Guest Speaker: Manaal Faruqui
Research Scientist at Google Inc.
August 23rd, 4:00pm, Dreese Labs 480
Inducing Morpho-syntactic Lexicons and Morphological Inflections
Morphology of a word can help determine different aspects of its meaning such as tense, mood, voice, aspect, person, gender, number and case. Such morpho-syntactic information about word meaning provides crucial information while training models for downstream NLP tasks. In this talk we are going to discuss two different problems involving morphology. In the first part of the talk I will show how morphological information can be used to construct large-scale morpho-syntactic lexicons for a large number of languages. In the second part of the talk I will show how different possible inflected forms of a word can be generated using encoder-decoder neural network models in a language-independent manner.
Bio: Manaal Faruqui received his PhD from the Language Technologies Institute at Carnegie Mellon University. He has worked on problems in the areas of representation learning, distributional & lexical semantics and multilingual learning. Prior to joining CMU, he was at the Indian Institute of Technology (IIT) Kharagpur where he finished his undergraduate in computer science & engineering. He has won one of the best paper awards at NAACL 2015 for his work on incorporating knowledge from semantic lexicons in word vector representations.