29 citations · 120 across the 16 of their papers we have counts for
7 papers · 1 filter
Layer-wise Model Pruning based on Mutual Information
Chun Fan, Jiwei Li, Xiang Ao +3
The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into thei…
Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback
Haoming Li, Feiyang Pan, Xiang Ao +6
The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few…
GuideBoot: Guided Bootstrap for Deep Contextual Bandits
Feiyang Pan, Haoming Li, Xiang Ao +4
The exploration/exploitation (E&E) dilemma lies at the core of interactive systems such as online advertising, for which contextual bandit algorithms have been proposed. Bayesian a…
Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification
Binzong Geng, Min Yang, Fajie Yuan +3
Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non…
ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information
Zijun Sun, Xiaoya Li, Xiaofei Sun +6
Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for l…
Defending Against Backdoor Attacks in Natural Language Generation
Xiaofei Sun, Xiaoya Li, Yuxian Meng +4
The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that cou…
Sentence Similarity Based on Contexts
Xiaofei Sun, Yuxian Meng, Xiang Ao +4
Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural…