LING 073 / CPSC 013 — Spring 2021
Computational Linguistics

Professor:Jonathan North Washington
Office:Pearson 105
Office phone:x6134
Office hours:M 13:30-15:00
& by appointment
message me on Google Chat/Hangouts for Zoom link
Email/messaging: jwashin1@swarth...more.edu
 
Meeting time:TTh 14:00-15:15
Alternative lab hours: T 21:45-23:00, F 10:40-11:55
Meeting modality:Online synchronous
Classroom:Gather (see Moodle for meeting URL)
Course website: http://www.swarthmore.edu/SocSci/jwashin1/ling073
Course wiki: http://wikis.swarthmore.edu/ling073
IRC channel: irc.freenode.net#swatling
Course Piazza site: LING 073
Course Moodle site: LING073-01-S21

Course Syllabus

Schedule (updated often)

weekdatetopicdue / to read
(by class)
1 11 Feb

Introductions, syllabus

What (and why) is CL (and NLP)?

Environment setup

2 16 Feb

Linguistic communities

Models of development, FOSS

Resource identification

Corpus assembly

Long (2007) - Chilean Mapuches in language row with Microsoft

language selection

18 Feb

LAB

3 23 Feb

Input methods

Lebedev (2004) - Where once was a comma

lab 1 - documentation of resources + Initial corpus assembly

25 Feb

LAB

lab 2 - keyboard layout (due on Friday)

4 2 Mar

Morphological typology

Grammar documentation

Bird (2009) - Natural Language Processing and Linguistic Fieldwork

4 Mar

LAB

lab 3 - Grammar documentation (due on Friday)

5 9 Mar

FSTs and morphology

Analyser evaluation

Kornai (2013) - Digital Language Death

11 Mar

LAB

lab 4 - Basic morphological analyser (due on Friday)

6 16 Mar

FSTs and phonology

Generator evaluation

Pedersen (2008) - Empiricism Is Not A Matter of Faith

18 Mar

LAB

lab 5 - Basic morphological generator (due on Friday)

7 23 Mar

Morphological disambiguation

Manual disambiguation

Disambiguator evaluation

Moshagen & Trosterud (2019) - Rich Morphology, No Corpus – And We Still Made It. The Sámi Experience

25 Mar

Spring break!

8 30 Mar

Other applications

Corpus-based approaches

lab 6 - Basic CG disambiguator

1 Apr

midterm project demos

9 6 Apr

Machine translation

Lexical transfer

Forcada et al. (2011) - Apertium: a free/open-source platform for rule-based machine translation

8 Apr

LAB

lab 7 - Lexical transfer (due on Friday)

10 13 Apr

Lexical selection

Mahelona (2020) - Te reo Māori Speech Recognition: A Story of Community, Trust, and Sovereignty

15 Apr

LAB

lab 8 - Lexical selection (due on Friday)

11 20 Apr

Contrastive grammars

Romero (2016) - Bill Gates speaks Kʼicheeʼ! The corporatization of linguistic revitalization in Guatemala

22 Apr

LAB

lab 9 - Contrastive grammar (due on Friday)

12 27 Apr

Structural transfer

Bird (2020) - Decolonising Speech and Language Technology

29 Apr

LAB

lab 10 - Structural transfer (due on Friday)

13 4 May

RBMT evaluation

6 May

LAB

lab 11 - Polished basic RBMT system (due on Friday)

14 TBA

Final project