Topics in Natural Language Processing

TOPICS IN NATURAL LANGUAGE PROCESSING

Lecturer: Shay Cohen
Time and Location: Tuesday and Friday, 17:10-18:00, H.R.B Lecture Theatre, Rosbon Building (semester 2)
Office Hours: Tuesday, 14:30-15:30. Could also set an appointment.

SCHEDULE

Part I: Lectures

Week	No.	Date	Topic	Slides	Reading
1	1	12/1/16	Introduction	slides	History of NLP (Karen Sparck Jones)
1	2	15/1/16	Statistical Learning Paradigms in NLP	slides	Probability for linguists (John Goldsmith)
2	3	19/1/16	Statistical Learning Paradigms in NLP	slides	Bayesian inference with tears (Kevin Knight)
2	4	22/1/16	Bayesian Learning (continued)	slides
3	5	26/1/16	Structure in NLP and Probabilistic Grammar Formalisms	slides	PCFGs (Michael Collins) Linguistic Structure Prediction, Smith (2011), Chapter 1
3	6	29/1/16	Probabilistic Grammar Formalisms and Inference in NLP	slides	Linguistic Structure Prediction, Smith (2011), Chapter 2. See also readings from last class.
4	7	2/2/16	Learning Algorithms	slides	Log-linear models (Michael Collins), Log-linear models (Noah Smith)
4	8	5/2/16	Learning from Incomplete Data	slides	Linguistic Structure Prediction, Smith (2011), Chapter 3

Part II: Student presentations

9/2:

Matus Falis: Reading Tea Leaves: How Humans Interpret Topic Models, Chang et al., NIPS (2009). [slides] [Merce Vintro Ricart, Pengfei Tan]
Merce Vintro Ricart: Probabilistic Latent Semantic Indexing, Hofmann, SIGIR (1999). [slides] [Matus Falis, Pengfei Tan]

12/2:

Pengfei Tan: A Neural Probabilistic Language Model, Bengio et al., JMLR (2003). [slides] [Matus Falis, Merce Vintro Ricart]
Lingzhe Zhao: Probabilistic Topic Models, Steyvers and Griffiths (2007). [slides] [Georgia Maniati, Iulia Banghea]

23/2:

Jason Chen: Natural Language Processing (Almost) from Scratch, Collobert et al., JMLR (2011). [slides] [Paul Coles, Mattias Applegren]
Paul Coles: Better Word Representations with Recursive Neural Networks for Morphology, Luong et al., CoNLL (2013). [slides] [Mattias Applegren, Jason Chen]

26/2:

Massimo Innamorati: Word Embeddings: A Simple and General Method for Semi-supervised Learning, Turian et al., ACL (2010). [slides] [Andrew Watson, Chase Stevens]
Mattias Applegren: Learning Continuous Phrase Representations and Syntactic Parsing with Recursive Neural Networks, Socher et al., NIPS (2010). [slides] [Paul Coles, Jason Chen]

1/3:

Chase Stevens: Memory Networks, Weston et al., ICLR (2015). [slides] [Andrew Watson, Massimo Innamorati]
Andrew Watson: Linguistic Regularities in Continuous Space Word Representations, Mikolov et al., NAACL (2013). [slides] [Massimo Innamorati, Chase Stevens]

4/3:

Etienne De Crecy: Abstract Meaning Representation for Sembanking, Banarescu et al., LAWID (2013). [slides] [Hanzhang Xia, Amanda Tollafield-Small]
Hanzhang Xia: Universal Conceptual Cognitive Annotation, Abend and Rappoport, ACL (2013). [slides] [Etienne De Crecy, Amanda Tollafield-Small]

8/3:

Amanda Tollafield-Small: Automatic Labeling of Semantic Roles, Gildea and Jurafsky, CL (2002). [slides] [Etienne De Crecy, Georgia Maniati]
Georgia Maniati: Unsupervised Induction of Semantic Roles, Lang and Lapata, NAACL (2010). [slides] [Lingzhe Zhao, Hanzhang Xia]

11/3:

Ahmad Khaleeq: A Generative Model for Parsing Natural Language to Meaning Representations, Lu et al., EMNLP (2008). [slides] [Nadia Petersen, Guanyi Chen]
Iulia Banghea: Automatic Identification of General and Specific Sentences by Leveraging Discourse Annotations, Louis and Nenkova, IJCAI (2011). [slides] [Yue Yu, Alexei De Bono]

15/3:

Yue Yu: Detecting Learner Errors in the Choice of Content Words Using Compositional Distributional Semantics, Kochmar and Briscoe, COLING (2014). [slides] [Jakim Berndsen, Lingzhe Zhao]
Nicholas Mifsud: Unsupervised Word Sense Disambiguation Rivaling Supervised Methods, Yarowsky, ACL (1995). [slides] [Valentina Pyatkin, Pilar Oplustil]

18/3:

Guanyi Chen: Bayesian Inference for PCFGs via Markov Chain Monte Carlo, Johnson et al., NAACL (2007). [slides] [Nadia Petersen, Chunchuan Lyu]
Nadia Petersen: Dependency Parsing for Turkish, Eryigit, CL (2008). [slides] [Guanyi Chen, Ahmad Khaleeq]

22/3:

Pilar Oplustil: Learning OT Constraint Rankings Using a Maximum Entropy Model, Goldwater and Johnson, SWVOT (2003). [slides] [Valentina Pyatkin, Nicholas Mifsud]
Chunchuan Lyu: The Informational Complexity of Learning from Examples, Chapter 4, Niyogi (1995). [slides] [Yue Yu, Ahmad Khaleeq]

25/3:

Liquan Chai: Combining Multiple Information Types in Bayesian Word Segmentation, Doyle and Levy, NAACL (2013). [slides] [Alexei De Bono, Chunchuan Lyu]
Valentina Pyatkin: Word-Sense Disambiguation for Machine Translation, Vickrey et al., EMNLP (2005). [slides] [Pilar Oplustil, Nicholas Mifsud]

29/3:

Pia Chau: The Penn Discourse TreeBank 2.0, Prasad et al., LREC (2008). [slides] [Qianchu Liu, Iulia Banghea]
Qianchu Liu: Clause Restructing for Statistical Machine Translation, Collins et al., ACL (2005). [slides] [Pia Chau, Jakim Berndsen]

1/4:

Alexei De Bono: Combining Distributional and Morphological Information for Part of Speech Induction, Clark, EACL (2003). [slides] [Liquan Chai, Qiyang Zhang]
Jakim Berndsen: Recurrent Neural Network Based Language Model, Mikolov et al., INTERSPEECH (2010). [slides] [Qianchu Liu, Qiyang Zhang]
Qiyang Zhang: KenLM: Faster and Smaller Language Model Queries, Kenneth Heafield, WSMT (2011). [slides] [Pia Chau, Yue Yu]

Back to main page.

Home : Teaching : Courses : Tnlp : 2016