University of Cambridge > Talks.cam > Language Technology Lab Seminars > Urban Dictionary Embeddings for Slang NLP Applications

Urban Dictionary Embeddings for Slang NLP Applications

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Qianchu Liu.

The choice of the corpus on which word embeddings are trained can have a sizable effect on the learned representations, the types of analyses that can be performed with them, and their utility as features for machine learning models. In this talk I will present my work on the first set of word embeddings trained on the content of Urban Dictionary, a crowd-sourced dictionary for slang words and phrases. I will show that although these embeddings are trained on fewer total tokens, they have high performance across a range of common word embedding evaluations, ranging from semantic similarity to word clustering tasks. Further, for some extrinsic tasks such as sentiment analysis and sarcasm detection where we expect to require some knowledge of colloquial language on social media data, initializing classifiers with the Urban Dictionary Embeddings resulted in improved performance compared to initializing with a range of other well-known, pre-trained embeddings that are order of magnitude larger in size.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity