Publications

Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications

Published in 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021

Sentence-level Quality estimation (QE) of machine translation is traditionally formulated as a regression task, and the performance of QE models is typically measured by Pearson correlation with human labels. Recent QE models have achieved previously-unseen levels of correlation with human judgments, but they rely on large multilingual contextualized language models that are computationally expensive and make them infeasible for real-world applications. In this work, we evaluate several model compression techniques for QE and find that, despite their popularity in other NLP tasks, they lead to poor performance in this regression setting. We observe that a full model parameterization is required to achieve SoTA results in a regression task. However, we argue that the level of expressiveness of a model in a continuous range is unnecessary given the downstream applications of QE, and show that reframing QE as a classification problem and evaluating QE models using classification metrics would better reflect their actual performance in real-world applications.

Download here

Wikimatrix: Mining 135m parallel sentences in 1620 language pairs from wikipedia

Published in European Chapter of the Association for Computational Linguistics: Main Volume. 2021, 2021

We present an approach based on multilingual sentence embeddings to automatically extract parallel sentences from the content of Wikipedia articles in 85 languages, including several dialects or low-resource languages. We do not limit the the extraction process to alignments with English, but systematically consider all possible language pairs. In total, we are able to extract 135M parallel sentences for 1620 different language pairs, out of which only 34M are aligned with English. This corpus of parallel sentences is freely available at https://github.com/facebookresearch/LASER/tree/master/tasks/WikiMatrix. To get an indication on the quality of the extracted bitexts, we train neural MT baseline systems on the mined data only for 1886 languages pairs, and evaluate them on the TED corpus, achieving strong BLEU scores for many language pairs. The WikiMatrix bitexts seem to be particularly interesting to train MT systems between distant languages without the need to pivot through English.

Download here

An exploratory study on multilingual quality estimation

Published in 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2020

Predicting the quality of machine translation has traditionally been addressed with language-specific models, under the assumption that the quality label distribution or linguistic features exhibit traits that are not shared across languages. An obvious disadvantage of this approach is the need for labelled data for each given language pair. We challenge this assumption by exploring different approaches to multilingual Quality Estimation (QE), including using scores from translation models. We show that these outperform singlelanguage models, particularly in less balanced quality label distributions and low-resource settings. In the extreme case of zero-shot QE, we show that it is possible to accurately predict quality for any given new language from models trained on other languages. Our findings indicate that state-of-the-art neural QE models based on powerful pre-trained representations generalise well across languages, making them more applicable in real-world settings.

Download here

CLIRMatrix: A Massively Large Collection of Bilingual and Multilingual Datasets for Cross-Lingual Information Retrieval

Published in 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020

We present CLIRMatrix, a massively large collection of bilingual and multilingual datasets for Cross-Lingual Information Retrieval extracted automatically from Wikipedia. CLIRMatrix comprises (1) BI-139, a bilingual dataset of queries in one language matched with relevant documents in another language for 139x138= 19,182 language pairs, and (2) MULTI-8, a multilingual dataset of queries and documents jointly aligned in 8 different languages. In total, we mined 49 million unique queries and 34 billion (query, document, label) triplets, making it the largest and most comprehensive CLIR dataset to date. This collection is intended to support research in end-to-end neural information retrieval and is publicly available at [url]. We provide baseline neural model results on BI-139, and evaluate MULTI-8 in both single-language retrieval and mix-language retrieval settings.

Download here

BERGAMOT-LATTE submissions for the WMT20 quality estimation shared task

Published in 5th Conference on Machine Translation (WMT), 2020

This paper presents our submission to the WMT2020 Shared Task on Quality Estimation (QE). We participate in Task and Task 2 focusing on sentence-level prediction. We explore (a) a black-box approach to QE based on pre-trained representations; and (b) glass-box approaches that leverage various indicators that can be extracted from the neural MT systems. In addition to training a feature-based regression model using glass-box quality indicators, we also test whether they can be used to predict MT quality directly with no supervision. We assess our systems in a multi-lingual setting and show that both types of approaches generalise well across languages. Our black-box QE models tied for the winning submission in four out of seven language pairs inTask 1, thus demonstrating very strong performance. The glass-box approaches also performed competitively, representing a light-weight alternative to the neural-based models.

Download here

MLQE-PE: A multilingual quality estimation and post-editing dataset

Published in arXiv preprint arXiv:2010.04480, 2020

We present MLQE-PE, a new dataset for Machine Translation (MT) Quality Estimation (QE) and Automatic Post-Editing (APE). The dataset contains eleven language pairs, with human labels for up to 10,000 translations per language pair in the following formats: sentence-level direct assessments and post-editing effort, and word-level good/bad labels. It also contains the post-edited sentences, as well as titles of the articles where the sentences were extracted from, and the neural MT models used to translate the text.

Download here

CLIReval: Evaluating Machine Translation as a Cross-Lingual Information Retrieval Task

Published in 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (2020), 2020

We present CLIReval, an easy-to-use toolkit for evaluating machine translation (MT) with the proxy task of cross-lingual information retrieval (CLIR). Contrary to what the project name might suggest, CLIReval does not actually require any annotated CLIR dataset. Instead, it automatically transforms translations and references used in MT evaluations into a synthetic CLIR dataset; it then sets up a standard search engine (Elasticsearch) and computes various information retrieval metrics (eg, mean average precision) by treating the translations as documents to be retrieved. The idea is to gauge the quality of MT by its impact on the document translation approach to CLIR. As a case study, we run CLIReval on the “metrics shared task” of WMT2019; while this extrinsic metric is not intended to replace popular intrinsic metrics such as BLEU, results suggest CLIReval is competitive in many language pairs in terms of correlation to human judgments of quality. CLIReval is publicly available at https://github. com/ssun32/CLIReval.

Download here

Are we Estimating or Guesstimating Translation Quality?

Published in 58th Annual Meeting of the Association for Computational Linguistics (2020), 2020

Recent advances in pre-trained multilingual language models lead to state-of-the-art results on the task of quality estimation (QE) for machine translation. A carefully engineered ensemble of such models won the QE shared task at WMT19. Our in-depth analysis, however, shows that the success of using pre-trained language models for QE is over-estimated due to three issues we observed in current QE datasets:(i) The distributions of quality scores are imbalanced and skewed towards good quality scores;(iii) QE models can perform well on these datasets while looking at only source or translated sentences;(iii) They contain statistical artifacts that correlate well with human-annotated QE labels. Our findings suggest that although QE models might capture fluency of translated sentences and complexity of source sentences, they cannot model adequacy of translations effectively.

Download here

Unsupervised quality estimation for neural machine translation

Published in Transactions of the Association for Computational Linguistics, 2020

Quality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on the quality of the MT output at test time. Existing approaches require large amounts of expert annotated data, computation, and time for training. As an alternative, we devise an unsupervised approach to QE where no training or access to additional resources besides the MT system itself is required. Different from most of the current work that treats the MT system as a black box, we explore useful information that can be extracted from the MT system as a by-product of translation. By utilizing methods for uncertainty quantification, we achieve very good correlation with human judgments of quality, rivaling state-of-the-art supervised QE models. To evaluate our approach we collect the first dataset that enables work on both black-box and glass-box approaches

Download here

End-to-end Gated Self-attentive Memory Network for Dialog Response Selection

Published in The 7th Dialog System Technology Challenge (DSTC7, 2019

This paper presents approaches for the noetic end-to-end response selection challenge in DSTC7. Given a pool of response candidates in a dialog history with external domain knowledge, we propose a Gated Self-attentive Memory Network to encode dialog history and external domain knowledge in an end-to-end trainable manner. Our novelty is that each utterance in the memory is enhanced with self-attention building the connection between dialog history and external domain knowledge in a gated multi-hop manner. We ensemble various gated self-attentive memory network with hierarchical GRU baseline models for final submission. Official evaluation results show that our approach ranks at the second place for both student advising and Ubuntu subtasks integrated with external domain knowledge.

Download here

Cross-lingual learning-to-rank with shared representations

Published in 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), 2018

Cross-lingual information retrieval (CLIR) is a document retrieval task where the documents are written in a language different from that of the user’s query. This is a challenging problem for data-driven approaches due to the general lack of labeled training data. We introduce a large-scale dataset derived from Wikipedia to support CLIR research in 25 languages. Further, we present a simple yet effective neural learning-to-rank model that shares representations across languages and reduces the data requirement. This model can exploit training data in, for example, Japanese-English CLIR to improve the results of Swahili-English CLIR.

Download here

Shuo Sun

Publications