COMPSCI 546: Applied Information Retrieval (Spring 2021)

COMPSCI 546 is a graduate level course intended to cover information retrieval and other information processing activities, from an applied perspective. There will be multiple programming projects, as well as short answer homeworks. It provides a richer technical follow on to COMPSCI 446 (Search Engines), for undergraduates interested in a deeper understanding of the technologies. It also provides a strong basis for continuing on with COMPSCI 646 (Information Retrieval), for those graduate students who are interested in a more complete theoretical coverage of the area. Topics will include: search engine construction (document acquisition, processing, indexing, and querying); learning to rank; information retrieval system performance evaluation; classification and clustering; other machine learning information processing tasks; and many more.

Time: Tue & Thu, 10:00 - 11:15 AM

Location: Virtual!

Instructor

Hamed Zamani

Contact: zamani@cs.umass.edu

Office Hour: Tue 11:30 - 12:30 & Thu 16:00 - 17:00

Teaching Assistant

Lakshmi Vikraman

Contact: lvnair@cs.umass.edu

Office Hour: Mon 16:00 - 17:00 & Wed 11:00 - 12:00

Prerequisites

Proficiency in Python is highly recommended.

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: 7x10% (+1 optional assignment: extra 10%)
Final exam: 30%

Tentative Schedule

#	Date	Lecture	Readings	Note
1	Tue Feb 2	Introduction to IR	[WBC] Ch.1 [WBC] Ch.7.1 [CDM] Ch.8.1, 8.2
2	Thu Feb 4	Introduction to IR	[WBC] Ch.1 [WBC] Ch.7.1 [CDM] Ch.8.1, 8.2
3	Tue Feb 9	IR Evaluation and Ranking Metrics	[CDM] Ch.8.3, 8.4 (optional) NDCG: Järvelin and Kekäläinen (TOIS 2002)
4	Thu Feb 11	IR Evaluation and Ranking Metrics		Assignment 1 - IR Metrics (deadline: Feb 18)
5	Tue Feb 16	Text Processing	[WBC] Ch.4.1, 4.2, 4.3
6	Thu Feb 18	Indexing	[WBC] Ch.5.1, 5.2, 5.3, 5.4, 5.7	Assignment 2 - Text Processing and Indexing (deadline: Mar 2)
7	Tue Feb 23	Basic Retrieval Models	[CDM] Ch.6.2, 6.3, 6.4 [CDM] Ch.18 [CDM] Ch.11.1, 11.2, 11.3, 11.4.3 (optional) LSI: Deerwester et al. (JASIS 1990)
8	Thu Feb 25	Basic Retrieval Models
9	Tue Mar 2	Language Models for IR	[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)	If you are interested in learning more about language modeling for IR, the book "Statistical Language Models for Information Retrieval" by ChengXiang Zhai is recommended.
10	Thu Mar 4	Language Models for IR		Assignment 3 - Retrieval Models (deadline: Mar 11)
11	Tue Mar 9	Query Expansion and Relevance Feedback	[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)
12	Thu Mar 11	Web Search	[CDM] Ch.21 (optional) PageRank: Page et al. (1998) (optional) HITS: Kleinberg (JACM 1999) (optional) Waterloo spam scorer: Cormack et al. (IRJ 2011)	Assignment 4 - Query Expansion (deadline: Mar 18)
13	Tue Mar 16	Search Engine Technologies
14	Thu Mar 18	Question Answering		Assignment 5 - Link Analysis (deadline: Mar 30)
15	Tue Mar 23	Novelty and Diversity in IR	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)
16	Thu Mar 25	Machine Learning Basics
17	Tue Mar 30	Document Clustering		Assignment 6 - Clustering (deadline: Apr 8)
18	Thu Apr 1	Document Classification
19	Tue Apr 6	Learning to Rank	LTR Textbook: Li (2011) Ch.1, 2, 6 (optional) LTR Textbook: Li (2011) Ch.4
20	Thu Apr 8	Learning to Rank
21	Tue Apr 13	Neural Information Retrieval	word2vec: Mikolov et al. (NIPS 2013) Transformer: Vaswani et al. (NeurIPS 2017) BERT: Devlin et al. (NAACL 2019) Neural Ranking Models Survey: Guo et al. (IPM 2020) Weak Supervision for Ranking: Dehghani et al. (SIGIR 2017) From Neural Re-Ranking to Ranking: Zamani et al. (CIKM 2018) (optional) Introduction to Neural IR (Survey): Mitra and Craswell (optional) BERT and Beyond (Survey): Lin et al. (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) (optional) The Duet Model: Mitra et al. (WWW 2017) (optional) The KNRM Model: Xiong et al. (SIGIR 2017)	Assignment 7 - Learning to Rank (deadline: Apr 22)
22	Thu Apr 15	Neural Information Retrieval		Assignment 7 - Learning to Rank (deadline: Apr 22)
	Tue Apr 20	No class (Wednesday schedule)
23	Thu Apr 22	Recommender Systems	(optional) Information Retrieval and Information Filtering: Belkin and Croft (CACM 1992) (optional) Recommender Systems Handbook: Ricci et al. (2015)
24	Tue Apr 27	Recommender Systems		Assignment 8 - Collaborative Filtering (deadline: May 4)
25	Thu Apr 29	IR Applications
26	Tue May 4	IR Research

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, nor done in collaboration with anyone.

Last update: Mar. 18, 2021