Papers by Binxuan Huang

7 papers
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.
Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)

Copied to clipboard

Challenge: Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability.
Approach: They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs .
Outcome: The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks.
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.
Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification (D18-1)

Copied to clipboard

Challenge: Existing approaches to aspect level sentiment classification ignore aspect information, causing large error.
Approach: They propose a parameterized convolutional neural network for aspect level sentiment classification . they incorporate aspect information into convolutionally-based neural networks .
Outcome: The proposed model achieves excellent results on SemEval 2014 datasets.
A Hierarchical Location Prediction Neural Network for Twitter User Geolocation (D19-1)

Copied to clipboard

Challenge: Existing methods to estimate user location ignore hierarchical structure among locations.
Approach: They propose a hierarchical location prediction neural network for Twitter user geolocation that first predicts the home country for a user, then uses the country result to guide the city-level prediction.
Outcome: The proposed model can achieve state-of-the-art results over three common benchmarks under different feature settings and greatly reduces the mean error distance.
Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks (D19-1)

Copied to clipboard

Challenge: Aspect level sentiment classification aims to identify the sentiment expressed towards an aspect given a context sentence.
Approach: They propose a target-dependent graph attention network for aspect level sentiment classification . it explicitly utilizes the dependency relationship among words to propagate sentiment features . they show that using BERT representations further substantially boosts the performance .
Outcome: The proposed method outperforms baselines with GloVe embeddings and improves with BERT representations.
Small Agents, Big Gains: Journey-Aware and Critic-Guided Simulation for Long-Horizon Shopping Dialogues (2026.acl-industry)

Copied to clipboard

Challenge: e-commerce assistants must support inspiration, comparison, and tool-grounded fact-checking . lack of data-coverage and verification problem hampers efficient, deployable models . eaa: "training trajectories must cover diverse user workflows with high fidelity"
Approach: They propose a system that synthesizes diverse, faithful, and policy-aligned shopping trajectories . a small model can significantly outperform same-size baselines and surpass a large-model baseline .
Outcome: The proposed model outperforms existing models and surpasses large models with 8 higher inference throughput.

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