Mohammad Aliannejadi
(aka. Alian Nejadi)

Assistant Professor
IRLab
University of Amsterdam
Science Park 904
1098 XH Amsterdam, The Netherlands
Email:  m.aliannejadi@uva.nl


I am an assistant professor at IRLab (formerly known as ILPS), the University of Amsterdam in The Netherlands. I obtained my Ph.D. in the Faculty of Informatics, Università della Svizzera italiana (USI) in Lugano, Switzerland. During my Ph.D., I spent four months visiting CIIR at the University of Massachusetts, Amherst, USA. Before my Ph.D., I completed my MSc degree in the Department of Computer Engineering and Information Technologies at Tehran Polytechnic, Tehran, Iran.

My Ph.D. topic was on modeling user information needs on mobile devices. I studied this problem in three different settings. Therefore, I had the chance to explore multiple directions in Information Retrieval (IR), namely, recommender systems, unified (meta) search, and conversational systems. I intend to continue working mainly on conversational search system during my post-doctoral at UvA while exploring various areas related to IR, machine learning, and NLP.

I have been actively part of the IR community, serving as a SIGIR Student Liaison for two years. I have co-organized several shared tasks and workshops on recommender systems and conversational systems. In particular, I am co-organizing the IGLU Contest at NeurIPS 2021, and the XMRec Workshop co-located with RecSys 2021. Also, I have co-organized the SCAI Workshop, co-located with EMNLP 2020 and MICROS Workshop co-located with ECIR 2020. As part of the SCAI Workshop, I chaired a shared task, i.e., the third version of the ConvAI challenges, focusing on mixed-initiative information-seeking conversations, called ClariQ. Also, I have been publishing and attending major IR conferences such as SIGIR, CIKM, CHIIR, ICTIR, and ECIR. Please check out my Google Scholar, Semantic Scholar, and DBLP profiles for more details. Moreover, I have been a member of program committees (PC) of various conferences such as SIGIR, ACL, WSDM, TheWebConference (WWW), EACL, ICTIR, and ECIR, while reviewing for major journals in the field such as TOIS, TKDE, IP&M, and ESWA.


Organizational duties and activities


Data

  • XMarket (New!) XMarket is a cross-market prodcut recommendation data, crawled from Amazon. The data is publicly available and can be found here. We are also organizing a shared task as a WSDM Cup challenge, called XMRec on the same topic. For more information, visit XMRec WSDM Cup homepage.
  • ClariQ (New!) ClariQ is the SCAI Workshop data challenge on conversational search clarification. The challenge instructions and data is publicly available here. More details and analysis can be found in our paper. Also, more information about the challenge and the leaderboard can be found on ConvAI homepage.
  • ConvKeyConvKey contains a set of informative keywords extracted from news articles and mixed-initiative conversations, used for improved document ranking in conversational search. The data is publicly available here. More details and analysis can be found in our paper.
  • LSApp LSApp is a large dataset of sequential mobile app usage, consisting of ~600K app usage records of ~300 users. LSApp is a complementary collection to ISTAS where we also collect sequential app usage events of the users. During the study, we asked the participants to report their mobile searches using uSearch as soon as they conducted the search. In the meantime, we collected their app usage statistics with their consent. The data createdtion and stats are described in our TOIS paper.
  • CAsTUR CAsTUR consists of a set of relevance labels that we collected on conversational utterances of the TREC CAsT 2019. We aimed to identify the relevant conversational turns in a conversation as context of an utterance. The data is publicly available here. More details and analysis can be found in our CHIIR 2020 paper.
  • ANTIQUE ANTIQUE is an open-domain non-factoid question answering benchmark, collected from diverse categories of Yahoo! Answers.. You can find more details on the collection in our ECIR 2020 paper. ANTIQUE is publicly available here.
  • Qulac We have released Qulac, the data collection we created as part of our SIGIR paper, Qulac: a dataset on asking Questions for Lack of Clarity in open-domain information-seeking conversations.. You can find more details on the collection here.
  • ISTAS We have released the source code of the app as well as the data collection we created as part of our CIKM paper, ISTAS: a collection of mobile cross-app search queries. You can find more details on the collection here.
  • UniMobile We have released the data collection we created as part of our SIGIR paper, UniMobile: a collection of mobile cross-app search queries. You can find more details on the collection here.
  • TREC-CS We have released the data collection that we crawled and used for our participations in the TREC Contextual Suggestion track. You can find more details on the data collection and how to gain access to it here.

Code


Publications

2022

2021

2020

2019

2018

2017

2016 and before