Ashwin Paranjape
I am a PhD student in the Computer Science Department at Stanford University affiliated with the Natural Language Processing Group. I am advised by Prof. Christopher Manning and I'm currently working on making open domain socialbots sound more conversational when they talk about external knowledge pieces.
Last year I co-led Stanford's team in the Alexa Prize Socialbot competition. This was our first year participating and our bot Chirpy Cardinal placed 2nd place a b c of 10 teams!
Before joining as a PhD student, I spent two years pursing a master's degree in Artificial Intelligence at Stanford broadening my understanding with a variety of courses and conducting research with Prof. Jure Leskovec, Robert West and Austin Benson.
I graduated from Indian Institute of Technology Bombay in 2014, majoring in Computer Science and Engineering with a minor degree in Electrical Engineering.
Publications
-
Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations
Ashwin Paranjape*, Abigail See*, Kathleen Kenealy, Haojun Li, Amelia Hardy, Peng Qi, Kaushik Ram Sadagopan, Nguyet Minh Phu, Dilara Soylu, Christopher D. Manning
Alexa Prize Proceedings 2020 [abstract] [paper] [supplementary] Importance sampling for unbiased on-demand evaluation of knowledge base population Arun Tejasvi Chaganty*, Ashwin Pradeep Paranjape*, Percy Liang and Christopher D. Manning
Empirical Methods in Natural Language Processing (EMNLP) 2017 [abstract] [paper] [code] [service] Motifs in Temporal Networks. Ashwin Paranjape*, Austin Benson*, Jure Leskovec
Tenth ACM International Conference on Web Search and Data Mining (WSDM), 2017. [abstract] [paper] [poster] [code] [data] Improving Website Hyperlink Structure Using Server Logs Ashwin Paranjape*, Robert West*, Jure Leskovec, Leila Zia
9th ACM International Conference on Web Search and Data Mining (WSDM), 2016 [abstract] [paper] [slides] [poster] Mining Missing Hyperlinks from Human Navigation Traces- A Case Study of Wikipedia Robert West, Ashwin Paranjape, and Jure Leskovec
24th International World Wide Web Conference (WWW’15), pp. 1242–1252, Florence, Italy, 2015. [abstract] [paper] Unsupervised Word Sense Disambiguation Using Markov Random Field and Dependency Parser. Devendra Chaplot, Pushpak Bhattacharya and Ashwin Paranjape
29th AAAI Conference on Artificial Intelligence (AAAI), pp. 2217-2223, 2015. [abstract] [paper]
* implies equal contribution
Updates
Our team Chirpy Cardinal stood 2nd place in Alexa Prize 2020. Check out our technical paper and get it touch if you want to know more!
Ashwin Paranjape*, Abigail See*, Kathleen Kenealy, Haojun Li, Amelia Hardy, Peng Qi, Kaushik Ram Sadagopan, Nguyet Minh Phu, Dilara Soylu, Christopher D. Manning Alexa Prize Proceedings 2020 We present Chirpy...
I will be presenting my poster on “Incorporating structure in language models” @ Bay Area Machine Learning Symposium. Would be happy to chat!
I will be attending Pytorch Developer Conference in San Fransisco. Hoping to get some updates on profiling ;)
I presented a poster and gave a lightening talk about my ongoing work on incorporating structure into language models at the West Coast NLP Summit. The invited talks were of...
Arun Tejasvi Chaganty*, Ashwin Pradeep Paranjape*, Percy Liang and Christopher D. Manning Empirical Methods in Natural Language Processing (EMNLP) 2017 Knowledge base population (KBP) systems take in a large document...
I recently toured the Stanford recycling center tour with Nandita Bhaskhar to figure out what happens after all the waste segregation that is asked of Stanford residents. It was an...
Ashwin Paranjape*, Austin Benson*, Jure Leskovec Tenth ACM International Conference on Web Search and Data Mining (WSDM), 2017. Networks are a fundamental tool for modeling complex systems in a variety...