Evaluating machine translation output for an unknown source language: report of an ISLE-based investigation
Keith J. Miller, Donna M. Gates, Nancy Underwood, Josemina Magdalen
Abstract
It is often assumed that knowledge of both the source and target languages is necessary in order to evaluate the output of a machine translation (MT) system. This paper reports on an experimental evaluation of Chinese-English MT and Spanish-English MT from output specifically designed for evaluators who do not read or speak Chinese or Spanish. An outline of the characteristics measured and evaluation follows.- Anthology ID:
- 2001.mtsummit-eval.3
- Volume:
- Workshop on MT Evaluation
- Month:
- September 18-22
- Year:
- 2001
- Address:
- Santiago de Compostela, Spain
- Editors:
- Eduard Hovy, Margaret King, Sandra Manzi, Florence Reeder
- Venue:
- MTSummit
- SIG:
- Publisher:
- Note:
- Pages:
- Language:
- URL:
- https://aclanthology.org/2001.mtsummit-eval.3
- DOI:
- Cite (ACL):
- Keith J. Miller, Donna M. Gates, Nancy Underwood, and Josemina Magdalen. 2001. Evaluating machine translation output for an unknown source language: report of an ISLE-based investigation. In Workshop on MT Evaluation, Santiago de Compostela, Spain.
- Cite (Informal):
- Evaluating machine translation output for an unknown source language: report of an ISLE-based investigation (Miller et al., MTSummit 2001)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2001.mtsummit-eval.3.pdf