activity
20182021
most citedWarm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings

29 citations · 69 across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2021

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…

cs.CL202115 cited

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…

cs.CL20205 cited

Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information

Yuyang Nie, Yuanhe Tian, Yan Song +2

Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the…

cs.CL20205 cited

Improving Robustness and Generality of NLP Models Using Disentangled Representations

Jiawei Wu, Xiaoya Li, Xiang Ao +3

Supervised neural networks, which first map an input to a single representation , and then map to the output label , have achieved remarkable success in a wide range…

cs.CL2020

Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network

Chi Xu, Hao Feng, Guoxin Yu +3

Most recent existing aspect-term level sentiment analysis (ATSA) approaches combined various neural network models with delicately carved attention mechanisms built upon given aspe…

cs.CL2018

Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents

Ganbin Zhou, Rongyu Cao, Xiang Ao +4

In this study, we focus on extracting knowledgeable snippets and annotating knowledgeable documents from Web corpus, consisting of the documents from social media and We-media. Inf…