HFST—Framework for Compiling and Applying Morphologies

Lindén, Krister; Axelson, Erik; Hardwick, Sam; Pirinen, Tommi A.; Silfverberg, Miikka

doi:10.1007/978-3-642-23138-4_5

Cited by 40 publications

(23 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our results against the predictive text entry system by [13]. 7 The results are shown in Table 4. …”

Section: Results For Turkishmentioning

confidence: 99%

“…Apart from two phonological rules, our approach is entirely unsupervised and data-driven, since we use the unsupervised morphological segmentation system Morfessor [3] for segmenting the training corpus and the tools for constructing POS-taggers from the HFST interface [7]. We show that our method can also be applied to another agglutinative language 1 besides Finnish, namely Turkish.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

THE RED SEQUENCE AT BIRTH IN THE GALAXY CLUSTER Cl J1449+0856 AT z = 2

Strazzullo

Daddi

Gobat

et al. 2016

ApJL

View full text Add to dashboard Cite

Abstract. Systems for predictive text entry on ambiguous keyboards typically rely on dictionaries with word frequencies which are used to suggest the most likely words matching user input. This approach is insufficient for agglutinative languages, where morphological phenomena increase the rate of out-of-vocabulary words. We propose a method for text entry, which circumvents the problem of out-of-vocabulary words, by replacing the dictionary with a Markov chain on morph sequences combined with a third order hidden Markov model (HMM) mapping key sequences to letter sequences and phonological constraints for pruning suggestion lists. We evaluate our method by constructing text entry systems for Finnish and Turkish and comparing our systems with published text entry systems and the text entry systems of three commercially available mobile phones. Measured using the keystrokes per character ratio (KPC) [8], we achieve superior results. For training, we use corpora, which are segmented using unsupervised morphological segmentation.

show abstract

“…We compare our results against the predictive text entry system by [13]. 7 The results are shown in Table 4. …”

Section: Results For Turkishmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

THE RED SEQUENCE AT BIRTH IN THE GALAXY CLUSTER Cl J1449+0856 AT z = 2

Strazzullo

Daddi

Gobat

et al. 2016

ApJL

View full text Add to dashboard Cite

show abstract

“…The Helsinki Finite-State Technology (hfst) library (Lindén et al, 2011) is a frontend for various open source finite-state library back-ends. It allows for data exchange between finite state tools implemented in multiple different formalisms; relevant to us, it covers the Xerox LexC and TwolC formalisms (Lindén et al, 2009).…”

Section: Hfstmentioning

confidence: 99%

Finite-State Back-Transliteration for Marathi

Ravishankar

2017

The Prague Bulletin of Mathematical Linguistics

View full text Add to dashboard Cite

show abstract

“…Morphological analysis is done on the input using the Helsinki Finite-State Toolkit (Lindén et al, 2011). For each surface form, a finite-state t ransducer r eturns a s et of the possible analyses, where an analysis is a combination of lemma, and a sequence of tags which describe the morphological structure of the surface form.…”

Section: Discussionmentioning

confidence: 99%

A North Saami to South Saami Machine Translation Prototype

Antonsen

Trosterud

Tyers

2016

NEJLT

View full text Add to dashboard Cite

The paper describes a rule-based machine translation (MT) system from North to South Saami. The system is designed for a workflow where N orth S aami functions as pivot language in translation from Norwegian or Swedish. We envisage manual translation from Norwegian or Swedish to North Saami, and thereafter MT to South Saami. The system was aimed at a single domain, that of texts for use in school administration. We evaluated the system in terms of the quality of translations for postediting. Two out of three of the Norwegian to South Saami professional translators found the output of the system to be useful. The evaluation shows that it is possible to make a functioning rule-based system with a small transfer lexicon and a small number of rules and achieve results that are useful for a restricted domain, even if there are substantial differences b etween t he languages.

show abstract

HFST—Framework for Compiling and Applying Morphologies

Cited by 40 publications

References 11 publications

THE RED SEQUENCE AT BIRTH IN THE GALAXY CLUSTER Cl J1449+0856 AT z = 2

THE RED SEQUENCE AT BIRTH IN THE GALAXY CLUSTER Cl J1449+0856 AT z = 2

Finite-State Back-Transliteration for Marathi

A North Saami to South Saami Machine Translation Prototype

Contact Info

Product

Resources

About