Bidirectional Language Model for Handwriting Recognition
By Volkmar Frinken, Alicia Fornés, Josep Lladós, Jean-Marc Ogier. 2012
7 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Matthew E. Peters
- Chandra Bhagavatula
- Bridger Waleed Ammar
- Björn Schuller
- Amr El-Desoky Mousa
- Russell Power
- Hannaneh Hajishirzi
- Noah A. Smith
In Computer Vision and Pattern Recognition
- Björn Schuller
- Bridger Waleed Ammar
- Chandra Bhagavatula
- Amr El-Desoky Mousa
- Russell Power
- Matthew E. Peters
- Yejin Choi
- Erik Cambria
In Natural Language Processing
- Matthew E. Peters
- Chandra Bhagavatula
- Bridger Waleed Ammar
- Björn Schuller
- Amr El-Desoky Mousa
- Russell Power
- Hannaneh Hajishirzi
- Yejin Choi
Citations in the corpus
- Semi-supervised sequence tagging with bidirectional language models (2017, methodology): “ instance selection. They tied the input token embeddings and softmax weights in the forward and backward directions, unlike our approach which uses two distinct models without any shared parameters. Frinken et al. (2012) also used a bidirectional n-gram LM for handwriting recognition. Interpreting ”
- Contextual Bidirectional Long Short-Term Memory Recurrent Neural Network Language Models: A Generative Approach to Sentiment Analysis (2017, background): “For example, in (Frinken et al., 2012), distinct forward and backward LMs are estimated for handwriting recognition.”