Machine Translation
Machine Translation is an excellent example of how cutting-edge research and world-class infrastructure come together at Google. We focus our research efforts on developing statistical translation techniques that improve with more data and generalize well to new languages. Our large scale computing infrastructure allows us to rapidly experiment with new models trained on web-scale data to significantly improve translation quality. This research backs the translations served at translate.google.com, allowing our users to translate text, web pages and even speech. Deployed within a wide range of Google services like GMail, Books, Android and web search, Google Translate is a high-impact, research-driven product that bridges language barriers and makes it possible to explore the multilingual web in 90 languages. Exciting research challenges abound as we pursue human quality translation and develop machine translation systems for new languages.
Recent Publications
Results of WMT23 Metrics Shared Task: Metrics might be Guilty but References are not Innocent
Nitika Mathur
Chi-kiu Lo
Eleftherios Avramidis
Ricardo Rei
Brian Thompson
Tom Kocmi
Frédéric Blain
Craig Stewart
Chrysoula Zerva
Sheila Castilho
Alon Lavie
George Foster
Proceedings of the Eighth Conference on Machine Translation, Association for Computational Linguistics, Singapore (2023), pp. 576-626
Preview abstract
This paper presents the results of the WMT23 Metrics Shared Task. Participants submitting automatic MT evaluation metrics were asked to score the outputs of the translation systems competing in the WMT23 News Translation Task. All metrics were evaluated on how well they correlate with human ratings at the system and segment level. Similar to last year, we acquired our own human ratings based on expert-based human evaluation via Multidimensional Quality Metrics (MQM). Following last year's success, we also included a challenge set subtask, where participants had to create contrastive test suites for evaluating metrics' ability to capture and penalise specific types of translation errors. Furthermore, we improved our meta-evaluation procedure by considering fewer tasks and calculating a global score by weighted averaging across the various tasks.
We present an extensive analysis on how well metrics perform on three language pairs: Chinese-English, Hebrew-English on the sentence-level and English-German on the paragraph-level. The results strongly confirm the results reported last year, that neural-based metrics are significantly better than non-neural metrics in their levels of correlation with human judgments. Further, we investigate the impact of bad reference translations on the correlations of metrics with human judgment. We present a novel approach for generating synthetic reference translations based on the collection of MT system outputs and their corresponding MQM ratings, which has the potential to mitigate bad reference issues we observed this year for some language pairs. Finally, we also study the connections between the magnitude of metric differences and their expected significance in human evaluation, which should help the community to better understand and adopt new metrics.
View details
INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback
Wenda Xu
Danqing Wang
Liangming Pan
Zhenqiao Song
William Wang
Lei Li
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Singapore, pp. 5967-5994
Preview abstract
Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics do not provide explicit explanation of their verdict, nor associate the scores with defects in the generated text. To address this limitation, we present INSTRUCTSCORE, a fine-grained explainable evaluation metric for text generation. By harnessing both explicit human instruction and the implicit knowledge of GPT-4, we fine-tune a text evaluation metric based on LLaMA, producing both a score for generated text and a human readable diagnostic report. We evaluate INSTRUCTSCORE on a variety of generation tasks, including translation, captioning, data-to-text, and commonsense generation. Experiments show that our 7B model surpasses all other unsupervised metrics, including those based on 175B GPT-3 and GPT-4. Surprisingly, our INSTRUCTSCORE, even without direct supervision from human-rated data, achieves performance levels on par with state-of-the-art metrics like COMET22, which were fine-tuned on human ratings.
View details
Preview abstract
Neural machine translation (NMT) has progressed rapidly over the past several years, and modern models are able to achieve relatively high quality using only monolingual text data, an approach dubbed Unsupervised Machine Translation, or UNMT. However, these models still struggle in a variety of ways, including aspects of translation that for a human are the easiest---for instance, correctly translating common nouns. This work explores a cheap and abundant resource to combat this problem: bilingual lexicons (\textsc{BiLex}s). We test the efficacy of bilingual lexicons in a real-world set-up, on 200-language translation models trained on web-mined text. We present several findings: (1) we demonstrate the most effective ways to use this resource for MT by extensively experimenting with lexical data augmentation techniques, such as codeswitching and lexical prompting; (2) we pinpoint what settings and languages are benefited most from lexical data augmentation; and (3) we provide an empirical, per-language analysis of the quality of the public resource PanLex, a multilingual lexicon covering thousands of languages.
View details
Preview abstract
We present Mu2SLAM, a multilingual sequence-to-sequence model pre-trained jointly on un-labeled speech, unlabeled text and supervised data spanning Automatic Speech Recognition(ASR), Automatic Speech Translation (AST)and Machine Translation (MT), in over 100 languages. By leveraging a quantized representation of speech as a target, Mu2SLAM trains ona sequence-to-sequence masked denoising objective similar to T5 on both unlabeled speech and text, while utilizing the supervised tasks to improve cross-lingual and cross-modal representation alignment within the model. On CoVoSTAST, Mu2SLAM establishes a new state-of-the-art for models trained on public datasets, improv-ing on xx-en translation over the previous best by 1.9 Bleu points and on en-xx translation by 0.9 Bleu points. On Voxpopuli ASR, our model matches the performance of a mSLAM model finetuned with a RNN-T decoder, despite using a relatively weaker sequence-to-sequence architecture. On text understanding tasks, our model improves by more than 6% over mSLAM on XNLI, getting closer to the performance of mT5 models of comparable capacity on XNLI and TydiQA, paving the way towards a single model for all speech and text understanding tasks.
View details
Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation
Behrooz Ghorbani
Patrick Fernandes
Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics, Singapore, pp. 9198-9209
Preview abstract
Recent advances in machine translation (MT) have shown that Minimum Bayes Risk (MBR) decoding can be a powerful alternative to beam search decoding, especially when combined with neural-based utility functions. However, the performance of MBR decoding depends heavily on how and how many candidates are sampled from the model. In this paper, we explore how different sampling approaches for generating candidate lists for MBR decoding affect performance. We evaluate popular sampling approaches, such as ancestral, nucleus, and top-k sampling. Based on our insights into their limitations, we experiment with the recently proposed epsilon-sampling approach, which prunes away all tokens with a probability smaller than epsilon, ensuring that each token in a sample receives a fair probability mass. Through extensive human evaluations, we demonstrate that MBR decoding based on epsilon-sampling significantly outperforms not only beam search decoding, but also MBR decoding with all other tested sampling methods across four language pairs.
View details
Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration
George Foster
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Singapore, pp. 12914-12929
Preview abstract
Kendall's tau is frequently used to meta-evaluate how well machine translation (MT) evaluation metrics score individual translations. Its focus on pairwise score comparisons is intuitive but raises the question of how ties should be handled, a gray area that has motivated different variants in the literature. We demonstrate that, in settings like modern MT meta-evaluation, existing variants have weaknesses arising from their handling of ties, and in some situations can even be gamed. We propose instead to meta-evaluate metrics with a version of pairwise accuracy that gives metrics credit for correctly predicting ties, in combination with a tie calibration procedure that automatically introduces ties into metric scores, enabling fair comparison between metrics that do and do not predict ties. We argue and provide experimental evidence that these modifications lead to fairer ranking-based assessments of metric performance.
View details
