CMU Multilingual NLP: Language Contact and Similarity Across Languages

Explore language contact and computational models of language change in this lecture from CMU's Multilingual Natural Language Processing course. Delve into topics such as lexical borrowing, cross-lingual similarities, and lexicon mapping across languages. Learn about transliteration models and evaluation, cognates and loanwords, and bilingual lexicon induction. Examine real-world examples of Arabic-Swahili borrowing and discover various linguistic resources for studying language contact phenomena. Gain insights into the complex interactions between languages and their impact on natural language processing tasks.

CS11-737: Multilingual Natural Language Processing
Language contact drives language change
Lexical borrowing is pervasive in languages
Cross-lingual lexical similarities
Mapping lexicons across languages
Cross-lingual lexicon induction
Lexicon structure
How to bridge across languages? Borrowing
Transliteration models
Transliteration evaluation
Transliteration resources
Cognates and loanwords
Arabic Swahili borrowing examples
Linguistic research on lexical borrowing
Cognate and loanword models
Cognate databases
Lexical borrowing databases
Bilingual lexicon induction
Class discussion