Trong Duc Nguyen
Iowa State University
16 Papers
13 Citations
Trong Duc Nguyen is an academic researcher from Iowa State University. The author has contributed to research in topics: Sampling (statistics) & Computer science. The author has an hindex of 7, co-authored 16 publications.
Chat about Author
Papers
Exploring API embedding for API usages and applications
Trong Duc Nguyen,Anh Tuan Nguyen,Hung Dang Phan,Tien N. Nguyen +3 more
- 20 May 2017
TL;DR: This work develops API2API, a tool to automatically learn the APImappings between Java and C# using a characteristic of the API2VECvectors for API elements in the two languages: semantic relations amongAPI elements in their usages are observed in theTwo vectorspaces for the two Languages as similar geometric arrangements among their API2 VEC vectors.
204
Stratified random sampling from streaming and stored data
TL;DR: In this paper, it was shown that any streaming algorithm for SRS over the entire stream must have, in the worst case, a variance that is a factor away from the optimal, where r is the number of strata.
61
A deep neural network language model with contexts for source code
Anh Tuan Nguyen,Trong Duc Nguyen,Hung Dang Phan,Tien N. Nguyen +3 more
- 20 Mar 2018
TL;DR: Dnn4C is presented, a DNN language model that complements the local context of lexical code elements with both syntactic and type contexts and helps improve accuracy over n-gram LM in migrating source code from Java to C# with a machine translation model.
57
Stratified Random Sampling from Streaming and Stored Data
Trong Duc Nguyen,Ming-Hung Shih,Divesh Srivastava,Srikanta Tirthapura,Bojian Xu +4 more
- 01 Mar 2019
TL;DR: It is proved that any sliding window-based streaming SRS needs a workspace of $$varOmega (rM\log W)$$ in the worst case, to maintain a variance-optimal SRS of size M, where W is the number of elements in the sliding window.
47
Combining Word2Vec with revised vector space model for better code retrieval
Thanh V. Nguyen,Anh Tuan Nguyen,Hung Dang Phan,Trong Duc Nguyen,Tien N. Nguyen +4 more
- 20 May 2017
TL;DR: A preliminary study suggests that combining traditional IR with Word2Vec achieves better retrieval accuracy, and more experiments need to be done to study different types of combination among two lines of approaches.
40