Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Wirén, Mats"'
Although rarely stated, in practice, Grammatical Error Correction (GEC) encompasses various models with distinct objectives, ranging from grammatical error detection to improving fluency. Traditional evaluation methods fail to fully capture the full
Externí odkaz:
http://arxiv.org/abs/2308.08982
Autor:
Eklund, Robert, Wirén, Mats
This paper describes an experiment where open and directed prompts were alternated when collecting speech data for the deployment of a call-routing application. The experiment tested whether open and directed prompts resulted in any differences with
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-40230
Autor:
Boye, Johan, Wirén, Mats
Statistical classification techniques for natural-language call routing systems have matured to the point where it is possible to distinguish between several hundreds of semantic categories with an accuracy that is sufficient for commercial deploymen
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-91439
Autor:
Carter, David, Becket, Ralph, Rayner, Manny, Eklund, ; Robert, MacDermid, Catriona, Wiren, Mats, Kirchmeier-Andersen, ; Sabine, Philp, Christina
In this paper we describe how the translation methodology adopted for the Spoken Language Translator (SLT) addresses the characteristics of the speech translation task in a context where it is essential to achieve easy customization to new languages
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9705015
Autor:
Rayner, Manny, Carter, David, Bretan, Ivan, Eklund, Robert, Wiren, Mats, Hansen, Steffen Leo, Kirchmeier-Andersen, Sabine, Philp, Christina, Sorensen, Finn, Thomsen, Hanne Erdman
We describe two methods relevant to multi-lingual machine translation systems, which can be used to port linguistic data (grammars, lexicons and transfer rules) between systems used for processing related languages. The methods are fully implemented
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9705007
Autor:
Wirén, Mats
Ideally, the time that an incremental algorithm uses to process a change should be a function of the size of the change rather than, say, the size of the entire current input. Based on a formalization of ``the set of things changed'' by an incrementa
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9410028
SweLL Infrastructure for Swedish Learner Language corpus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6f2a798add99f12820ed7af2672cdedc
http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-196023
http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-196023
Autor:
Kurfalı, Murathan, Wirén, Mats
In this paper, we describe our submission to the Shared Task on Scene Segmentation (STSS). The shared task requires participants to segment novels into coherent segments, called scenes. We approach this as a sequential sentence classification task an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::de21e26edaaf3198f37affc5aaf139a1
http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-207019
http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-207019
Publikováno v:
In Speech Communication 2006 48(3):335-353
