SPAN 413.01, Natural Language Processing in Spanish

Time and place: MWF 2:00 - 2:50, Newcomb Hall 123
Prof. Harry Howard

Office: Newcomb Hall 322-D
862-3417 (voice mail 24 hours a day)
Office hours: MW 4:30-5:30, T 4-5 and by appointment

Course language: As in almost all of the courses offered with the SPAN prefix, this course is taught in Spanish. However, this initial information is in English because one of the goals of the course is to translate it into Spanish.

Overview: Natural Language Processing in Spanish teaches you how to use a computer to do useful things with the Spanish language. Hopefully you'll finish the semester with some practical knowledge about solving linguistic problems, such as techniques for filtering junk email, automatically discovering the different meanings of a word, automatically translating from one language to another, and identifying the author of a text from the statistics of the words that he or she uses. You will also become familiar with the computer programming language called Python, which is easy to learn and makes doing many tasks in natural language processing rather simple. It is great training if you are interested in doing natural language processing work in industry, either in a research lab (Google, Microsoft, Powerset, Yahoo, etc.) or in a startup. As part of the course, we will use Google translate to translate an English-language textbook on natural language processing to Spanish, with the help of a research group in Barcelona.

Objectives:

• You will learn some linguistics: word categorization, syntax, sentence and discourse semantics.
• You will learn some algorithms: part-of-speech tagging, parsing, building feature-based grammars, text classification, information extraction.
• You will learn some statistics: frequency distribution, Bayesian inference, maximum entropy.
• You will learn some computer programming: how to do all this in Python.
• You will learn some Spanish: the technical vocabulary of linguistics, computing, and computer programming.
• You will learn about translation: tools for doing it, problems and challenges of actually doing it.

Outcomes: For you to demonstrate your attainment of these objectives, you will perform the following tasks:

• Do daily homework assignments. This is a hands-on course, in which you actually learn how to do something. Learning how to do something takes practice, though. The homework will not be graded.
• Take a quiz or turn in a project almost every week, on Monday. [11-1 * 7.5% = 75%]
  • No quiz/project can be accepted late, though I will drop the lowest grade.
  • Even though these look like a lot of small grades, missing just one lowers your final grade almost an entire letter, as an unfortunate few have found out the hard way.
  • If you know ahead of time that you will miss a quiz/project, send me an e-mail beforehand, and I will excuse you with no penalty. Beforehand does not mean the morning that the quiz/project is due, however.
• Present a final project to the class on the final exam day (???) and turn in a written report of your project within two days. [25%]
  • You final project will be a Python program to solve some problem of interest to you in Spanish.
  • This may be a group effort, but the entire group will receive the same grade.
• Note that there is no credit for class participation, though I will raise a Y+ to an X– if your class participation is worthy of recognition.
  • There is no class participation grade because:
    • I will pod-cast my lectures (record them as mp3 files and make them available on this page, in the 'mp3' column in the Schedule of Assignments below), and
    • I will also make my PowerPoint presentations available on this page, in the 'ppt' column in the Schedule of Assignments below.
  • So all of the information that is imparted in class is available to you outside of class. Therefore I don't care whether you show up for class or not, but if you do not, you do not get to ask me questions or brainstorm with your fellow students. And that is how most people really learn something. And you will miss out on all the fun.

Code of Academic Integrity

“The integrity of Newcomb-Tulane College is based on the absolute honesty of the entire community in all academic endeavors. As part of the Tulane University community, students have certain responsibilities regarding work that forms the basis for the evaluation of their academic achievement. Students are expected to be familiar with these responsibilities at all times. No member of the university community should tolerate any form of academic dishonesty, because the scholarly community of the university depends on the willingness of both instructors and students to uphold the Code of Academic Conduct. When a violation of the Code of Academic Conduct is observed it is the duty of every member of the academic community who has evidence of the violation to take action. Students should take steps to uphold the code by reporting any suspected offense to the instructor or the associate dean of the college. Students should under no circumstances tolerate any form of academic dishonesty.” For further information, point your browser at http://college.tulane.edu/honorcode.htm.

Violations of the Code of Academic Integrity will not be tolerated in this class. I will rigorously investigate and pursue any such transgression.

Students with disabilities who need academic accommodation should:

• Contact and register with the Office of Disability Services (ODS). For more information, visit the ODS website at http://erc.tulane.edu/disability/.
• Bring official notice to me from the ODS indicating that you need academic accommodation. This should be done before the first quiz/project.

Schedule of assigments, Spring 2010
Natural Language Processing with Python, 1e, (2009) by Steven Bird, Ewan Klein, and Edward Loper [NLPP]
There may be additional readings assigned from other sources.

Date	Day	Topic	Assignment	ppt	mp3	P
Jan 11 (M)	1	Presentación del curso	NLPP Preface
13 (W)	2	La computación con el lenguaje	NLPP 1.1
15 (F)	3	La computación con el lenguaje	NLPP 1.1
18 (M)		MLK Birthday
20 (W)	4	Acercamiento a Python, La estadística	NLPP 1.2 - 1.3
22 (F)	5	La estadística, Tomar decisiones y control	NLPP 1.3 - 1.4
25 (M)	6	Tomar decisiones y control, Comprensión automática del LN, Resumen	NLPP 1.4 - 1.6			P1
27 (W)	7	Acceder a corpuses de texto	NLPP 2.1
29 (F)	8	Unicode	NLPP 3.3
Feb 1 (M)	9			--	--	P2
3 (W)	10	Unicode 2	NLPP 3.3
5 (F)	11	Distribución de frecuencia condicionada	NLPP 2.2
8 (M)	12	Más Python: Reciclar código	NLPP 2.3		--
10 (W)	13	Acceso a textos locales y de la web	NLPP 3.1			P3
12 (F)	14	Acceso a textos locales y de la web	NLPP 3.1 - 3.2		--
15 (M)		Lundi Gras
17 (W)	15	Más sobre las cadenas, Las expresiones regulares	NLPP 3.2, 3.4
19 (F)	16	Aplicaciones de las expresiones regulares	NLPP 3.5
22 (M)	17	Más aplicaciones de las expresiones regulares	NLPP 3.6			P4
24 (W)	18	Normalizing & tokenizing text, segmentation, formatting, summary	NLPP 3.7 - 3.10
26 (F)	19	Using a tagger, Tagged corpora	NLPP 5.1 - 5.2		--
Mar 1 (M)	20	La asociación de palabras con propiedades con diccionarios de Python	NLPP 5.3			P5
3 (W)	21	Automatic tagging	NLPP 5.3- 5.4
5 (F)	22	Automatic tagging, N-gram tagging, Trans-based tagging, Word category, Summary	NLPP 5.4 - fin
8 (M)	23	La clasificación supervisada 1	NLPP 6.1			P6
10 (W)	24	La clasificación supervisada 2	NLPP 6.1
12 (F)	25	La clasificación supervisada 3	NLPP 6.1
15 (M)	26	La clasificación supervisada 4	NLPP 6.1
17 (W)	27	La clasificación supervisada 5	NLPP 6.1			P7
19 (F)	28	La clasificación supervisada 6	NLPP 6.1
22 (M)	29	La clasificación supervisada 7	NLPP 6.1			P8
24 (W)	30	La evaluación	NLPP 6.3
26 (F)	31	La extracción de información	NLPP 7.1		--
29 (M)		Spring Break
31 (W)		Spring Break
Apr 2 (F)		Spring Break
5 (M)		Spring Break
7 (W)	32	Chunking, Chunkers, Recursion, Names, Relations, Summary, Grammatical dilemmas, Syntax, CFG, Parsing, Dependencies, Grammar development, Summary, Grammatical features, Processing features, Extending the grammar, Extending the grammar, Summary	NLPP 7.2 - 9.4
9 (F)	33	NL understanding, Propositional logic	NLPP 10.1 - 10.2
12 (M)	34	FOL	NLPP 10.3			P9
14 (W)	35	FOL, Semantics of sentences	NLPP 10.3 - 10.4
16 (F)	36	Semantics of sentences, Discourse semantics, Summary	NLPP 10.4 - 10.6
19 (M)	37	Corpus structure, Life cycle	NLPP 11.1 - 11.2			P10
21 (W)	38	Acquiring data, XML	NLPP 11.3 - 11.4
23 (F)	39	Toolbox data, OLAC, Summary	NLPP 11.5 - 11.7
26 (M)	40	The language challenge	Afterward			P11
May 6 (R)	--	FINAL EXAM DAY 8 - noon	Present projects to class

Go back to Harry Howard's home page