Approach: They propose a novel geometric representation that jointly embeds the two views of a KG using dual geometric representations.
Outcome: Experiments on the public DBpedia KG and a newly-created industrial KG show the proposed method works well.
Enhancing Cross-lingual Transfer via Phonemic Transcription Integration (2023.findings-acl)

Copied to clipboard

Challenge: Previous cross-lingual transfer methods are limited to orthographic representation learning via textual scripts.
Approach: They propose a phonemic transcription framework that incorporates phonemic translations as an additional linguistic modality beyond the orthographic transcriptions for cross-lingual transfer.
Outcome: The proposed framework captures local one-to-one alignment between two different modalities and integrates bilingual dictionaries into multilingual contexts.
End-to-End Conversational Search for Online Shopping with Utterance Transfer (2021.emnlp-main)

Copied to clipboard

Challenge: a new study proposes a conversational search system that integrates product attributes and dialog with search . but it faces two real world challenges: imperfect product schema/knowledge and lack of training dialog data .
Approach: They propose an end-to-end conversational search system that integrates search with text . they propose an utterance transfer approach that generates dialogue utterations from other domains .
Outcome: The proposed system outperforms the best tested baseline in a conversational search dataset for online shopping.
Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods to extract relation facts from limited labeled corpora are laborintensive to obtain . Existing approaches use self-training to generate pseudo labels that will cause gradual drift problem or leverage meta-learning scheme which does not solicit feedback explicitly.
Approach: They propose a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate gradient descent direction on labeled data and bootstrap its optimization capability through trial and error.
Outcome: The proposed method handles two major scenarios in low-resource relation extraction when no unlabeled data is available.
DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to align large language models with human preferences are noisy and varying in importance of preference samples.
Approach: a new method enhances reward modeling by learning to dynamically weigh preference data.
Outcome: a new method improves the performance of large language models with human preferences . it initializes data importance and iteratively refines them to maximize validation performance.
Pinpointing Diffusion Grid Noise to Enhance Aspect Sentiment Quad Prediction (2024.findings-acl)

Copied to clipboard

Challenge: Current studies on aspect-based sentiment analysis focus on essential content for model generation, ignoring the incorporation of various noise during training.
Approach: They propose a grid noise-diffusion pinpoint network (GDP) model that incorporates three new modules to tackle generation instability.
Outcome: The proposed model reduces the generation instability of model learning and outputs by incorporating Consistency Likelihood Learning and GDP-FOR.
CORI: CJKV Benchmark with Romanization Integration - a Step towards Cross-lingual Transfer beyond Textual Scripts (2024.lrec-main)

Copied to clipboard

Challenge: Naively assuming English as a source language may hinder cross-lingual transfer . despite recent advances in cross-linguistic research, most studies have restricted themselves to two major assumptions .
Approach: They propose to integrate Romanized transcription beyond textual scripts to capture contact between these languages . they propose to use a benchmark dataset to further encourage in-depth studies of language contact .
Outcome: The proposed method allows for enhanced cross-lingual representations and effective zero-shot cross-linguistic transfer.
Towards Open-World Product Attribute Mining: A Lightly-Supervised Approach (2023.acl-long)

Copied to clipboard

Challenge: Existing task setting for attribute mining on e-commerce products is closed-world, but recent work has moved towards open-world aspect.
Approach: They propose a task setting for attribute mining on e-commerce products that uses a high-quality seed attribute set bootstrapped from existing resources.
Outcome: The proposed approach surpasses baselines on existing attributes by 12 F1 and discovers values from 39% new attributes.
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach: They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome: The proposed framework outperforms baseline methods in real-time and in real applications.
Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent studies show that multi-level matching is difficult due to the scarcity of available annotated utterances.
Approach: They propose a method where semantic components are distilled from utterances via multi-head self-attention with additional dynamic regularization constraints.
Outcome: The proposed method improves representations of labeled and unlabeled instances while retaining high-level information.
Semi-supervised Relation Extraction via Incremental Meta Self-Training (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods suffer from the gradual drift problem, where noisy pseudo labels are incorporated during training.
Approach: They propose a method that uses pseudo labels to assess quality on unlabeled samples . they use a relation label generation network to learn from successful and failed attempts .
Outcome: Experimental results show the proposed method can improve on two public datasets.
Zero-shot User Intent Detection via Capsule Neural Networks (D18-1)

Copied to clipboard

Challenge: Existing methods to classify intents are labor-intensive and time-consuming as intents will be diverse and new intents may be involved.
Approach: They propose a zero-shot intent detection problem which aims to detect emerging user intents where no labeled utterances are currently available.
Outcome: The proposed model can discriminate emerging intents when no labeled utterances are available in training data.
Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for hallucination detection have attracted more attention from the community.
Approach: They propose to model the distributional distance between the regular conditional output and the unconditional output, which is generated without a given input text.
Outcome: The proposed model achieves state-of-the-art on the hallucination benchmarks HADES and other datasets.
CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks (2023.emnlp-main)

Copied to clipboard

Challenge: Chain-of-Thought prompting is popular in reasoning tasks, but its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored.
Approach: They propose a Coarse-to-Fine Chain-of-Thought approach that breaks down NLU tasks into multiple reasoning steps where LLMs can learn to acquire essential concepts.
Outcome: The proposed approach is effective in assisting the LLMs adapt to multi-grained NLU tasks under zero-shot and few-shot multi-domain settings.
Multi-grained Named Entity Recognition (P19-1)

Copied to clipboard

Challenge: Existing approaches treat Named Entity Recognition (NER) as a sequence labeling task.
Approach: They propose a framework for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested.
Outcome: The proposed framework outperforms current state-of-the-art frameworks by 4.4% in terms of the F1 score among nested/non-overlapping NER tasks.
Joint Slot Filling and Intent Detection via Capsule Neural Networks (P19-1)

Copied to clipboard

Challenge: Existing models that label slots and detect intent do not preserve hierarchical relationship between words, slots, and intents.
Approach: They propose a capsule-based neural network model which performs slot filling and intent detection via a dynamic routing-by-agreement schema.
Outcome: The proposed model performs better than existing models and existing models on real-world datasets.

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