H2@BUCC18: Parallel Sentence Extraction from Comparable Corpora Using Multilingual Sentence Embeddings

By Houda Bouamor, Hassan Sajjad. 2018

45 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

In Representation & Self-Supervised Learning

Citations in the corpus

Beyond English-Centric Multilingual Machine Translation (2020, background): “Other work expanded to use embeddings from translation systems (Abdul-Rauf and Schwenk, 2009; Bouamor and Sajjad, 2018).”
Filtering and Mining Parallel Data in a Joint Multilingual Space (2018, methodology): “The systems RALI (Gr´egoire and Langlais, 2017) and H2 (Bouamor and Sajjad, 2018) have been already described in section 2.”
Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings (2018, methodology): “…our 1 Multilingual entence embeddings have also been used as part of a larger system, either to obtain an initial alignment that is then further ﬁltered (Bouamor and Sajjad, 2018) or as an intermediate representation of an end-to-end classiﬁer (Gr ´ egoire and Langlais, 2017). a r X i v : 1811 .”
WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia (2019, background): “(Abdul-Rauf and Schwenk, 2009; Bouamor and Sajjad, 2018), typically to obtain an initial alignment that is then further filtered.”
CCMatrix: Mining Billions of High-Quality Parallel Sentences on the Web (2019, background): “Finally, related ideas have been also proposed in Bouamor and Sajjad (2018) or Gr´egoire and Langlais (2017).”
Effective Parallel Corpus Mining using Bilingual Sentence Embeddings (2018, background): “Recent work has approached the problem by training lightweight end-to-end models based on word and sentencelevel embeddings (Grégoire and Langlais, 2017; Bouamor and Sajjad, 2018; Schwenk, 2018).”
Multimodal and Multilingual Embeddings for Large-Scale Speech Mining (2021, background): “A large variety of approaches has been explored like relying on document meta-information (Resnik, 1999), cross-lingual document retrieval (Munteanu and Marcu, 2005) or machine translation and information retrieval (Abdul-Rauf and Schwenk, 2009; Bouamor and Sajjad, 2018), just to name a few.”
Findings of the WMT 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Conditions (2019, background): “Bouamor and Sajjad (2018) learned sentence embeddings for the source and target languages and selected the nearest translation from a list of candidate sentences for a given source sentence using a classiﬁer.”
Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation (2019, methodology): “Bilingual word embeddings were used in (Grover and Mitra, 2017), neural sentence pair classifiers were used in (Bouamor and Sajjad, 2018) and bilingual sentence representations were trained in (Schwenk, 2018).”
SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations (2022, background): “Early works on bitext mining used document metainformation (Resnik, 1999), cross-lingual document retrieval (Munteanu and Marcu, 2005) or information retrieval (Abdul-Rauf and Schwenk, 2009; Bouamor and Sajjad, 2018).”
Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmax (2019, background): “Recently, lightweight end-to-end word and sentence embedding-based approaches have gained popularity and are showing some success for this purpose [Gr´egoire and Langlais, 2017; Bouamor and Sajjad, 2018; Schwenk, 2018; Guo et al. , 2018; Artetxe and Schwenk, 2018].”
Parallel Sentence Mining by Constrained Decoding (2020, background): “Bouamor and Sajjad (2018) consider cosine similarity between averaged multilingual word embeddings.”