Wenting Wang


pdf bib
From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment
Xin Mao | Wenting Wang | Yuanbin Wu | Man Lan
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs (Knowledge Graphs), which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance improvements on several public datasets. However, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNN-based methods, we successfully transform the cross-lingual EA problem into an assignment problem. Based on this re-definition, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments have been conducted to show that our proposed unsupervised approach even beats advanced supervised methods across all public datasets while having high efficiency, interpretability, and stability.


pdf bib
Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title
Huimin Xu | Wenting Wang | Xin Mao | Xinyu Jiang | Man Lan
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Supplementing product information by extracting attribute values from title is a crucial task in e-Commerce domain. Previous studies treat each attribute only as an entity type and build one set of NER tags (e.g., BIO) for each of them, leading to a scalability issue which unfits to the large sized attribute system in real world e-Commerce. In this work, we propose a novel approach to support value extraction scaling up to thousands of attributes without losing performance: (1) We propose to regard attribute as a query and adopt only one global set of BIO tags for any attributes to reduce the burden of attribute tag or model explosion; (2) We explicitly model the semantic representations for attribute and title, and develop an attention mechanism to capture the interactive semantic relations in-between to enforce our framework to be attribute comprehensive. We conduct extensive experiments in real-life datasets. The results show that our model not only outperforms existing state-of-the-art NER tagging models, but also is robust and generates promising results for up to 8,906 attributes.


pdf bib
Extracting Entities and Relations with Joint Minimum Risk Training
Changzhi Sun | Yuanbin Wu | Man Lan | Shiliang Sun | Wenting Wang | Kuang-Chih Lee | Kewen Wu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We investigate the task of joint entity relation extraction. Unlike prior efforts, we propose a new lightweight joint learning paradigm based on minimum risk training (MRT). Specifically, our algorithm optimizes a global loss function which is flexible and effective to explore interactions between the entity model and the relation model. We implement a strong and simple neural network where the MRT is executed. Experiment results on the benchmark ACE05 and NYT datasets show that our model is able to achieve state-of-the-art joint extraction performances.

pdf bib
ECNU at SemEval-2018 Task 3: Exploration on Irony Detection from Tweets via Machine Learning and Deep Learning Methods
Zhenghang Yin | Feixiang Wang | Man Lan | Wenting Wang
Proceedings of The 12th International Workshop on Semantic Evaluation

The paper describes our submissions to task 3 in SemEval-2018. There are two subtasks: Subtask A is a binary classification task to determine whether a tweet is ironic, and Subtask B is a fine-grained classification task including four classes. To address them, we explored supervised machine learning method alone and in combination with neural networks.

pdf bib
HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets
Wenting Wang
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

This paper describes our system designed for the WASSA-2018 Implicit Emotion Shared Task (IEST). The task is to predict the emotion category expressed in a tweet by removing the terms angry, afraid, happy, sad, surprised, disgusted and their synonyms. Our final submission is an ensemble of one supervised learning model and three deep neural network based models, where each model approaches the problem from essentially different directions. Our system achieves the macro F1 score of 65.8%, which is a 5.9% performance improvement over the baseline and is ranked 12 out of 30 participating teams.


pdf bib
DLIREC: Aspect Term Extraction and Term Polarity Classification System
Zhiqiang Toh | Wenting Wang
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)