We reassess a recent study (Hassan et al., 2018) that claimed that machine translation (MT) has reached human parity for the translation of news from Chinese into English, using pairwise ranking and considering three variables that were not taken into account in that previous study: the language in which the source side of the test set was originally written, the translation proficiency of the evaluators, and the provision of inter-sentential context. If we consider only original source text (i.e. not translated from another language, or translationese), then we find evidence showing that human parity has not been achieved. We compare the judgments of professional translators against those of non-experts and discover that those of the experts result in higher inter-annotator agreement and better discrimination between human and machine translations. In addition, we analyse the human translations of the test set and identify important translation issues. Finally, based on these findings, we provide a set of recommendations for future human evaluations of MT.

Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequenceto-sequence neural semantic parser that is able to produce Discourse Representation Structures (DRSs) for English sentences with high accuracy, outperforming traditional DRS parsers. To facilitate the learning of the output, we represent DRSs as a sequence of flat clauses and introduce a method to verify that produced DRSs are well-formed and interpretable. We compare models using characters and words as input and see (somewhat surprisingly) that the former performs better than the latter. We show that eliminating variable names from the output using De Bruijn-indices increases parser performance. Adding silver training data boosts performance even further.

The effect of translationese has been studied in the field of machine translation (MT), mostly with respect to training data. We study in depth the effect of translationese on test data, using the test sets from the last three editions of WMT's news shared task, containing 17 translation directions. We show evidence that (i) the use of translationese in test sets results in inflated human evaluation scores for MT systems; (ii) in some cases system rankings do change and (iii) the impact translationese has on a translation direction is inversely correlated to the translation quality attainable by state-of-the-art MT systems for that direction. pology, leipzig. Christian Federmann. 2012. Appraise: an open-source toolkit for manual evaluation of mt output. The Prague Bulletin of Mathematical Linguistics, 98:25-35.

We aim to shed light on the strengths and weaknesses of the newly introduced neural machine translation paradigm. To that end, we conduct a multifaceted evaluation in which we compare outputs produced by state-of-the-art neural machine translation and phrase-based machine translation systems for 9 language directions across a number of dimensions. Specifically, we measure the similarity of the outputs, their fluency and amount of reordering, the effect of sentence length and performance across different error categories. We find out that translations produced by neural machine translation systems are considerably different, more fluent and more accurate in terms of word order compared to those produced by phrase-based systems. Neural machine translation systems are also more accurate at producing inflected forms, but they perform poorly when translating very long sentences.

This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems. We build upon the well-established Multidimensional Quality Metrics (MQM) error taxonomy and implement a novel method that assesses whether the differences in performance for MQM error types between different MT systems are statistically significant. We conduct a case study for English-toCroatian, a language direction that involves translating into a morphologically rich language, for which we compare three MT systems belonging to different paradigms: pure phrase-based, factored phrase-based and neural. First, we design an MQM-compliant error taxonomy tailored to the relevant linguistic phenomena of Slavic languages, which made the annotation process feasible and accurate. Errors in MT outputs were then annotated by two annotators following this taxonomy. Subsequently, we carried out a statistical analysis which showed that the best-performing system (neural) reduces the errors produced by the worst system (pure phrase-based) by more than half (54%). Moreover, we conducted an additional analysis of agreement errors in which we distinguished between short (phrase-level) and long distance (sentence-level) errors. We discovered that phrase-based MT approaches are of limited use for long distance agreement phenomena, for which neural MT was found to be especially effective.

We conduct the first experiment in the literature in which a novel is translated automatically and then post-edited by professional literary translators. Our case study is Warbreaker, a popular fantasy novel originally written in English, which we translate into Catalan. We translated one chapter of the novel (over 3,700 words, 330 sentences) with two data-driven approaches to Machine Translation (MT): phrase-based statistical MT (PBMT) and neural MT (NMT). Both systems are tailored to novels; they are trained on over 100 million words of fiction. In the post-editing experiment, six professional translators with previous experience in literary translation translate subsets of this chapter under three alternating conditions: from scratch (the norm in the novel translation industry), post-editing PBMT, and post-editing NMT. We record all the keystrokes, the time taken to translate each sentence, as well as the number of pauses and their duration. Based on these measurements, and using mixed-effects models, we study post-editing effort across its three commonly studied dimensions: temporal, technical and cognitive. We observe that both MT approaches result in increases in translation productivity: PBMT by 18%, and NMT by 36%. Post-editing also leads to reductions in the number of keystrokes: by 9% with PBMT, and by 23% with NMT. Finally, regarding cognitive effort, post-editing results in fewer (29 and 42% less with PBMT and NMT, respectively) but longer pauses (14 and 25%).

The quality of machine translation has increased remarkably over the past years, to the degree that it was found to be indistinguishable from professional human translation in a number of empirical investigations. We reassess Hassan et al.'s 2018 investigation into Chinese to English news translation, showing that the finding of human-machine parity was owed to weaknesses in the evaluation design-which is currently considered best practice in the field. We show that the professional human translations contained significantly fewer errors, and that perceived quality in human evaluation depends on the choice of raters, the availability of linguistic context, and the creation of reference translations. Our results call for revisiting current best practices to assess strong machine translation systems in general and human-machine parity in particular, for which we offer a set of recommendations based on our empirical findings.

Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequenceto-sequence (BART) models boosts content preservation, and that this is possible even with limited amounts of parallel data. Augmenting these models with rewards that target style and content -the two core aspects of the task-we achieve a new state-of-the-art.