Many applications within natural language processing involve performing text-to-text transformations, i.e., given a text in natural language as input, systems are required to produce a version of this text (e.g., a translation), also in natural language, as output. Automatically evaluating the output of such systems is an important component in developing text-to-text applications. Two approaches have been proposed for this problem: (i) to compare the system outputs against one or more reference outputs using string matching-based evaluation metrics and (ii) to build models based on human feedback to predict the quality of system outputs without reference texts. Despite their popularity, reference-based evaluation metrics are faced with the challenge that multiple good (and bad) quality outputs can be produced by text-to-text approaches for the same input. This variation is very hard to capture, even with multiple reference texts. In addition, reference-based metrics cannot be used in production (e.g., online machine translation systems), when systems are expected to produce outputs for any unseen input. In this book, we focus on the second set of metrics, so-called Quality Estimation (QE) metrics, where the goal is to provide an estimate on how good or reliable the texts produced by an application are without access to gold-standard outputs. QE enables different types of evaluation that can target different types of users and applications. Machine learning techniques are used to build QE models with various types of quality labels and explicit features or learnt representations, which can then predict the quality of unseen system outputs. This book describes the topic of QE for text-to-text applications, covering quality labels, features, algorithms, evaluation, uses, and state-of-the-art approaches. It focuses on machine translation as application, since this represents most of the QE work done to date. It also briefly describes QE for several other applications, including text simplification, text summarization, grammatical error correction, and natural language generation.

This is the first volume that brings together research and practice from academic and industry settings and a combination of human and machine translation evaluation. Its comprehensive collection of papers by leading experts in human and machine translation quality and evaluation who situate current developments and chart future trends fills a clear gap in the literature. This is critical to the successful integration of translation technologies in the industry today, where the lines between human and machine are becoming increasingly blurred by technology: this affects the whole translation landscape, from students and trainers to project managers and professionals, including in-house and freelance translators, as well as, of course, translation scholars and researchers. The editors have broad experience in translation quality evaluation research, including investigations into professional practice with qualitative and quantitative studies, and the contributors are leading experts in their respective fields, providing a unique set of complementary perspectives on human and machine translation quality and evaluation, combining theoretical and applied approaches.

Statistical post-editing (SPE) has been successfully applied to RBMT systems and, to a less successful extent, to some SMT systems. This thesis investigates the impact of SPE on SMT systems. We apply SPE to an SMT system using a new context-modelling approach to preserve some aspects of source information in the second stage translation. This technique yields mixed results, but fails to consistently improve the output over the baseline. Furthermore, we compared the results to those of an RBMT+SPE system and a pure SMT system, using both automatic and human evaluation methods. Results show that while automatic evaluation metrics favour a pure SMT system, manual evaluators prefer the output provided by the combined RBMT+SPE system. We investigate the use machine learning methods to predict which sentences would benefit from post-editing, however, as the oracle score for both SMT and SMT+SPE was not much higher than the two systems alone, we decided to compare two systems that had a higher upper bound. Combining our analysis with machine learning techniques for quality estimation, we are able to improve the overall output by automatically selecting the best sentences from each of the SMT and RBMT+SPE systems.

This book constitutes the refereed proceedings of the 16th China Conference on Machine Translation, CCMT 2020, held in Hohhot, China, in October 2020. The 13 papers presented in this volume were carefully reviewed and selected from 78 submissions and focus on all aspects of machine translation, including preprocessing, neural machine translation models, hybrid model, evaluation method, and post-editing.