End-to-end statistical machine translation with zero or small parallel texts

Irvine, Ann; Callison-Burch, Chris

doi:10.1017/s1351324916000127

Cited by 18 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, we experiment with orthogonal features, and with combining multiple source languages to get state of the art results on standard datasets. Irvine and Callison-Burch (2016) build a machine translation system for low-resource languages by inducing bilingual dictionaries from monolingual texts. Koehn and Knight (2001) experiment with varying knowledge levels on the task of translating German nouns in a small parallel German-English corpus.…”

Section: Othersmentioning

confidence: 99%

Cheap Translation for Cross-Lingual Named Entity Recognition

Mayhew¹,

Tsai²,

Roth³

2017

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

122

125

View full text Add to dashboard Cite

Recent work in NLP has attempted to deal with low-resource languages but still assumed a resource level that is not present for most languages, e.g., the availability of Wikipedia in the target language. We propose a simple method for crosslingual named entity recognition (NER) that works well in settings with very minimal resources. Our approach makes use of a lexicon to "translate" annotated data available in one or several high resource language(s) into the target language, and learns a standard monolingual NER model there. Further, when Wikipedia is available in the target language, our method can enhance Wikipedia based methods to yield state-of-the-art NER results; we evaluate on 7 diverse languages, improving the state-of-the-art by an average of 5.5% F1 points. With the minimal resources required, this is an extremely portable crosslingual NER approach, as illustrated using a truly low-resource language, Uyghur.

show abstract

Section: Othersmentioning

confidence: 99%

Cheap Translation for Cross-Lingual Named Entity Recognition

Mayhew¹,

Tsai²,

Roth³

2017

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

122

125

View full text Add to dashboard Cite

show abstract

“…As demonstrated by previous work [19,20], features based on the frequency of the phrases in the monolingual data may help to better estimate the similarity between two phrases. Indeed, we can expect that words or phrases that are translation of one another have a similar relative frequency in their respective language.…”

Section: Phrase Frequency and Phrase Lengthmentioning

confidence: 86%

Phrase Table Induction Using Monolingual Data for Low-Resource Statistical Machine Translation

Marie

Fujita

2018

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

We propose a new method for inducing a phrase-based translation model from a pair of unrelated monolingual corpora. Our method is able to deal with phrases of arbitrary length and to find phrase pairs that are useful for statistical machine translation, without requiring large parallel or comparable corpora. First, our method generates phrase pairs through coupling source and target phrases separately collected from respective monolingual data. Then, for each phrase pair, we compute features using the monolingual data and a small quantity of parallel sentences. Finally, incorrect phrase pairs are pruned, and a phrase table is made using the remaining phrase pairs. In our experiments on French-Japanese and Spanish-Japanese translation tasks under low-resource conditions, we observe that incorporating a phrase table induced by our method to the machine translation system leads to large improvements in translation quality. Furthermore, we show that a phrase table induced by our method can also be useful in a wide range of configurations, including configurations where we have already access to large parallel corpora and configurations where only small monolingual corpora are available.

show abstract

“…As demonstrated by previous work (Irvine and Callison-Burch, 2014;Irvine and Callison-Burch, 2016), features based on the frequency of the phrases in the monolingual data may help us to better score a phrase pair. We add as features the inversed frequency of the source and target phrases in the in-domain monolingual data, along with their relative difference given by the following formula:…”

Section: Other Featuresmentioning

confidence: 88%

Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation

Marie

Fujita

2017

TACL

View full text Add to dashboard Cite

We present a new framework to induce an in-domain phrase table from in-domain monolingual data that can be used to adapt a general-domain statistical machine translation system to the targeted domain. Our method first compiles sets of phrases in source and target languages separately and generates candidate phrase pairs by taking the Cartesian product of the two phrase sets. It then computes inexpensive features for each candidate phrase pair and filters them using a supervised classifier in order to induce an in-domain phrase table. We experimented on the language pair English–French, both translation directions, in two domains and obtained consistently better results than a strong baseline system that uses an in-domain bilingual lexicon. We also conducted an error analysis that showed the induced phrase tables proposed useful translations, especially for words and phrases unseen in the parallel data used to train the general-domain baseline system.

show abstract

End-to-end statistical machine translation with zero or small parallel texts

Cited by 18 publications

References 26 publications

Cheap Translation for Cross-Lingual Named Entity Recognition

Cheap Translation for Cross-Lingual Named Entity Recognition

Phrase Table Induction Using Monolingual Data for Low-Resource Statistical Machine Translation

Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation

Contact Info

Product

Resources

About