Note: The deadline for submission has passed.
While a significant body of work has been done by the machine translation (MT) research community towards the development and meta-evaluation of automatic metrics to assess overall MT quality, less attention has been dedicated to more operational evaluation metrics aimed at testing whether translations are adequate within a specific context: purpose, end-user, task, etc., and why the MT system fails in some cases. Both of these can benefit from some form of manual analysis. Most work in this area is limited to productivity tests (e.g. contrasting time for human translation and MT post-editing). A few initiatives consider more detailed metrics for the problem, which can also be used to understand and diagnose errors in MT systems. These include the Multidimensional Quality Metrics (MQM) recently proposed by the EU F7 project QTLaunchPad, the TAUS Dynamic Quality Framework, and past projects such as FEMTI, EAGLES and ISLE. Some of these metrics are also applicable to human translation evaluation. A number of task-based metrics have also been proposed for applications such as topic ID / triage and reading comprehension.
The purpose of this workshop is to bring together representatives from academia, industry and government institutions to discuss and assess metrics for manual quality evaluation and compare them through correlation analysis with well-established metrics for automatic evaluation such as BLEU, METEOR and others, as well as reference-less metrics for quality prediction.
The workshop will benefit from datasets already collected and manually annotated for translation errors by the QTLaunchPad project as part of a shared task on error annotation and automatic quality translation.
We will accept two types of submissions:
For formatting guidelines for full papers, please use the LREC submission format found at http://lrec2014.lrec-conf.org/en/submission/authors-kit/.
Both abstracts and full papers will address any of the topics included in this CFP (see below), but full papers have the advantage of presenting the authors’ work and ideas at a greater level of detail. All submissions (abstract-only submissions or abstract+paper submissions) must be received by the submission deadline below and will be reviewed by experts in the field. Short slots for oral presentation will be given to all accepted submissions, regardless of their format (abstract only or abstract+paper). The workshop proceedings will consist of abstracts from all accepted submissions and select full papers from abstract+paper submissions.
The workshop welcomes submissions on the topics of
The format of the workshop will be a half-day of short presentations on the above topics, followed by a half-day of hands-on collaborative work with MT metrics that show promise for the prediction of task suitability of MT output. The afternoon hands-on work will follow from the morning's presentations. Thus, all submissions, both abstracts and abstracts + papers should address at least the following points:
Submissions will be addressed via the START Conference Manager: https://www.softconf.com/lrec2014/MTE/.
When making a submission from the START page, authors will be asked to provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research. Moreover, ELRA encourages all LREC authors to share the described LRs (data, tools, services, etc.), to enable their reuse, replicability of experiments, including evaluation ones, etc.