NIST scores
Experts

1

2

3

4

5
Publications (13)

1Interpreting BLEU/NIST Scores: how Much Improvement do we Need to have a Better SystemInterpreting BLEU/NIST Scores: How Much Improvement Do We Need to Have a Better System? Ying Zhang Stephan Vogel Alex...

2The Effect of Text Difficulty on Machine Translation Performance  a Pilot Study with ILRRated Texts in Spanish, Farsi, Arabic, Russian and Koreanrelation: R2=0.69 (with one MT system). Furthermore, the NIST scores for a machine translation of these sentences shows a...

3Augmenting Manual Dictionaries for Statistical Machine Translation Systems2004  Christian Monson,Stephan Vogelthe overall picture stays the same. Table 2 shows the NIST scores under different conditions. Table 2: Translation Results...

4Language Model Adaptation for Statistical Machine Translation Based on Information Retrievaltranslation we also used automatic translations with NIST scores (mteval metric) of 7.18 and 7.90 respectively. ...

5A Repository of Data and Evaluation Resources for Natural Language Generation2012  Albert Gatt,Anja BelzOther metrics: As in TUNAR, we also computed BLEU and NIST scores to compare peer and human outputs. In 2008, as in TUNAAS’07...

6Evaluation of a Machine Translation System for Low Resource Languages: METISII2008  Gemma Boleda,Ineke Schuurman,Maite Melero,Marina Vassiliou,Michael Carl,Olga Yannoutsou,Paul Schmidt,Peter Dirix,Sokratis Sofianopoulos,Markantonatou Stella,Toni Badia,Vincent Vandeghinste(2007) have shown that it has a positive effect on BLEU and NIST scores. These transitions result in a number of translation candidates...

7How does Automatic Machine Translation Evaluation Correlate with Human Scoring as the Number of Reference Translations Increasesis given by: 1 The software used to derive the BLEU and NIST scores in these experiments is version 09c of the NIST MT evaluation...

8Portuguese Text Generation from Large Corporaover all potential candidate sentences. 4Since BLEU and NIST scores are computed for each system as a whole, and Accuracy is...

9Error Analysis of Statistical Machine Translation OutputPosition Independent Word Error Rate and the BLEU and NIST scores are widely use and provide a useful tool for comparing...

10Mood: a Modular ObjectOriented Decoder for Statistical Machine Translationscores we observe. However, note that the difference in NIST scores is in favor of RAMSES. BLEU NIST states / sec states RAMSES...