Dehong Gao


2022

pdf bib
Dependency Position Encoding for Relation Extraction
Qiushi Guo | Xin Wang | Dehong Gao
Findings of the Association for Computational Linguistics: NAACL 2022

Leveraging the dependency tree of the input sentence is able to improve the model performance for relation extraction. A challenging issue is how to remove confusions from the tree. Efforts have been made to utilize the dependency connections between words to selectively emphasize target-relevant information. However, these approaches are limited in focusing on exploiting dependency types. In this paper, we propose dependency position encoding (DPE), an efficient way of incorporating both dependency connections and dependency types into the self-attention mechanism to distinguish the importance of different word dependencies for the task. In contrast to previous studies that process input sentence and dependency information in separate streams, DPE can be seamlessly incorporated into the Transformer and makes it possible to use an one-stream scheme to extract relations between entity pairs. Extensive experiments show that models with our DPE significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED.

2020

pdf bib
Deep Hierarchical Classification for Category Prediction in E-commerce System
Dehong Gao
Proceedings of the 3rd Workshop on e-Commerce and NLP

In e-commerce system, category prediction is to automatically predict categories of given texts. Different from traditional classification where there are no relations between classes, category prediction is reckoned as a standard hierarchical classification problem since categories are usually organized as a hierarchical tree. In this paper, we address hierarchical category prediction. We propose a Deep Hierarchical Classification framework, which incorporates the multi-scale hierarchical information in neural networks and introduces a representation sharing strategy according to the category tree. We also define a novel combined loss function to punish hierarchical prediction losses. The evaluation shows that the proposed approach outperforms existing approaches in accuracy.

2015

pdf bib
Cross-lingual Sentiment Lexicon Learning With Bilingual Word Graph Label Propagation
Dehong Gao | Furu Wei | Wenjie Li | Xiaohua Liu | Ming Zhou
Computational Linguistics, Volume 41, Issue 1 - March 2015

2013

pdf bib
Sequential Summarization: A New Application for Timely Updated Twitter Trending Topics
Dehong Gao | Wenjie Li | Renxian Zhang
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2012

pdf bib
Efficient Feedback-based Feature Learning for Blog Distillation as a Terabyte Challenge
Dehong Gao | Wenjie Li | Renxian Zhang
Proceedings of COLING 2012: Demonstration Papers

pdf bib
Beyond Twitter Text: A Preliminary Study on Twitter Hyperlink and its Application
Dehong Gao | Wenjie Li | Renxian Zhang
Proceedings of COLING 2012: Demonstration Papers

pdf bib
Towards Scalable Speech Act Recognition in Twitter: Tackling Insufficient Training Data
Renxian Zhang | Dehong Gao | Wenjie Li
Proceedings of the Workshop on Semantic Analysis in Social Media

2011

pdf bib
Simultaneous Clustering and Noise Detection for Theme-based Summarization
Xiaoyan Cai | Renxian Zhang | Dehong Gao | Wenjie Li
Proceedings of 5th International Joint Conference on Natural Language Processing