Abstract
Word embeddings have played a great role in improving the current state of the art in many tasks in NLP and IR. However, we can also leverage their role as representational models of meaning to work on tasks that immediately deal with the semantics of words. In this project, we employ word and character embeddings to identify existing words and reverse-engineer new words based on their definitions. Provided a sentence giving the meaning of the target word, we aim to generate words that match the input meaning.
Members
- Cara Leong (FYP undergraduate student)
- Wenqiang Lei (Graduate student)
- Min-Yen Kan (Professor and advisor)