Current events (2007)
From LS2
| Dates (tentative) | Topic | Readings | Lecture slides | Reminders | |
| T 8-28 | Philosophy: the empirical way of thinking about language. | Pereira, 2000; Abney, 1996 | |||
| Th 8-30 | Stochastic models for sequences: Markov models, hidden Markov models, and related algorithms | Manning and Schütze, 1999 (ch. 9); Smith, 2004 | assignment 1 out | ||
| T 9-4 | additional notes | ||||
| Th 9-6 | Log-linear/exponential/maximum entropy models, conditional estimation, random fields, CRFs, regularization, and convex optimization | Three tutorials: Adam Berger's tutorial; Smith, 2004, and Ratnaparkhi, 1997. Research papers: Lafferty, McCallum, and Pereira, 2001; Khudanpur and Wu, 2000; Chen and Rosenfeld 1999; Rosenfeld, Chen, and Zhu, 2000; Della Pietra, Della Pietra, and Lafferty, 1995 | |||
| T 9-11 | assignment 1 due | ||||
| Th 9-13 | lit. review proposal due 5pm (post on your "talk" page, here); assignment 2 out | ||||
| T 9-18 | |||||
| Th 9-20 | Weighted finite-state technology | Mohri's list of references on algorithms; Eisner, 2002; Stolcke and Omohundro 1993, Kartunnen, 2001 . Tools: Xerox's FS group; AT&T FSM libraries; RWTH FSA toolkit; OpenFST | |||
| T 9-25 | assignment 2 due | ||||
| Th 9-27 | Stochastic grammars, statistical parsing | Johnson, 1998 | set up a meeting with Noah sometime next week to discuss lit. review; assignment 3 out | ||
| T 10-2 | |||||
| Th 10-4 | Dependency parsing | McDonald, Pereira, Ribarov, and Hajic, 2005 | |||
| T 10-9 | Collins, Charniak, and Klein/Manning parsers | Charniak, 1997; Charniak, 2000; Collins, 2003; Klein and Manning, 2003 | assignment 3 due | ||
| Th 10-11 | Weighted dynamic programming | Goodman, 1999; Eisner, Goldlust, and Smith, 2005; if you're in love, Shieber, Schabes, and Pereira, 1995 | assignment 4 out | ||
| T 10-16 | |||||
| Th 10-18 | Going discriminative: perceptron, boosting, maximum margin estimation | Collins, 2002; Altun, Johnson, and Hofmann, 2003; Taskar and Klein's ACL 2005 tutorial | |||
| T 10-23 | Guest lecture: Einat Minkov (information extraction) | assignment 4 due | |||
| Th 10-25 | Guest lecture: Amr Ahmed (statistical machine translation) | lit. review draft due tomorrow at 5pm (email to Noah) | |||
| T 10-30 | Discriminative learning continued | ||||
| Th 11-1 | assignment 5 out | ||||
| T 11-6 | Going unsupervised: clustering and EM, clustering words | Brown et al., 1992; Pereira, Tishby, and Lee, 1993; Schütze, 1993 | |||
| Th 11-8 | EM algorithm for structured models, and with hidden data and partially-hidden data; contrastive estimation | Merialdo, 1994; Pereira and Schabes, 1992; Klein and Manning, 2002; Smith and Eisner, 2005 | |||
| T 11-13 | Going Bayesian | Blei, Ng, and Jordan, 2003; Goldwater and Griffiths, 2007; Liang and Klein's ACL 2007 tutorial | assignment 5 due | ||
| Th 11-15 | Going semisupervised: Yarowsky algorithms, co-training | Yarowsky, 1995; Blum and Mitchell, 1998; Nigam and Ghani, 2000; Abney, 2004, Smith and Eisner, 2007; see also Jerry Zhu's semisupervised learning survey | |||
| T 11-20 | Experimentation and hypothesis testing | lit. review due tomorrow at 5pm (email to Noah) | |||
| Th 11-22 | Thanksgiving (no class) | ||||
| T 11-27 | Oral presentations | relation extraction; historical linguistics; named-entity translation | |||
| Th 11-29 | Oral presentations |
data-oriented parsing; summarization; textual entailment and paraphrase | |||
| T 12-4 | Oral presentations | sentiment classification; cross-language learning | |||
| Th 12-6 | Oral presentations | coreference resolution; active learning | |||
| F 12-14 | Final exam (8:30-11:30 am, location TBD) |
