I am a Researcher at Microsoft AI Research, working on a wide range of information retrieval, natural language processing, and machine learning problems. Prior to Microsoft, I spent four years (2015-2019) at the Center for Intelligent Information Retrieval (CIIR), University of Massachusetts Amherst (UMass), where I was a Ph.D. Candidate (with distinction) under supervision of W. Bruce Croft. During my Ph.D., I completed three summer internships at Microsoft AI Research (2017, 2019) and Google Research (2016). I received my M.Sc. and B.Sc. degrees from the University of Tehran.
I am an active member of the information retrieval (IR) community and regularly publish at the major IR venues, such as SIGIR, WSDM, WWW, CIKM, ICTIR, and ECIR. A brief description of my past and current research is presented below.
My research interests include various aspects of information retrieval, recommender systems, and text mining. My major contributions and current research focus include:
Neural Information Retrieval: Following our initial study on distributed representations for information retrieval (ICTIR16a, ICTIR16b, CIKM16), we have developed multiple neural network models for the fundamental IR tasks. They include relevance-based word embedding (SIGIR17a), context-aware query representation (WWW17), and semi-structured document representation (WSDM18). We have also invented the first learning to rank model that can retrieve (as opposed to re-rank) documents from large-scale collections, called standalone neural ranking model (CIKM18a).
Weak Supervision for IR: We have developed a student-teacher learning model for training machine learning IR models with no labeled data, called weak supervision. We have empirically shown the effectiveness of weak supervision in various IR tasks, including ad-hoc retrieval (SIGIR17b), representation learning (SIGIR17a), and query performance prediction (SIGIR18a). We have also theoretically study weak supervision for information retrieval (ICTIR18). Check out our SIGIR 2018 workshop on learning from limited or noisy data (LND4IR).
Conversational Information Seeking: I have recently started working on conversational search and recommendation tasks.
We have designed and implemented an extensible platform for conversational information seeking research, called Macaw (see the GitHub repository).
We have developed models for generating clarifying questions (WWW20) and offline evaluation methodologies for asking clarifying questions in conversational systems (SIGIR19a). We have also proposed a unified search framework for mobile devices (SIGIR18b, CIKM18b). More is coming, stay tuned!
IR Meets RecSys: I have made efforts on bridging the gap between the IR and RecSys communities. We have modeled query expansion as collaborative filtering (CIKM16), proposed content-based recommendation models using IR techniques (RecSys17, IRJ18), and designed a joint search and recommendation model (DESIRES18, WSDM20). I co-organized the ACM Recommender Systems Challenge in 2018 on music playlist generation and continuation, which can be seen as a RecSys or IR task (RecSys18). Check out our visions on music recommendation (IJMIR18) and the overview of ACM RecSys Challenge 2018 (TIST19).
In Fall 2018, I taught CS646, the Information Retrieval course (PhD-level), at UMass Amherst. The course webpage is available here.
- H. Zamani, S. Dumais, N. Craswell, P. Bennett, G. Lueck. “Generating Clarifying Questions for Information Retrieval”, WWW 2020.
- H. Zamani, N. Craswell. “Macaw: An Extensible Conversational Information Seeking Platform”.
- H. Zamani, W. B. Croft. “Learning a Joint Search and Recommendation Model from User-Item Interactions”, WSDM 2020.
- M. Aliannejadi, H. Zamani, F. Crestani, W. B. Croft. “Asking Clarifying Questions in Open-Domain Information Seeking Conversations”, SIGIR 2019.
- H. Zamani, M. Dehghani, W. B. Croft, E. Learned-Miller, J. Kamps “From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing”, CIKM 2018.
- H. Zamani, W. B. Croft. “On the Theory of Weak Supervision for Information Retrieval”, ICTIR 2018.
- H. Zamani, B. Mitra, X. Song, N. Craswell, S. Tiwary. “Neural Ranking Models with Multiple Document Fields”, WSDM 2018.
- H. Zamani, W. B. Croft. “Relevance-based Word Embedding”, SIGIR 2017.
- M. Dehghani, H. Zamani, A. Severyn, J. Kamps, W. B. Croft. “Neural Ranking Models with Weak Supervision”, SIGIR 2017.
- H. Zamani, M. Bendersky, X. Wang, M. Zhang. “Situational Context for Ranking in Personal Search”, WWW 2017.
- H. Zamani, J. Dadashkarimi, A. Shakery, W. B. Croft. “Pseudo-Relevance Feedback Based on Matrix Factorization”, CIKM 2016.
- H. Zamani, W. B. Croft. “Embedding-based Query Language Models”, ICTIR 2016.
- H. Zamani, W. B. Croft. “Estimating Embedding Vectors for Queries”, ICTIR 2016.
- More on the publications page.
- Organizer / Chair:
- SIGIR 2018 Workshop: Learning from Limited or Noisy Data for Information Retrieval
- RecSys 2018 Workshop: ACM RecSys Challenge 2018
- Senior Program Committee:
- SIGIR 2020
- Program Committee:
- SIGIR 2018 – 2019
- The Web Conference (WWW) 2018 – 2020
- WSDM 2018 – 2020
- RecSys 2018 – 2019
- CIKM 2017 – 2019
- ICTIR 2019
- NAACL 2019
- ECIR 2019 (short papers)
- DESIRES 2020
- Workshops: SCAI @ IJCAI 2019 – EARS @ SIGIR 2018 – KG4IR @ SIGIR 2017, 2018 – NeuIR @ SIGIR 2017 – LEARNER @ ICTIR 2017 – RecSysChallenge @ RecSys 2017
- Journal Reviewer:
- Inf. Syst.
- ACM SIGIR Student Liaison (representing North and South Americas) 2017 – 2019
- Dagstuhl Conversational Search Seminar, Wadern, Germany, November 14, 2019
- Allen Institute for Artificial Intelligence (AI2), Seattle, WA, June 20, 2019
- Microsoft Research, Redmond, WA, June 6, 2019
- University of Tehran, Tehran, Iran, April 9, 2019
- Purdue University, West Lafayette, IN, March 27-28, 2019
- University of Illinois, Chicago, IL, March 19, 2019
- University of Texas, Austin, TX, March 12, 2019
- University of North Texas, Denton, TX, March 8, 2019
- Yale University, New Haven, CT, February 28, 2019 Link
- University of Maryland, College Park, MD, February 20-21, 2019 Link
- University of Pittsburgh, PA, February 4-5, 2019 Link
- UMass Data Science Talk, Amherst, MA, October 24, 2018 Link
- Microsoft Research, Redmond, WA, September 18, 2018
- Google Research, Mountain View, CA, March 21, 2018
- Amazon’s A9, Palo Alto, CA, March 19, 2018 (with Bruce Croft and Qingyao Ai)
- Yale University, New Haven, CT, March 2, 2018 Link
|Dec 19, 2019||We have designed and implemented an open-source platform for conversational information seeking research, called Macaw. Macaw is open-sourced under the MIT License [paper] [GitHub Repo].|
|Nov 14, 2019||I gave a talk on “Clarification in Conversational Search” at the Dagstuhl Conversational Search Seminar. I will be releasing an open-source framework for conversational information seeking research soon. Stay tuned!|
|Oct 18, 2019||Our ICTIR 2019 paper won the best short paper honorable mention award. In the same week, our paper on entity-centric retrieval for multi-hop QA won the best paper award at EMNPL-MRQA 2019.|
|Aug 27, 2019||I have defended my Ph.D. dissertation, entitled “Neural Models for Information Retrieval without Labeled Data”.|
|Aug 4, 2019||I will be joining Microsoft AI Research as a Researcher in September!|
|Apr 22, 2019||Joining Microsoft AI Research as an intern to work with Susan Dumais on conversational search.|
|Apr 14, 2019||Two papers accepted at SIGIR 2019! See publication page.|
|Apr 5, 2019||I am honored to receive the “Search and AI” Award in 2018-2019 (Sponsored by Microsoft Research). Visit here for the citation.|
|Aug 6, 2018||Two full papers accepted at CIKM 2018! See publication page.|
|Apr 11, 2018||5 papers accepted at SIGIR 2018! See publication page.|