Feature-enriched word embeddings for named entity recognition in open-domain conversations

Yukun Ma; Jung-Jae Kim; Benjamin Bigot; Muhammad Tahir Khan

ICASSP 2016accepted0 citations

Feature-enriched word embeddings for named entity recognition in open-domain conversations

Yukun Ma, Jung-Jae Kim, Benjamin Bigot, Muhammad Tahir Khan

Abstract

Named entity recognition (NER) from open-domain conversation is challenging due to the informality of spoken language. Instead of increasing the size of labeled data, which is expensive and time-consuming, word embeddings learned from unlabeled data have been used by NER models to handle data sparsity. We propose a novel method for training the word embeddings specifically for the NER task. We show that our task-specific word embeddings outperform task-independent word embeddings when used as features of NER method.

BibTeX

@inproceedings{icassp2016_featureenrichedw,
  title = {Feature-enriched word embeddings for named entity recognition in open-domain conversations},
  author = {Yukun Ma and Jung-Jae Kim and Benjamin Bigot and Muhammad Tahir Khan},
  booktitle = {ICASSP 2016},
  year = {2016}
}