Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections

By Dipanjan Das, Slav Petrov. Annual Meeting of the Association for Computational Linguistics, 2011

320 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/343733a063e491d234a36d3e1090a739318b3566

How researchers see this paper

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

Citations in the corpus

A Survey of Cross-lingual Word Embedding Models (2017, methodology): “Fang and Cohn (2017) use data from the CoNLL-X datasets of European languages (Buchholz & Marsi, 2006), from CoNLL 200316 and from Das and Petrov (2011), the latter of which is also used by Gouws and Søgaard (2015).”
Ten Pairs to Tag – Multilingual POS Tagging via Coarse Mapping between Embeddings (2016, methodology): “Multilingual POS Tagging Prior work on multilingual POS tagging has mainly focused on the tag projection method (Yarowsky et al., 2001; Wisniewski et al., 2014; Duong et al., 2013; Duong et al., 2014; Täckström et al., 2013; Das and Petrov, 2011; Snyder et al., 2008; Naseem et al., 2009; Chen et al.”
Learning a POS tagger for AAVE-like language (2016, methodology): “Word representations To learn word embeddings from our unlabeled corpus, we use the Gensim im-2 plementation of the word2vec algorithm (Mikolov et al., 2013b; Mikolov et al., 2013a).”
Baselines and Test Data for Cross-Lingual Inference (2017, background): “Since training data is generally unavailable for most languages, work on transfer learning is abundant for the basic NLP tasks such as tagging and syntactic parsing (Das and Petrov, 2011; Ammar et al., 2016).”
Multilingual Deep Learning (2013, background): “To overcome this problem of resource scarcity, recently there as been a lot of interest in reusing resources from a resource fortunate language to develop NLP capabilities in a resource deprived language [25] [6] [14] [23] [17] [15] [13] [10].”
Universal Dependency Annotation for Multilingual Parsing (2013, methodology): “The selected sentences were pre-processed using cross-lingual taggers (Das and Petrov, 2011) and parsers (McDonald et al., 2011).”
Frame-Semantic Parsing (2014, methodology): “This is a multiclass generalization of the quadratic cost criterion (Bengio, Delalleau, and Le Roux 2006), also used by Subramanya, Petrov, and Pereira (2010) and Das and Petrov (2011).”
Distributed Word Representation Learning for Cross-Lingual Dependency Parsing (2014, methodology): “…much work developed in the literature has focused on designing robust projection algorithms such as graph-based projection with label prop-agations (Das and Petrov, 2011), improving projection performance by using auxiliary resources such as Wikipedia metadata (Kim and Lee, 2012) or WordNet…”
Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders (2019, background): “Some models exploit the availability of parallel corpora in multiple languages (Das and Petrov, 2011; Cohen et al., 2011).”
Massively Multilingual Transfer for NER (2019, methodology): “An-notation projection has been applied to POS tagging (Yarowsky et al., 2001; Das and Petrov, 2011; Duong et al., 2014; Fang and Cohn, 2016), NER (Zitouni and Florian, 2008; Ehrmann et al., 2011; Agerri et al., 2018), and parsing (Hwa et al., 2005; Ma and Xia, 2014; Rasooli and Collins, 2015a,b).”
Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary (2017, methodology): “Parallel data therefore appears to be the most realistic additional source of information for developing NLP systems in low-resource languages (Yarowsky and Ngai, 2001; Das and Petrov, 2011; Täckström et al., 2013; Fang and Cohn, 2016; Zhang et al., 2016). Yarowsky and Ngai (2001) pioneered the use ”
Cross-lingual Coreference Resolution of Pronouns (2014, background): “Parallel bilingual data is often exploited to solve well-known tasks such as part-of-speech tagging (Das and Petrov, 2011), named entity recognition (Kim et al., 2012), name tagging (Li et al., 2012), and semantic role labeling (Zhuang and Zong, 2010).”
An Autoencoder Approach to Learning Bilingual Word Representations (2014, methodology): “Such aligned representations can potentially allow the use of resources from a resource fortunate language to develop NLP capabilities in a resource deprived language (Yarowsky and Ngai, 2001; Das and Petrov, 2011; Mihalcea et al., 2007; Wan, 2009; Padó and Lapata, 2009).”
Universal Dependencies v1: A Multilingual Treebank Collection (2016, methodology): “It was initially used for unsupervised part-of-speech tagging by Das and Petrov (2011), and has been adopted as a widely used standard for mapping diverse tag sets to a common standard.”
A massively parallel corpus: the Bible in 100 languages (2014, methodology): “2011), the most successful models use sentence-aligned corpora (Yarowsky and Ngai 2001; Das and Petrov 2011).”
JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages (2019, background): “Parallel data features a prominent role in building multilingual word representations (Ruder et al., 2017), annotation projection for parts-of-speech and syntactic dependencies (Das and Petrov, 2011; Tiedemann, 2014) and naturally machine translation.”
The Social Impact of Natural Language Processing (2016, background): “While there are many approaches to develop multi-lingual and cross-lingual NLP tools for linguistic outliers (Yarowsky and Ngai, 2001; Das and Petrov, 2011; Søgaard, 2011; Søgaard et al., 2015; Agić et al., 2015), there simply are more commercial incentives to overexpose English, rather than other l”