A Comparative Study of Word Embeddings for Reading Comprehension arxiv pdf codeīhuwan Dhingra, Hanxiao Liu, Ruslan Salakhutdinov, William W. Linguistic Knowledge as Memory for Recurrent Neural Networks arxiv pdfīhuwan Dhingra, Zhilin Yang, William W. Quasar: Datasets for Question Answering by Search and Reading arxiv dataīhuwan Dhingra, Kathryn Mazaitis, William W. Evaluating Explanations: How much do explanations from the teacher aid students? arxivĭanish Pruthi, Bhuwan Dhingra, Livio Baldini Soares, Michael Collins,. Cole, Julian Martin Eisenschlos, Daniel Gillick, Jacob Eisenstein, William W. Time-Aware Language Models as Temporal Knowledge Bases arxivīhuwan Dhingra, Jeremy R. Reasoning Over Virtual Knowledge Bases With Open Predicate Relations arxiv market prediction using hidden markov models},Īuthor=,. Fall 2021: CS590.03 Introduction to Natural Language Processing (graduate). Phyllis Ang (PhD, primary adviser: Lisa Wu Wills). Raghuveer Thirukovalluru (PhD, co-advised with Sam Wiseman). Rich Stureborg (PhD, co-advised with Jun Yang). Invited talks at IIT Delhi, UMass Amherst and USC. New preprint on time-aware language models. Teaching CS590.03: Introduction to NLP with Sam Wiseman. 
Organizing the 2nd workshop on Structured & Unstructured KBs at AKBC2021. HMMs o er a mathematical description of a system whose internal state is not known, only its. Their rst widespread use was in speech recognition, although they have since been used in other elds as well 13. Invited talk at UNC Chapel Hill on "Language models as Structured KBs". 2 Hidden Markov models Hidden Markov models (HMMs) are a tool for the statistical analysis of se-quences, especially for signal models. Please only email if you have significant prior experience in NLP or ML. However, if you think you are a very good fit please send an email describing your background and what you want to work on.
Others: Please note that at this point I have limited bandwidth to advise students not currently at Duke. Include your transcript and also mention how much time will you be able to commit to the project. Undergraduate or masters students at Duke: If you are interested in working with me, please send an email describing your background and what specifically you want to work on. Please only email if you have questions which are not answered here, I may not be able to respond to all emails. I am currently looking for students to join my group. PhD applicants: Please apply to the Duke CS PhD program here (next deadline is Dec 15). Reasoning over structured and unstructured knowledge. Adding extra-linguistic contexts, such as time, to language models. Question answering and information retrieval. In between I worked at Qualcomm Research in San Diego, USA. Before that I did Electrical Engineering at IIT Kanpur, where I worked with Amitabha Mukerjee. My thesis advisers were William Cohen and Russ Salakhutdinov. I completed my PhD in 2020 from the Language Technologies Institute at Carnegie Mellon University. My group works on machine learning for natural language processing and knowledge representation.
0 kommentar(er)
