• Publications
  • Influence
Hierarchical Attention Networks for Document Classification
Experiments conducted on six large scale text classification tasks demonstrate that the proposed architecture outperform previous methods by a substantial margin. Expand
Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics
The results show that automatic evaluation using unigram co-occurrences between summary pairs correlates surprising well with human evaluations, based on various statistical metrics; while direct application of the BLEU evaluation procedure does not always give good results. Expand
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
A novel neutral network architecture is introduced that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF, thus making it applicable to a wide range of sequence labeling tasks. Expand
OntoNotes: The 90% Solution
It is described the OntoNotes methodology and its result, a large multilingual richly-annotated corpus constructed at 90% interannotator agreement, which will be made available to the community during 2007. Expand
RACE: Large-scale ReAding Comprehension Dataset From Examinations
The proportion of questions that requires reasoning is much larger in RACE than that in other benchmark datasets for reading comprehension, and there is a significant gap between the performance of the state-of-the-art models and the ceiling human performance. Expand
Self-Training With Noisy Student Improves ImageNet Classification
We present a simple self-training method that achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. OnExpand
Unsupervised Data Augmentation for Consistency Training
A new perspective on how to effectively noise unlabeled examples is presented and it is argued that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning. Expand
Determining the Sentiment of Opinions
A system that, given a topic, automatically finds the people who hold opinions about that topic and the sentiment of each opinion and another module for determining word sentiment and another for combining sentiments within a sentence is presented. Expand
Learning surface text patterns for a Question Answering System
This paper has developed a method for learning an optimal set of surface text patterns automatically from a tagged corpus, and calculates the precision of each pattern, and the average precision for each question type. Expand
Government 2.0: Making connections between citizens, data and government
The digital government or electronic government (e-government) has started as a new form of public organization that supports and redefines the existing and new information, communication and transaction-related interactions with stakeholders with the purpose of improving government performance and processes. Expand