Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition (1808.08450v1)

Published 25 Aug 2018 in cs.CL

Abstract: We compare the use of LSTM-based and CNN-based character-level word embeddings in BiLSTM-CRF models to approach chemical and disease named entity recognition (NER) tasks. Empirical results over the BioCreative V CDR corpus show that the use of either type of character-level word embeddings in conjunction with the BiLSTM-CRF models leads to comparable state-of-the-art performance. However, the models using CNN-based character-level word embeddings have a computational performance advantage, increasing training time over word-based models by 25% while the LSTM-based character-level word embeddings more than double the required training time.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Zenan Zhai (10 papers)
  2. Dat Quoc Nguyen (55 papers)
  3. Karin Verspoor (34 papers)
Citations (30)

Summary

We haven't generated a summary for this paper yet.