If you are new to the computational linguistics program, you might be interested in GettingStarted with computational linguistics at IU.
If you're not on the computational linguistics email list, COMPLING-L, send a blank email to: CompLing-l-subscribe 'at' indiana.edu ... This is where announcements are sent out about CLingDing (see below) and everything else.
Nearly every week, we have a discussion group (CLingDing, Spring2017ClingDing) where people present work-in-progress or useful tutorials. Last semester's list can be found here Fall2016ClingDing: Past topics include HowToUseBigRed and UnixTricks.
NLP Reading Group
Share, read, and discuss interesting NLP papers. Fall 2016 semester meeting time is Friday 4-5pm, in BH 306. See our page here: http://cl.indiana.edu/wiki/nlp_reading_group_fall2016
The department maintains a List_of_Corpora from many languages.
Some useful information for the Lab in Memorial Hall 401.
Bloggregation and reading list
Started a list of CL/NLP blogs over here: ClBloggregation. Do you write stuff online? Do you read stuff online? Maybe you could add some blogs to the list.
What is everyone doing?
- Data-driven corpus linguistics: annotation error detection, POS tagging, interfaces to parsing; Intelligent Computer-aided language learning (ICALL)
- sentiment analysis, machine learning for automatic identification of semantic relations, supervised approaches to ranking, domain adaptation
- Word sense disambiguation for MT, low-resource MT, handling lexical and syntactic ambiguity jointly (for MT).
grammatical error detection (especially Korean particles & English comma usage), POS tagging, anaphora resolution, Intelligent computer-aided language learning (ICALL)
- Parsing (for morphologically rich languages), data-driven corpus linguistics, machine learning for CL problems, coreference resolution, fusing hard and soft information
- NLP for morphologically rich languages (esp., Japanese)
- Machine translation for morphologically rich languages, for low-resource languages, and incorporating linguistics into the statistics
- Type-theoretical approaches to linguistics and semantics (esp., categorial/type-logical grammars)
- dependency parsing, error detection, machine learning, perceptron learning
- Mohammad Khan (Shahab)
Morphology and POS tagging of the low resource Iranian languages. Dependency parsing and parse revision of noisy data such as YouTube comments.
- modeling language evolution and acquisition, linguistic and non-linguistic data mining, machine learning, complexity
- Domain adaptation via co-training for dependency parsers and constituency parsers; Word-level language identification for multilingual documents; Extraction of semantic information from learner sentences.
- Automatic sentence simplification; domain adaptation for dependency parsing
Add to the Wiki
Click "edit (text)" to edit existing pages. To add a page, delete the current page name from the URL and enter a new one. For example, change http://cl.indiana.edu/wiki/MainPage to http://cl.indiana.edu/wiki/NewPage to create NewPage. You will notice that making a link to a non-existent page allows you to create it as well.
It would be useful for you to create a user name so we can keep track of who has changed what. Click 'login', then 'add user' and create a user name and password.
See also WikiNews for updates to the wiki itself.
- Dialect distance: phonological distance, syntactic distance, extracting the most important features from the generated distances
- Computational phonology: OT learning, OT implementation, explanation of historical processes like analogy
- computational phonology, phonotactics, sonority, frequency in phonology
- comparative syntax, Minimalist parsing and generation, Intelligent computer-aided language learning (ICALL), Machine translation, Finite-state morphology