COMPSCI 646: Information Retrieval – Fall 2021

COMPSCI 646 is a graduate-level course in Information Retrieval, the science and engineering of indexing, organizing, searching, and making sense of unstructured or mostly unstructured information, particularly text. The class focuses primarily on the underlying models used for effective search and organization, but includes some discussion of efficiency concerns. The course also covers current research problems and methodologies in the field of Information Retrieval.

Tue & Thu, 4:00 – 5:15 PM

CS 142

	Instructor: Hamed Zamani Contact: zamani@cs.umass.edu Office Hours: Tue & Thu, 9:00 – 10:00 AM @ CS 350
	Teaching Assistant: Lakshmi Vikraman Contact: lvnair@cs.umass.edu Office Hours: Mon & Wed, 10:00 – 11:00 AM @ LGRT 220 (T220)

Prerequisites

Proficiency in Python and/or Java
Basic knowledge of probability, statistics, and information theory
Foundations of applied machine learning and deep learning

Textbook

[WBC] W. Bruce Croft, Donald Metzler, and Trevor Strohman. Search Engines: Information Retrieval in Practice. Pearson Education, 2009.
[CDM] Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. Introduction to Information Retrieval. Cambridge University Press, 2008.

Grading

Assignments (3×10%)
Midterm exam (25%): Friday, October 29, 2021, 7 – 9 PM
Final exam, take home (20%)
Final project (25%)

Tentative Schedule

#	Lecture	Date	Readings
1	Introduction	Thu 9/2	[WBC] Ch.1 [WBC] Ch.7.1 [CDM] Ch.8.1, 8.2
2	IR Basics	Tue 9/7	[WBC] Ch.1 [WBC] Ch.7.1 [CDM] Ch.8.1, 8.2
3	IR Evaluation Methodologies, Metrics, and User Models	Thu 9/9	[CDM] Ch.8.3, 8.4 (optional) NDCG: Järvelin and Kekäläinen (TOIS 2002)
4	IR Evaluation Methodologies, Metrics, and User Models	Tue 9/14
5	Text Processing and Indexing	Thu 9/16	[WBC] Ch.4.1, 4.2, 4.3 [WBC] Ch.5.1, 5.2, 5.3, 5.4, 5.7
6	Basic Retrieval Models: Vector Space Models & Probabilistic Retrieval Models	Tue 9/21	[CDM] Ch.6.2, 6.3, 6.4 [CDM] Ch.11.1, 11.2, 11.3, 11.4.3
7	Language Modeling	Thu 9/23	[CDM] Ch.12.1, 12.2, 12.3 (optional) Query likelihood: Ponte and Croft (SIGIR 1998) (optional) KL-divergence retrieval model: Lafferty and Zhai (SIGIR 2001) (optional) Language model smoothing: Zhai and Lafferty (TOIS 2004)
8	Enhanced Language Modeling	Tue 9/28	[WBC] Ch.11.3 [CDM] Ch.12.4 (optional) Cluster-based LM: Liu and Croft (SIGIR 2004) (optional) LDA-based LM: Wei and Croft (SIGIR 2006) (optional) Local document expansion: Tao et al. (NAACL 2006) (optional) General LM: Song and Croft (CIKM 1999) (optional) HMM IR: Miller et al. (SIGIR 1999) (optional) Dependence models: Metzler and Croft (SIGIR 2005) (optional) Positional LM: Lv and Zhai (SIGIR 2009)
9	Relevance Feedback	Thu 9/30	[WBC] Ch.7.3.2 (optional) Relevance models: Lavrenko and Croft (SIGIR 2001) (optional) Model-based feedback: Zhai and Lafferty (CIKM 2001) (optional) Matrix factorization model: Zamani et al. (CIKM 2016)
10	ML Basics & Learning to Rank	Tue. 10/5	LTR Textbook: Li (2011) Ch.1, 2, 6 (optional) LTR Textbook: Li (2011) Ch.4
11	Introduction to Neural Networks and Neural IR	Thu 10/7
12	Distributed Representation Learning for Text	Tue 10/12	word2vec: Mikolov et al. (NIPS 2013) (optional) GloVe: Pennington et al. (EMNLP 2014) (optional) Relevance-based Word Embedding: Zamani and Croft (SIGIR 2017) (optional) Embedding-based Query Expansion: Zamani and Croft (ICTIR 2016)
13	Neural Ranking Models	Thu 10/14	(optional) DSSM: Huang et al. (CIKM 2013) (optional) K-NRM: Xiong et al. (SIGIR 2017) (optional) Duet Model: Mitra et al. (WWW 2017) (optional) SNRM: Zamani et al. (CIKM 2018)
14	Neural Ranking Models	Tue 10/19
15	Implicit Feedback, Biases, and Click Models	Thu 10/21	(optional) Implicit feedback: Joachims et al. (SIGIR 2005) (optional) Click models for web search: Chuklin et al. (2015) (optional) Counterfactual learning: Joachims and Swaminathan (SIGIR 2016) (optional) Unbiased learning to rank: Joachims et al. (WSDM 2017)
16	Web Search: Link Analysis, Spam Filtering, MapReduce	Tue 10/26	[CDM] Ch.21 (optional) PageRank: Page et al. (1998) (optional) HITS: Kleinberg (JACM 1999) (optional) Waterloo spam scorer: Cormack et al. (IRJ 2011)
17	Context-Awareness and Personalization in Search	Thu 10/28	(optional) Context-sensitive language model: Shen et al. (SIGIR 2005) (optional) Web search personalization: Bennett et al. (SIGIR 2012) (optional) Situational context for search: Zamani et al. (WWW 2017)
18	Novelty and Diversity	Tue 11/2	Maximal Marginal Relevance (MMR): Carbonell and Goldstein (SIGIR 1998) Novelty and diversity evaluation: Clarke et al. (SIGIR 2008) (optional) Subtopic retrieval using language models: Zhai et al. (SIGIR 2003) (optional) Term-level diversification: Dang and Croft (SIGIR 2013)
19	User Study and Crowdsourcing in IR	Thu 11/4	Crowdsourcing user studies with Mechanical Turk: Kittur et al. (CHI 2008) (optional) Interactive IR evaluation: Kelly et al. (ICTIR 2015) (optional) Understanding user behaviour from query logs: Dumais et al. (Ways of Knowing in HCI, 2014)
20	Cross- and Multi-Lingual IR	Tue 11/9
	No Class: Veteran’s Day	Thu 11/11
21	Information Filtering and Recommendation	Tue 11/16	(optional) Information Retrieval and Information Filtering: Belkin and Croft (CACM 1992) (optional) Recommender Systems Handbook: Ricci et al. (2015)
22	Information Filtering and Recommendation	Thu 11/18
23	Entity Search	Tue 11/23
	No Class: Thanksgiving	Thu 11/25
24	Question Answering	Tue 11/30
25	Conversational Information Seeking	Thu 12/2
26	Current IR Research	Tue 12/7

Course Policy

Late Submission

Each student has a total of 6 late days without penalty. You can use up to 3 late days per assignment or project milestone excluding project final report. Late submission of team assignments will result in each member of the team being charged for the late days. For example, if a group of two students submitted their project proposal 23 hours after the deadline, this results in 1 late day being used per student.

Once all 6 late days are used, any assignments turned in late will be penalized 20% per late day.

In case of multiple submissions of an assignment, only the last one will be taken into account for the number of late days.

Collaboration and Help

You may discuss the ideas behind assignments with others. You may ask for help understanding class and IR concepts. You may study with friends. However…

The work that you submit must be your own. It may not be copied from the web, from another student in the class, or from anyone else. If you stumble upon and use a solution from the textbook or from class, you are expected to acknowledge the source of the work.

Your effort on exams (mini or final) must be your own. Your homework submissions must be your own work and not in collaboration with anyone. Your project work must be your own work and not a copy of someone else’s work.

Search Google Appliance

Hamed Zamani