Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/lrec2008/papers/535> ?p ?o. }
Showing items 1 to 19 of
19
with 100 items per page.
- 535 creator beatrice-oshika.
- 535 creator christy-doran.
- 535 creator craig-schlenoff.
- 535 creator dan-parvaz.
- 535 creator greg-sanders.
- 535 creator john-aberdeen.
- 535 creator jon-phillips.
- 535 creator sherri-condon.
- 535 type InProceedings.
- 535 label "Applying Automated Metrics to Speech Translation Dialogs".
- 535 sameAs 535.
- 535 abstract "Over the past five years, the Defense Advanced Research Projects Agency (DARPA) has funded development of speech translation systems for tactical applications. A key component of the research program has been extensive system evaluation, with dual objectives of assessing progress overall and comparing among systems. This paper describes the methods used to obtain BLEU, TER, and METEOR scores for two-way English-Iraqi Arabic systems. We compare the scores with measures based on human judgments and demonstrate the effects of normalization operations on BLEU scores. Issues that are highlighted include the quality of test data and differential results of applying automated metrics to Arabic vs. English.".
- 535 hasAuthorList authorList.
- 535 hasTopic Linguistics.
- 535 isPartOf proceedings.
- 535 keyword "Evaluation methodologies".
- 535 keyword "Machine Translation, SpeechToSpeech Translation".
- 535 keyword "Speech recognition and understanding".
- 535 title "Applying Automated Metrics to Speech Translation Dialogs".