Letter N-Gram-based Input Encoding for Continuous Space Language Models

By Henning Sperr, Jan Niehues, A. Waibel. 2013

21 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Bin Gao
2. Adam Lopez
3. Qing Cui
4. Jiang Bian
5. Tie-Yan Liu
6. Clara Vania
7. Siyu Qiu
8. Philipp Koehn

In Representation & Self-Supervised Learning

1. Bin Gao
2. Adam Lopez
3. Qing Cui
4. Jiang Bian
5. Tie-Yan Liu
6. Clara Vania
7. Siyu Qiu
8. Saket Navlakha

Citations in the corpus

• From Characters to Words to in Between: Do We Capture Morphology? (2017, methodology): “…morphology and orthography can be exploited by composing the representations of characters (Ling et al., 2015; Kim et al., 2016), character n-grams (Sperr et al., 2013; Wieting et al., 2016; Bojanowski et al., 2016; Botha and Blunsom, 2014), bytes (Plank et al., 2016; Gillick et al., 2016), or…”
• Co-learning of Word Representations and Morpheme Representations (2014, methodology): “Represent works include Letter n -gram (Sperr et al., 2013) and feature-rich DNN-LMs (Mousa et al., 2013).”