Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time. Our aim is to teach a pre-trained MT model to translate previously unseen words accurately, based on very few examples. We propose (i) an experimental setup allowing us to simulate novel vocabulary appearing in human-submitted translations, and (ii) corresponding evaluation metrics to compare our approaches. We extend a data augmentation approach using a pretrained language model to create training examples with similar contexts for novel words. We compare different fine-tuning and data augmentation approaches and show that adaptation on the scale of one to five examples is possible. Combining data augmentation with randomly selected training sentences leads to the highest BLEU score and accuracy improvements. Impressively, with only 1 to 5 examples, our model reports better accuracy scores than a reference system trained with on average 313 parallel examples.
In the sixth edition of the WMT Biomedical Task, we addressed a total of eight language pairs, namely English/German, English/French, English/Spanish, English/Portuguese, English/Chinese, English/Russian, English/Italian, and English/Basque. Further, our tests were composed of three types of textual test sets. New to this year, we released a test set of summaries of animal experiments, in addition to the test sets of scientific abstracts and terminologies. We received a total of 107 submissions from 15 teams from 6 countries.
We describe the University of Edinburgh’s submissions to the WMT20 news translation shared task for the low resource language pair English-Tamil and the mid-resource language pair English-Inuktitut. We use the neural machine translation transformer architecture for all submissions and explore a variety of techniques to improve translation quality to compensate for the lack of parallel training data. For the very low-resource English-Tamil, this involves exploring pretraining, using both language model objectives and translation using an unrelated high-resource language pair (German-English), and iterative backtranslation. For English-Inuktitut, we explore the use of multilingual systems, which, despite not being part of the primary submission, would have achieved the best results on the test set.
This paper describes the joint submission of the University of Edinburgh and Uppsala University to the WMT’20 chat translation task for both language directions (English-German). We use existing state-of-the-art machine translation models trained on news data and fine-tune them on in-domain and pseudo-in-domain web crawled data. Our baseline systems are transformer-big models that are pre-trained on the WMT’19 News Translation task and fine-tuned on pseudo-in-domain web crawled data and in-domain task data. We also experiment with (i) adaptation using speaker and domain tags and (ii) using different types and amounts of preceding context. We observe that contrarily to expectations, exploiting context degrades the results (and on analysis the data is not highly contextual). However using domain tags does improve scores according to the automatic evaluation. Our final primary systems use domain tags and are ensembles of 4 models, with noisy channel reranking of outputs. Our en-de system was ranked second in the shared task while our de-en system outperformed all the other systems.
Machine translation of scientific abstracts and terminologies has the potential to support health professionals and biomedical researchers in some of their activities. In the fifth edition of the WMT Biomedical Task, we addressed a total of eight language pairs. Five language pairs were previously addressed in past editions of the shared task, namely, English/German, English/French, English/Spanish, English/Portuguese, and English/Chinese. Three additional languages pairs were also introduced this year: English/Russian, English/Italian, and English/Basque. The task addressed the evaluation of both scientific abstracts (all language pairs) and terminologies (English/Basque only). We received submissions from a total of 20 teams. For recurring language pairs, we observed an improvement in the translations in terms of automatic scores and qualitative evaluations, compared to previous years.
We describe parBLEU, parCHRF++, and parESIM, which augment baseline metrics with automatically generated paraphrases produced by PRISM (Thompson and Post, 2020a), a multilingual neural machine translation system. We build on recent work studying how to improve BLEU by using diverse automatically paraphrased references (Bawden et al., 2020), extending experiments to the multilingual setting for the WMT2020 metrics shared task and for three base metrics. We compare their capacity to exploit up to 100 additional synthetic references. We find that gains are possible when using additional, automatically paraphrased references, although they are not systematic. However, segment-level correlations, particularly into English, are improved for all three metrics and even with higher numbers of paraphrased references.
In this paper we provide a systematic comparison of existing and new document-level neural machine translation solutions. As part of this comparison, we introduce and evaluate a document-level variant of the recently proposed Star Transformer architecture. In addition to using the traditional metric BLEU, we report the accuracy of the models in handling anaphoric pronoun translation as well as coherence and cohesion using contrastive test sets. Finally, we report the results of human evaluation in terms of Multidimensional Quality Metrics (MQM) and analyse the correlation of the results obtained by the automatic metrics with human judgments.
This paper presents an example architecture for a scalable, secure and resilient Machine Translation (MT) platform, using components available via Amazon Web Services (AWS). It is increasingly common for a single news organisation to publish and monitor news sources in multiple languages. A growth in news sources makes this increasingly challenging and time-consuming but MT can help automate some aspects of this process. Building a translation service provides a single integration point for news room tools that use translation technology allowing MT models to be integrated into a system once, rather than each time the translation technology is needed. By using a range of services provided by AWS, it is possible to architect a platform where multiple pre-existing technologies are combined to build a solution, as opposed to developing software from scratch for deployment on a single virtual machine. This increases the speed at which a platform can be developed and allows the use of well-maintained services. However, a single service also provides challenges. It is key to consider how the platform will scale when handling many users and how to ensure the platform is resilient.
We investigate a long-perceived shortcoming in the typical use of BLEU: its reliance on a single reference. Using modern neural paraphrasing techniques, we study whether automatically generating additional *diverse* references can provide better coverage of the space of valid translations and thereby improve its correlation with human judgments. Our experiments on the into-English language directions of the WMT19 metrics task (at both the system and sentence level) show that using paraphrased references does generally improve BLEU, and when it does, the more diverse the better. However, we also show that better results could be achieved if those paraphrases were to specifically target the parts of the space most relevant to the MT outputs being evaluated. Moreover, the gains remain slight even when human paraphrases are used, suggesting inherent limitations to BLEU’s capacity to correctly exploit multiple references. Surprisingly, we also find that adequacy appears to be less important, as shown by the high results of a strong sampling approach, which even beats human paraphrases when used with sentence-level BLEU.
Current approaches to machine translation (MT) either translate sentences in isolation, disregarding the context they appear in, or model context at the level of the full document, without a notion of any internal structure the document may have. In this work we consider the fact that documents are rarely homogeneous blocks of text, but rather consist of parts covering different topics. Some documents, such as biographies and encyclopedia entries, have highly predictable, regular structures in which sections are characterised by different topics. We draw inspiration from Louis and Webber (2014) who use this information to improve statistical MT and transfer their proposal into the framework of neural MT. We compare two different methods of including information about the topic of the section within which each sentence is found: one using side constraints and the other using a cache-based model. We create and release the data on which we run our experiments - parallel corpora for three language pairs (Chinese-English, French-English, Bulgarian-English) from Wikipedia biographies, which we extract automatically, preserving the boundaries of sections within the articles.
The University of Edinburgh participated in the WMT19 Shared Task on News Translation in six language directions: English↔Gujarati, English↔Chinese, German→English, and English→Czech. For all translation directions, we created or used back-translations of monolingual data in the target language as additional synthetic training data. For English↔Gujarati, we also explored semi-supervised MT with cross-lingual language model pre-training, and translation pivoting through Hindi. For translation to and from Chinese, we investigated character-based tokenisation vs. sub-word segmentation of Chinese text. For German→English, we studied the impact of vast amounts of back-translated training data on translation quality, gaining a few additional insights over Edunov et al. (2018). For English→Czech, we compared different preprocessing and tokenisation regimes.
In the fourth edition of the WMT Biomedical Translation task, we considered a total of six languages, namely Chinese (zh), English (en), French (fr), German (de), Portuguese (pt), and Spanish (es). We performed an evaluation of automatic translations for a total of 10 language directions, namely, zh/en, en/zh, fr/en, en/fr, de/en, en/de, pt/en, en/pt, es/en, and en/es. We provided training data based on MEDLINE abstracts for eight of the 10 language pairs and test sets for all of them. In addition to that, we offered a new sub-task for the translation of terms in biomedical terminologies for the en/es language direction. Higher BLEU scores (close to 0.5) were obtained for the es/en, en/es and en/pt test sets, as well as for the terminology sub-task. After manual validation of the primary runs, some submissions were judged to be better than the reference translations, for instance, for de/en, en/es and es/en.
In this article, we provide several approaches to the automatic identification of parallel sentences that require sentence-external linguistic context to be correctly translated. Our long-term goal is to automatically construct a test set of context-dependent sentences in order to evaluate machine translation models designed to improve the translation of contextual, discursive phenomena. We provide a discussion and critique that show that current approaches do not allow us to achieve our goal, and suggest that for now evaluating individual phenomena is likely the best solution.
For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with standard automatic metrics, poorly adapted to evaluating discourse phenomena. In this article, we present hand-crafted, discourse test sets, designed to test the models’ ability to exploit previous source and target sentences. We investigate the performance of recently proposed multi-encoder NMT models trained on subtitles for English to French. We also explore a novel way of exploiting context from the previous sentence. Despite gains using BLEU, multi-encoder models give limited improvement in the handling of discourse phenomena: 50% accuracy on our coreference test set and 53.5% for coherence/cohesion (compared to a non-contextual baseline of 50%). A simple strategy of decoding the concatenation of the previous and current sentence leads to good performance, and our novel strategy of multi-encoding and decoding of two sentences leads to the best performance (72.5% for coreference and 57% for coherence/cohesion), highlighting the importance of target-side context.
In this paper, we address the problem of generating English tag questions (TQs) (e.g. it is, isn’t it?) in Machine Translation (MT). We propose a post-edition solution, formulating the problem as a multi-class classification task. We present (i) the automatic annotation of English TQs in a parallel corpus of subtitles and (ii) an approach using a series of classifiers to predict TQ forms, which we use to post-edit state-of-the-art MT outputs. Our method provides significant improvements in English TQ translation when translating from Czech, French and German, in turn improving the fluidity, naturalness, grammatical correctness and pragmatic coherence of MT output.
Whilst the focus of Machine Translation (MT) has for a long time been the translation of planned, written texts, more and more research is being dedicated to translating speech-like texts (informal or spontaneous discourse or dialogue). To achieve high quality and natural translation of speechlike texts, the integration of context is needed, whether it is extra-linguistic (speaker identity, the interaction between speaker and interlocutor) or linguistic (coreference and stylistic phenomena linked to the spontaneous and informal nature of the texts). However, the integration of contextual information in MT systems remains limited in most current systems. In this paper, we present and critique three experiments for the integration of context into a MT system, each focusing on a different type of context and exploiting a different method: adaptation to speaker gender, cross-lingual pronoun prediction and the generation of tag questions from French into English.
We present an efficient model selection method using boosting for transition-based constituency parsing. It is designed for exploring a high-dimensional search space, defined by a large set of feature templates, as for example is typically the case when parsing morphologically rich languages. Our method removes the need to manually define heuristic constraints, which are often imposed in current state-of-the-art selection methods. Our experiments for French show that the method is more efficient and is also capable of producing compact, state-of-the-art models.
In this paper we investigate the impact of the integration of context into dialogue translation. We present a new contextual parallel corpus of television subtitles and show how taking into account speaker gender can significantly improve machine translation quality in terms of B LEU and M ETEOR scores. We perform a manual analysis, which suggests that these improvements are not necessary related to the morphological consequences of speaker gender, but to more general linguistic divergences.
This article presents the methods, results, and precision of the syntactic annotation process of the Rhapsodie Treebank of spoken French. The Rhapsodie Treebank is an 33,000 word corpus annotated for prosody and syntax, licensed in its entirety under Creative Commons. The syntactic annotation contains two levels: a macro-syntactic level, containing a segmentation into illocutionary units (including discourse markers, parentheses â¦) and a micro-syntactic level including dependency relations and various paradigmatic structures, called pile constructions, the latter being particularly frequent and diverse in spoken language. The micro-syntactic annotation process, presented in this paper, includes a semi-automatic preparation of the transcription, the application of a syntactic dependency parser, transcoding of the parsing results to the Rhapsodie annotation scheme, manual correction by multiple annotators followed by a validation process, and finally the application of coherence rules that check common errors. The good inter-annotator agreement scores are presented and analyzed in greater detail. The article also includes the list of functions used in the dependency annotation and for the distinction of various pile constructions and presents the ideas underlying these choices.