A Simple, Fast, and Effective Reparameterization of IBM Model 2

By Chris Dyer, Victor Chahuneau, Noah A. Smith. 2013

1,111 citations recorded by the source corpus.

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

Citations in the corpus

Convolutional Sequence to Sequence Learning (2017, methodology): “Dictionar-ies were extracted from the word aligned training data that we obtained with fast align (Dyer et al., 2013).”
Neural Machine Translation of Rare Words with Subword Units (2015, methodology): “We use a bilingual dictionary based on fast-align (Dyer et al., 2013).”
Edinburgh’s Phrase-based Machine Translation Systems for WMT-14 (2014, methodology): “Table 7: Comparison of fast word alignment method (Dyer et al., 2013) against GIZA++ (WMT 2013 data condition, test on newstest2012).”
Evaluating Gender Bias in Machine Translation (2019, background): “(2) Align between the source and target translations, using fast align (Dyer et al., 2013), trained on the automatic translations from from step (1).”
Non-Autoregressive Neural Machine Translation (2017, methodology): “We use the fast align5 implementation of IBM Model 2 for this purpose, with default parameters (Dyer et al., 2013).”
A Convolutional Encoder Model for Neural Machine Translation (2016, methodology): “In Figure 4 and Figure 5, we plot attention scores for a sample WMT’15 English-German and WMT’14 English-French translation with BiLSTM and deep convolutional encoders.”
Recurrent Continuous Translation Models (2013, background): “We compare the perplexities of the RCTMs with the perplexity of the IBM Model 1 (Brown et al., 1993) and of the Fast-Aligner (FA-IBM 2) model that is a state-of-the-art variant of IBM Model 2 (Dyer et al., 2013).”
On Using Very Large Target Vocabulary for Neural Machine Translation (2014, methodology): “The bilingual dictionary is built using fast align (Dyer et al., 2013).”
Learning protein sequence embeddings using information from structure (2019, methodology): “Kočiský et al. [20] learn bilingual word embeddings jointly with a FastAlign [21] word alignment model using expectation maximization.”
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement (2018, methodology): “They however use supervised learning for inference, using the word alignment tool (Dyer et al., 2013).”
BilBOWA: Fast Bilingual Distributed Representations without Word Alignments (2014, methodology): “However, performing word alignment requires running Giza++ (Och & Ney, 2003) or FastAlign (Dyer et al., 2013) software and training HMM word-alignment models.”
SYSTRAN's Pure Neural Machine Translation Systems (2016, methodology): “We used fast align (Dyer et al., 2013) to automatically align source words to target words.”
Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora (2017, methodology): “To generate the dictionaries for computing the adequacy scores, we use fast align (Dyer et al., 2013) to align the Europarl (Koehn, 2005) corpus and generate probabilistic dictionaries from the alignments.”
Unsupervised Statistical Machine Translation (2018, methodology): “Moreover, we use FastAlign (Dyer et al., 2013) parallel corpus is done through standard Moses tools with default settings.”
Learning to Deceive with Attention-Based Explanations (2019, methodology): “Since the gold target to source word-level alignment is unavailable, we rely on the Fast Align toolkit (Dyer et al., 2013) to align target words to their source counterparts.”
Massively Multilingual Word Embeddings (2016, methodology): “By forcing words from different languages 3 To do this, we align the corpus using fast align (Dyer et al., 2013) in both directions.”
Compositional Morphology for Word Representations and Language Modelling (2014, methodology): “We use cdec (Dyer et al., 2010; 2013) to build symmetric word-alignments and extract rules for hierarchical phrase-based translation (Chiang, 2007).”
Findings of the Third Shared Task on Multimodal Machine Translation (2018, methodology): “Second, we perform automatic word alignment using fast align (Dyer et al., 2013) to identify the English words that are aligned to two or more different words in the target language.”
Paraphrasing Revisited with Neural Machine Translation (2017, methodology): “Following Jean et al. (2015a), we set the common 1 github.com/sebastien-j/LV groundhog vocabulary size as 10000 and 25 uni-gram translations, using a bilingual dictionary based on fast-align (Dyer et al., 2013).”