QEAPE 2018: First Workshop on Translation Quality Estimation and Automatic Post-Editing

First Workshop on Translation Quality Estimation and Automatic 
Post-Editing
Boston, Massachusetts, March 21, 2018
@AMTA 2018 (http://www.conference.)

https://amtaweb.org/amta-2018-first-workshop-translation-quality-
estimation-automatic-post-editing/
(TL;DR: 4 pages, in ACL format, submit by February 2.)

The goal of quality estimation is to evaluate a translation 
system’s quality without access to reference translations (Blatz et 
al., 2004; Specia et al., 2013). This has many potential usages: 
informing an end user about the reliability of translated content; 
deciding if a translation is ready for publishing or if it requires 
human post-editing; highlighting the words that need to be changed. 
Quality estimation systems are particularly appealing for 
crowd-sourced and professional translation services, due to their 
potential to dramatically reduce post-editing times and to save 
labor costs (Specia, 2011). The increasing interest in this problem 
from an industrial angle comes as no surprise (Turchi et al., 2014; 
de Souza et al., 2015; Martins et al., 2016, 2017; Kozlova et al., 
2016). A related task is that of automatic post-editing (Simard et 
al. (2007), Junczys-Dowmunt and Grundkiewicz (2016)), which aims to 
automatically correct the output of machine translation. Recent 
work (Martins, 2017, Kim et al., 2017, Hokamp, 2017) has shown that 
the tasks of quality estimation and automatic post-editing benefit 
from being trained or stacked together.

In this workshop, we will bring together researchers and industry 
practitioners interested in the tasks of quality estimation (word, 
sentence, or document level) and automatic post-editing, both from 
a research perspective and with the goal of applying these systems 
in industrial settings for routing, for improving translation 
quality, or for making human post-editors more efficient. Special 
emphasis will be given to the case of neural machine translation 
and the new open problems that it poses for quality estimation and 
automatic post-editing.

The workshop will consist of one full day of technical 
presentations, including a tentative number of 6 invited talks and 
1 contributed talk, followed by a 30-minutes panel discussion. 
There will be a poster session featuring the papers accepted for 
publication in the workshop proceedings.

SUBMISSIONS

We invite the submission of original research papers, review papers 
as well as position papers, related to the topic of the workshop. 
The papers should not be longer than four pages, excluding 
references. Topics of the workshop include but are not limited to:

- Research, review, and position papers on document-level, 
sentence-level, or word-level Quality Estimation
- Research, review, and position papers on Automatic Post-Editing
- Machine learning techniques for exploiting the interaction among 
these two tasks (e.g. stacking and multi-task learning)
- Corpora curation technologies for developing Quality Estimation 
datasets
- User studies showing the impact of Quality Estimation tools in 
translator productivity
- Automatic metrics for translation fluency and adequacy
- Quality Estimation tailored to Neural Machine Translation
- Quality Estimation tailored to Human Translation

Papers should be formatted according to the ACL template 
(http://acl2018.org/downloads/).
Papers should be submitted via START system to 
https://www.softconf.com/.
Papers will be reviewed for relevance and quality. Accepted papers 
will be posted online, and offered oral or poster presentations.

IMPORTANT DATES

Submission deadline: February 2
Notification date: February 9
Camera ready deadline: February 16
Workshop day: March 21

ORGANIZERS

André Martins (Unbabel and University of Lisbon): 
andre.martins@unbabel.com
Ramon Astudillo (Unbabel and INESC-ID Lisboa): ramon@unbabel.com
João Graça (Unbabel): joao@unbabel.com

--
QEAPE 2018 - https://www.softconf.com/