Ashish Vaswani
I am a Computer Scientist in the Natural Language Group at the USC Information Sciences Institute. I did my PhD at USC under Dr. David Chiang and Dr. Liang Huang. I can be reached at vaswani at usc dot edu.
- Link to a tutorial that I gave on Discrete and Continuous language models at the NSF Interdisciplinary Workshop on Statistical NLP and Software Engineering .You can download the slides here.
Papers and Code
- Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States, Ashish Vaswani and Kenji Sagae (Equal Contribution). To appear in TACL.
- EUREKA: A toolkit for training LSTM Languge Models and LSTM Encoder Decoder Models with MLE and Noise Contrastive Estimation [code]
- Unifying Bayesian Inference and Vector Space Models for Improved Decipherment, Qing Dou*, Ashish Vaswani*, Kevin Knight, and Chris Dyer. In proceedings of ACL 2015[pdf].*Equal Contribution.
- Model Invertibility Regularization (MIR): Sequence Alignment With or Without Parallel Data, Tomer Levinboim, Ashish Vaswani, and David Chiang. In proceedings of NAACL 2015[pdf]
- Aligning context-based statistical models of language with brain activity during reading, Leila Wehbe, Ashish Vaswani, Kevin Knight, and Tom Mitchell, 2014. In proceedings of EMNLP[pdf]
- Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation, Qing Dou, Ashish Vaswani, and Kevin Knight, 2014. In proceedings of EMNLP[pdf]
- Learning word embeddings with a restricted Boltzmann machine and noise contrastive estimation[code]
- Decoding with large-scale neural language models improves translation. Ashish
Vaswani, Yinggong Zhao, Victoria Fossum, and David Chiang, 2013. In Proceedings of EMNLP [pdf] [code]
- The International Workshop on Language Preservation: An experiment in text collection and language technology. Steven Bird, David Chiang, Friedel Frowein, Andrea L. Berez, Mark Eby, Florian Hanke, Ryan Shelby, Ashish Vaswani, and Ada Wan, 2013. Language Documentation and Conservation 7:155[pdf]
- Learning Whom to Trust with MACE. Dirk Hovy, Taylor Berg-Kirkpatrick, Ashish Vaswani, and Eduard Hovy. In proceecings of NAACL [pdf]
- Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm. Ashish
Vaswani, Liang Huang, and David Chiang, 2012. In proceedings of ACL [pdf] [code]
- Rule Markov models for fast tree-to-string translation. Ashish
Vaswani, Haitao Mi, Liang Huang, and David Chiang, 2011. In Proceedings
of ACL.[pdf][bib]
- Efficient optimization of an MDL-inspired objective function for
unsupervised part-of-speech tagging. Ashish Vaswani, Adam Pauls, and
David Chiang, 2010. In Proceedings of ACL. [pdf]
- Models and Training for Unsupervised Preposition Sense
Disambiguation. Dirk Hovy, Ashish Vaswani, Stephen Tratz, David Chiang,
and Eduard Hovy, 2011. In Proceedings of ACL. [pdf]
- Fast, greedy model minimization for unsupervised tagging. Sujith
Ravi, Ashish Vaswani, Kevin Knight, and David Chiang, 2010. In
Proceedings of COLING. [pdf]
- Activity Based Dialogue Analysis As Evaluation Method. Bilyana
Martinovski and Ashish Vaswani,2006 In procedings of the Interspeech
Workshop: Dialogue on Dialogue. [pdf]
- Hassan: A Virtual Human For Tactical Questioning. David Traum,
Antonio Roque, Anton Leuski, Panayiotis Georgiou, Jillian Gerten,
Bilyana Martinovski, Shri Narayanan, Susan Robinson, and Ashish
Vaswani,2007. In Proceedings of the 8th SIGdial Workshop on Discourse
and Dialogue. [pdf]
- Evaluation Of A Spoken Dialogue System For Virtual Reality Call
For Fire Training. Susan. Robinson, Antonio Roque, Ashish Vaswani,
Charles Hernandez, Bill Millspaugh, and David Traum, 2006. In
Proceedings of the 25th Army Science Conference. Best paper award. [pdf]
- Radiobot-CFF: A Spoken Dialogue System For Military Training.
Antonio Roque, Anton Leuski, Vivek Rangarajan, Susan Robinson,
Ashish Vaswani, Shri Narayanan, and David Traum, 2006. In Proceedings
of Interspeech. [pdf]
- Compressing Large Graphs Using Partially Complemented
Representations. Shiva Kintali, Ashish Vaswani, David Kempe, and
Vishal Shah (In Preparation)
Awards
- Best Paper Award at the 25th Army Science Conference, 2006
- Best Paper Award at the Information Sciences Institute Graduate Research Symposium, 2010
- Runner-Up Best Presentation Award at the Information Sciences Institute Graduate Research
Symposium, 2010