Learning Bilingual Lexicons from Monolingual Corpora

By Aria Haghighi, Percy Liang, Taylor Berg-Kirkpatrick, Daniel Klein. 2008

358 citations recorded by the source corpus.

Subfields: Natural Language Processing, Machine Translation

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 Machine Translation

Citations in the corpus

Beyond CCA: Moment Matching for Multi-View Models (2016, neutral): “Examples of applications and extensions of Gaussian CCA are the works by Socher & Fei-Fei (2010), for mapping visual and textual features to the same latent space, and Haghighi et al. (2008), for machine translation applications.”
Exploiting Similarities among Languages for Machine Translation (2013, methodology): “Our proposed approach is complementary to the existing methods that use similarity of word morphology between related languages or exact context matches to infer the possible translations (Koehn and Knight, 2002; Haghighi et al., 2008; Koehn and Knight, 2000).”
Word Translation Without Parallel Data (2017, methodology): “, because the digits were ﬁltered out from the datasets used to train the fastText embeddings. This iterative EM-based algorithm initialized with a seed lexicon has also been explored in other works (Haghighi et al., 2008; Kondrak et al., 2017). There has been a few attempts to align monolingual wor”
SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation (2014, background): “Models of similarity are particularly applicable to various NLP tasks, such as lexical resource building, semantic parsing and machine translation (He et al., 2008; Haghighi et al., 2008; Marton et al., 2009; Beltagy et al., 2014).”
Offline bilingual word vectors, orthogonal transformations and the inverted softmax (2017, methodology): “Previously translation pairs have been extracted from monolingual corpora using CCA by bootstrapping a small seed lexicon (Haghighi et al., 2008).”
Multilingual Distributed Representations without Word Alignment (2013, methodology): “Earlier work, Haghighi et al. [13], proposed a method for inducing cross-lingual lexica using monolingual feature representations and a small initial lexicon to bootstrap with.”
Massively Multilingual Word Embeddings (2016, methodology): “Haghighi et al. (2008) used CCA to learn bilingual lexicons from monolingual corpora.”
Multilingual Models for Compositional Distributed Semantics (2014, methodology): “Earlier work, Haghighi et al. (2008), proposed a method for inducing bilingual lexica using monolingual feature representations and a small initial lexicon to bootstrap with.”
A Survey of Cross-lingual Word Embedding Models (2017, methodology): “Haghighi et al. (2008) were the first to use this method for learning translation lexicons for the words of different languages.”
Towards Principled Unsupervised Learning (2015, background): “…in the context of machine translation (typically in the form of matching bigrams) (Knight et al., 2006; Huang et al., 2006; Snyder et al., 2010; Ravi & Knight, 2008), and in unsupervised lexicon induction (Fung & McKeown, 1997; Koehn & Knight, 2002; Haghighi et al., 2008; Mikolov et al., 2013b).”
Bayesian Canonical correlation analysis (2013, background): “Haghighi et al. (2008) and Tripathi et al. (2011) extended probabilistic CCA beyond the underlying setup of co-occurring data samples.”
Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps (2018, background): “In word embedding research, some studies have tried to transfer linguistic knowledge from one language to another, especially from English to low-resource languages, through distributed representations at the word level (Hermann and Blunsom, 2013; Haghighi et al., 2008; Klementiev et al., 2012).”
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation (2019, background): “Automatic lexical induction is an active field of research (Fung, 1995; Koehn and Knight, 2002; Haghighi et al., 2008; Lample et al., 2018b).”
Connecting modalities: Semi-supervised segmentation and annotation of images using unaligned text corpora (2010, methodology): “2 (left) shows the corresponding graphical model.”
Bilingual Word Representations with Monolingual Quality in Mind (2015, background): “Representatives of this strand include work that extends CCA (Haghighi et al., 2008; Boyd-Graber and Blei, 2009), mapping representations of words in different languages into the same space, as well as work that follows a bootstrapping style to iteratively enlarge the initial lexicon (Peirsman and P”
Learning Bilingual Word Representations by Marginalizing Alignments (2014, background): “These models are also highly re-lated to prior work on bilingual lexicon induction (Haghighi et al., 2008).”
Crowdsourcing Translation: Professional Quality from Non-Professionals (2011, background): “…suited to the low resource setting (Al-Onaizan et al., 2002; Probst et al., 2002; Oard et al., 2003; Niessen and Ney, 2004), or designing models that are capable of learning translations from monolingual corpora (Rapp, 1995; Fung and Yee, 1998; Schafer and Yarowsky, 2002; Haghighi et al., 2008).”
BabelNet: Building a Very Large Multilingual Semantic Network (2010, background): “This barrier has led to proposals that acquire multilingual lexicons from either parallel text (Gale and Church, 1993; Fung, 1995, inter alia ) or monolingual corpora (Sammer and Soder-land, 2007; Haghighi et al., 2008).”