Inducing Crosslingual Distributed Representations of Words

By Alexandre Klementiev, Ivan Titov, Binod Bhattarai. 2012

390 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

XNLI: Evaluating Cross-lingual Sentence Representations (2018, methodology): “While XLU shows promising results for tasks such as cross-lingual document classification (Klementiev et al., 2012; Schwenk and Li, 2018), there are very few, if any, XLU benchmarks for more difficult language understanding tasks like natural language inference.”
MLQA: Evaluating Cross-lingual Extractive Question Answering (2019, methodology): “Given recent progress in cross-lingual tasks such as document classiﬁcation (Lewis et al., 2004; Klementiev et al., 2012; Schwenk and Li, 2018), semantic role labelling (Akbik et al., 2015) and NLI (Conneau et al., 2018), we argue that while multilingual QA training data might be useful but not…”
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization (2020, background): “Early work in this direction focused on single tasks, such as grammar induction (Snyder et al., 2009), part-of-speech (POS) tagging (T¨ackstr¨om et al., 2013), parsing (McDonald et al., 2011), and text classiﬁ-cation (Klementiev et al., 2012).”
Word Translation Without Parallel Data (2017, methodology): “ngs can be used to extract bilingual lexicons by computing the nearest neighbor of a source word, but also allow other applications such as sentence retrieval or cross-lingual document classiﬁcation (Klementiev et al., 2012). In general, they are used as building blocks for various cross-lingual lan”
Recurrent Convolutional Neural Networks for Text Classification (2015, positive): “Klementiev, Titov, and Bhattarai (2012) used this in crosslingual document classiﬁcation.”
Learning bilingual word embeddings with (almost) no bilingual data (2017, background): “, 2016), parsing (Xiao and Guo, 2014) and document classification (Klementiev et al., 2012).”
Offline bilingual word vectors, orthogonal transformations and the inverted softmax (2017, background): “, 2013), and enable language-agnostic text classifiers (Klementiev et al., 2012).”
Improving Vector Space Word Representations Using Multilingual Correlation (2014, methodology): “Klementiev et al. (2012) use a multitask learning framework to encourage the word representations learned by neural language models to agree cross-lingually.”
BilBOWA: Fast Bilingual Distributed Representations without Word Alignments (2014, methodology): “As a ﬁrst step, current methods [12, 21] rely on performing a word-alignment step over sentence-aligned data to obtain the word translation-pair co-occurrence frequencies prior to training the models.”
A Corpus for Multilingual Document Classification in Eight Languages (2018, methodology): “A subset of the English and German sections of RCV2 was defined by (Klementiev et al., 2012) to evaluate crosslingual document classification.”
Multilingual Distributed Representations without Word Alignment (2013, methodology): “We follow the experimental setup described in [16], with the exception that we learn our embeddings using solely the Europarl data and only use the Reuters RCV1 Cross-lingual compositional representations ( BI CVM and BI CVM+), cross-lingual representations using learned embeddings and an…”
Massively Multilingual Word Embeddings (2016, background): “In addition to improving the performance on standard monolingual NLP tasks, shared representation of words across languages offers intriguing possibilities (Klementiev et al., 2012).”
Multilingual Models for Compositional Distributed Semantics (2014, methodology): “First, we show that for cross-lingual document clas-siﬁcation on the Reuters RCV1/RCV2 corpora (Lewis et al., 2004), we outperform the prior state of the art (Klementiev et al., 2012).”
A Multiplicative Model for Learning Distributed Text-Based Attribute Representations (2014, methodology): “We follow the experimental procedure of [19], for which several existing baselines are available to compare our results.”
A Survey of Cross-lingual Word Embedding Models (2017, methodology): “The task is commonly used following the setup of Klementiev et al. (2012): it uses the RCV2 Reuters multilingual corpus14.”
Normalized Word Embedding and Orthogonal Transform for Bilingual Word Translation (2015, background): “A similar approach is proposed in (Klementiev et al., 2012), which casts multilingual learning as a multi-task learning and encodes the multilingual information in the interaction matrix.”
Polyglot: Distributed Word Representations for Multilingual NLP (2013, background): “(Klementiev et al., 2012) induce distributed representations for a pair of languages jointly, where a learner can be trained on annotations present in one language and applied to test data in another.”