Cognates can improve statistical translation models

Kondrak, Grzegorz; Marcu, Daniel; Knight, Kevin

doi:10.3115/1073483.1073499

Cited by 74 publications

(70 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cognate word matching has been shown to facilitate the extraction of translation lexicons from comparable corpora (Melamed 1995;Koehn and Knight 2002;Kondrak, Marcu, and Knight 2003;Fišer and Ljubešić 2011;Fišer and Sagot 2015). In this area, a large number of similarity measures have been developed (Tiedemann 1999;Kondrak and Dorr 2004;Kondrak and Sherif 2006), and cognate generation models based on such similarity measures, stochastic transducers or HMMs have been introduced, e.g., Mann and Yarowsky (2001) for closely related languages or Scherrer (2007) for dialects.…”

Section: Automatic Modernisation Of Historical Languagementioning

confidence: 99%

Modernising historical Slovene words

Scherrer¹,

Erjavec²

2015

Nat. Lang. Eng.

View full text Add to dashboard Cite

We propose a language-independent word normalisation method and exemplify it on modernising historical Slovene words. Our method relies on character-level statistical machine translation (CSMT) and uses only shallow knowledge. We present relevant data on historical Slovene, consisting of two (partially) manually annotated corpora and the lexicons derived from these corpora, containing historical word-modern word pairs. The two lexicons are disjoint, with one serving as the training set containing 40,000 entries, and the other as a test set with 20,000 entries. The data spans the years 1750-1900, and the lexicons are split into 50-year slices, with all the experiments carried out separately on the three time periods. We perform two sets of experiments. In the first one -a supervised setting -we build a CSMT system using the lexicon of word pairs as training data. In the second one -an unsupervised setting -we simulate a scenario in which word pairs are not available. We propose a two-step method where we first extract a noisy list of word pairs by matching historical words with cognate modern words, and then train a CSMT system on these pairs. In both sets of experiments we also optionally make use of a lexicon of modern words to filter the modernisation hypotheses. While we show that both methods produce significantly better results than the baselines, their accuracy and which method works best strongly correlates with the age of the texts, meaning that the choice of the best method will depend on the properties of the historical language which is to be modernised. As an extrinsic evaluation we also compare the quality of part-of-speech tagging and lemmatisation directly on historical text and on its modernised words. We show that, depending on the age of the text, annotation on modernised words also produces significantly better results than annotation on the original text.

show abstract

Section: Automatic Modernisation Of Historical Languagementioning

confidence: 99%

Modernising historical Slovene words

Scherrer¹,

Erjavec²

2015

Nat. Lang. Eng.

View full text Add to dashboard Cite

show abstract

“…Use of non-parallel data: Cognates can be extracted from monolingual data and used as a parallel lexicon (Hana et al, 2006;Mann and Yarowsky, 2001;Kondrak et al, 2003). However, our task is whole-text transformation, not just cognate extraction.…”

Section: Related Workmentioning

confidence: 99%

Deciphering Related Languages

Pourdamghani

Knight

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

We present a method for translating texts between close language pairs. The method does not require parallel data, and it does not require the languages to be written in the same script. We show results for six language pairs: Afrikaans/Dutch, Bosnian/Serbian, Danish/Swedish, Macedonian/Bulgarian, Malaysian/Indonesian, and Polish/Belorussian. We report BLEU scores showing our method to outperform others that do not use parallel data.

show abstract

“…where LCS(s 1 ,s 2 ) is the longest common subsequence of strings s 1 and s 2 and |s| is the length of string s. Following Kondrak et al (2003), we retained only pairs of entities with LCSR > 0.58, a value they found to be useful for cognate extraction in many language pairs. We also retained pairs without spelling differences, i.e.…”

Section: Cognate Pair Extraction From Wikipedia Titlesmentioning

confidence: 99%

Neural machine translation for low-resource languages without parallel corpora

Karakanta

Dehdari

Genabith

2017

Machine Translation

View full text Add to dashboard Cite

The problem of a total absence of parallel data is present for a large number of language pairs and can severely detriment the quality of machine translation. We describe a language-independent method to enable machine translation between a low-resource language (LRL) and a third language, e.g. English. We deal with cases of LRLs for which there is no readily available parallel data between the low-resource language and any other language, but there is ample training data between a closelyrelated high-resource language (HRL) and the third language. We take advantage of the similarities between the HRL and the LRL in order to transform the HRL data into data similar to the LRL using transliteration. The transliteration models are trained on transliteration pairs extracted from Wikipedia article titles. Then, we automatically back-translate monolingual LRL data with the models trained on the transliterated HRL data and use the resulting parallel corpus to train our final models. Our method achieves significant improvements in translation quality, close to the results that can be achieved by a general purpose neural machine translation system trained on a significant amount of parallel data. Moreover, the method does not rely on the existence of any parallel data for training, but attempts to bootstrap already existing resources in a related language.

show abstract

Cognates can improve statistical translation models

Cited by 74 publications

References 5 publications

Modernising historical Slovene words

Modernising historical Slovene words

Deciphering Related Languages

Neural machine translation for low-resource languages without parallel corpora

Contact Info

Product

Resources

About