Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings

no code implementations • 18 Aug 2019 • Ahmed El-Kishky, Frank Xu, Aston Zhang, Jiawei Han

However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures.

Language Modelling Segmentation +1

Entropy-Based Subword Mining with an Application to Word Embeddings

no code implementations • WS 2018 • Ahmed El-Kishky, Frank Xu, Aston Zhang, Stephen Macke, Jiawei Han

Recent literature has shown a wide variety of benefits to mapping traditional one-hot representations of words and phrases to lower-dimensional real-valued vectors known as word embeddings.

Language Modelling Machine Translation +3

Multi-channel BiLSTM-CRF Model for Emerging Named Entity Recognition in Social Media

no code implementations • WS 2017 • Bill Y. Lin, Frank Xu, Zhiyi Luo, Kenny Zhu

In this paper, we present our multi-channel neural architecture for recognizing emerging named entity in social media messages, which we applied in the Novel and Emerging Named Entity Recognition shared task at the EMNLP 2017 Workshop on Noisy User-generated Text (W-NUT).

named-entity-recognition Named Entity Recognition +1