UM-pAligner: Neural Network-Based Parallel Sentence Identification Model

By Chongman Leong, Derek F. Wong, Lidia S. Chao. 2018

11 citations recorded by the source corpus.

Subfields: 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 Natural Language Processing

1. Mikel Artetxe
2. Graham Neubig
3. Philipp Koehn
4. Eneko Agirre
5. Ondrej Bojar
6. Gorka Labaka
7. Holger Schwenk
8. Sebastian Ruder

Citations in the corpus

• Filtering and Mining Parallel Data in a Joint Multilingual Space (2018, methodology): “NLP2CT uses a denoising auto-encoder and a maximum-entropy classifier (Leong et al., 2018).”
• Parallel Sentence Mining by Constrained Decoding (2020, methodology): “Leong et al. (2018) use an autoencoder and a maximum entropy classifier.”
• Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining (2020, methodology): “Cross-lingual embeddings of words can be obtained by post-hoc alignment of monolingual word embeddings (Mikolov et al., 2013) and mean-pooled with IDF weights to represent sentences (Litschko et al., 2019).”