We study the problem of online learning with human feedback in the human-in-the-loop machine translation, in which the human translators revise the machine-generated translations and then the corrected translations are used to improve the neural machine translation (NMT) system. However, previous methods require online model updating or additional translation memory networks to achieve high-quality performance, making them inflexible and inefficient in practice. In this paper, we propose a novel non-parametric online learning method without changing the model structure. This approach introduces two k-nearest-neighbor (knn) modules: one module memorizes the human feedback, which is the correct sentences provided by human translators, while the other balances the usage of the history human feedback and original NMT models adaptively. Experiments conducted on EMEA and JRC-Acquis benchmarks demonstrate that our proposed method obtains substantial improvements on translation accuracy and achieves better adaptation performance with less repeating human correction operations.
We empirically investigate learning from partial feedback in neural machine translation (NMT), when partial feedback is collected by asking users to highlight a correct chunk of a translation. We propose a simple and effective way of utilizing such feedback in NMT training. We demonstrate how the common machine translation problem of domain mismatch between training and deployment can be reduced solely based on chunk-level user feedback. We conduct a series of simulation experiments to test the effectiveness of the proposed method. Our results show that chunk-level feedback outperforms sentenc…
Adapting machine translation systems in the real world is a difficult problem. In contrast to offline training, users cannot provide the type of fine-grained feedback (such as correct translations) typically used for improving the system. Moreover, different users have different translation needs, and even a single user's needs may change over time. In this work we take a different approach, treating the problem of adaptation as one of selection. Instead of adapting a single system, we train many translation systems using different architectures, datasets, and optimization methods. Using bandi…
We propose an interactive-predictive neural machine translation framework for easier model personalization using reinforcement and imitation learning. During the interactive translation process, the user is asked for feedback on uncertain locations identified by the system. Responses are weak feedback in the form of "keep" and "delete" edits, and expert demonstrations in the form of "substitute" edits. Conditioning on the collected feedback, the system creates alternative translations via constrained beam search. In simulation experiments on two language pairs our systems get close to the perf…
We present an approach to structured prediction from bandit feedback, called Bandit Structured Prediction, where only the value of a task loss function at a single predicted point, instead of a correct structure, is observed in learning. We present an application to discriminative reranking in Statistical Machine Translation (SMT) where the learning algorithm only has access to a 1-BLEU loss evaluation of a predicted translation instead of obtaining a gold standard reference translation. In our experiment bandit feedback is obtained by evaluating BLEU on reference translations without revealin…
Aligning Neural Machine Translation Models: Human Feedback in Training and Inference
Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院）；Instituto de Telecomunicações（电信研究所）；Carnegie Mellon University（卡内基梅隆大学）；Unbabel（Unbabel公司）
Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance on heterogeneous datasets and on sub-tasks like rare phrase translation. On the other hand, non-parametric approaches are immune to forgetting, perfectly complementing the generalization ability of NMT. However, attempts to combine non-parametric or retrieval based approaches with NMT have only been successful on narrow domains, possibly due to over-reliance…
We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform. Previous work has been confined to simulation experiments, whereas in this paper we work with real logged feedback for offline bandit learning of NMT parameters. We conduct a thorough analysis of the available explicit user judgments---five-star ratings of translation quality---and show that they are not reliable enough to yield significant improvements in bandit learning. In contr…
k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT). It aims to alleviate the performance degradation of advanced MT systems in translating out-of-domain sentences by coordinating with an additional token-level feature-based retrieval module constructed from in-domain data. Previous studies have already demonstrated that non-parametric NMT is even superior to models fine-tuned on out-of-domain data. In spite of this success, kNN retrieval is at the expense of high latency, in particula…
University of Maryland（马里兰大学）；Microsoft Research, New York（微软研究院纽约分院）
Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training focuses on expensive human-generated reference translations. We describe a reinforcement learning algorithm that improves neural machine translation systems from simulated human feedback. Our algorithm combines the advantage actor-critic algorithm (Mnih et al., 2016) with the attention-based neural encoder-decoder architecture (Luong et al., 2015). This algor…
We introduce ChrEnTranslate, an online machine translation demonstration system for translation between English and an endangered language Cherokee. It supports both statistical and neural translation models as well as provides quality estimation to inform users of reliability, two user feedback interfaces for experts and common users respectively, example inputs to collect human translations for monolingual data, word alignment visualization, and relevant terms from the Cherokee-English dictionary. The quantitative evaluation demonstrates that our backbone translation models achieve state-of-…
The University of Hong Kong（香港大学）；New York University（纽约大学）
In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first stage--retrieval stage--, an off-the-shelf, black-box search engine is used to retrieve a small subset of sentence pairs from a training set given a source sentence. These pairs are further filtered based on a fuzzy matching score based on edit distance. In the second stage--translation stage--, a novel translation model, called translation memory enhanced NMT…
Charles University（查理大学）；University of Edinburgh（爱丁堡大学）；University of Sheffield（谢菲尔德大学）；University of Wolverhampton（伍尔弗汉普顿大学）；University of Tartu（塔尔图大学）
Translating text into a language unknown to the text's author, dubbed outbound translation, is a modern need for which the user experience has significant room for improvement, beyond the basic machine translation facility. We demonstrate this by showing three ways in which user confidence in the outbound translation, as well as its overall final quality, can be affected: backward translation, quality estimation (with alignment) and source paraphrasing. In this paper, we describe an experiment on outbound translation from English to Czech and Estonian. We examine the effects of each proposed f…
Heidelberg University（海德堡大学）；Amazon Development Center（亚马逊开发中心）
The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically log the most probable translation. The lack of sufficient exploration of the SMT output space seemingly contradicts the theoretical requirements for counterfactual learning. We show that counterfactual learning from deterministic bandit logs is possible nevertheless by smoothing ou…
Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, it heavily relies on high-quality in-domain parallel corpora, limiting its capability on unsupervised domain adaptation, where in-domain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to con…
INESC-ID Lisboa（里斯本系统与计算机工程研究所）；Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院）；Unbabel AI（Unbabel人工智能）；Centro de Linguística da Universidade de Lisboa（里斯本大学语言学中心）；Faculdade de Letras da Universidade de Lisboa（里斯本大学文学院）
In Machine Translation, assessing the quality of a large amount of automatic translations can be challenging. Automatic metrics are not reliable when it comes to high performing systems. In addition, resorting to human evaluators can be expensive, especially when evaluating multiple systems. To overcome the latter challenge, we propose a novel application of online learning that, given an ensemble of Machine Translation systems, dynamically converges to the best systems, by taking advantage of the human feedback available. Our experiments on WMT'19 datasets show that our online approach quickl…
Instituto de Telecomunicações（电信研究所）；Unbabel（Unbabel公司）；Institute of Systems and Robotics（系统与机器人研究所）；DeepMind（深度思维）；Instituto Superior Técnico（里斯本高等理工学院）
Semi-parametric models, which augment generation with retrieval, have led to impressive results in language modeling and machine translation, due to their ability to retrieve fine-grained information from a datastore of examples. One of the most prominent approaches, $k$NN-MT, exhibits strong domain adaptation capabilities by retrieving tokens from domain-specific datastores \citep{khandelwal2020nearest}. However, $k$NN-MT requires an expensive retrieval operation for every single generated token, leading to a very low decoding speed (around 8 times slower than a parametric model). In this pap…
We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial translations. Secondly, human effort is further reduced by using the entropy of word predictions as uncertainty criterion to trigger feedback requests. Lastly, online updates of the model parameters after every interaction allow the model to adapt quickly. We show in simulation expe…
We describe the University of Maryland machine translation systems submitted to the WMT17 German-English Bandit Learning Task. The task is to adapt a translation system to a new domain, using only bandit feedback: the system receives a German sentence to translate, produces an English sentence, and only gets a scalar score as feedback. Targeting these two challenges (adaptation and bandit learning), we built a standard neural machine translation system and extended it in two ways: (1) robust reinforcement learning techniques to learn effectively from the bandit feedback, and (2) domain adaptat…
ADAPT Centre, Dublin City University（都柏林城市大学 ADAPT 中心）；Trinity Centre for Literary and Cultural Translation and ADAPT Centre, Trinity College Dublin（都柏林圣三一学院文学与文化翻译中心及 ADAPT 中心）
Sentiment classification has been crucial for many natural language processing (NLP) applications, such as the analysis of movie reviews, tweets, or customer feedback. A sufficiently large amount of data is required to build a robust sentiment classification system. However, such resources are not always available for all domains or for all languages. In this work, we propose employing a machine translation (MT) system to translate customer feedback into another language to investigate in which cases translated sentences can have a positive or negative impact on an automatic sentiment classifi…
INESC-ID（里斯本系统与计算机工程研究所）；Instituto Superior Técnico（高等技术学院）；Unbabel AI（Unbabel人工智能实验室）
Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active learning approaches for Machine Translation assume the existence of a pool of sentences in a source language, and rely on human annotators to provide translations or post-edits, which can still be costly. In this article, we assume a real world human-in-the-loop scenario in which: (i) the source sentences may not be readily available, but instead arrive in a stream; (ii) the automatic translations receive feedback i…
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术全国重点实验室）；ByteDance（字节跳动）；ByteDance AI Lab（字节跳动人工智能实验室）；University of California, Santa Barbara（加州大学圣塔芭芭拉分校）
How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating the deployed models online remains a challenge. Existing non-parametric approaches that retrieve similar examples from a database to guide the translation process are promising but are prone to overfit the retrieved examples. In this work, we propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER), an effective approach to adapt neural machine translation models online. Experiments on domain adapta…
University of Science and Technology of China（中国科学技术大学）；Peking University（北京大学）；Microsoft Research（微软研究院）
While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck, we develop a dual-learning mechanism, which can enable an NMT system to automatically learn from unlabeled data through a dual-learning game. This mechanism is inspired by the following observation: any machine translation task has a dual task, e.g., English-to-French translation (primal) versus French-to-English translation (dual); the primal and dual task…
Saarland University（萨尔大学）；DFKI（德国人工智能研究中心）；University of Wolverhampton（伍尔弗汉普顿大学）；Jadavpur University（贾达普大学）
This paper describes strategies to improve an existing web-based computer-aided translation (CAT) tool entitled CATaLog Online. CATaLog Online provides a post-editing environment with simple yet helpful project management tools. It offers translation suggestions from translation memories (TM), machine translation (MT), and automatic post-editing (APE) and records detailed logs of post-editing activities. To test the new approaches proposed in this paper, we carried out a user study on an English--German translation task using CATaLog Online. User feedback revealed that the users preferred usin…
Tencent AI Lab（腾讯人工智能实验室）；Zhejiang University（浙江大学）；Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）
Despite low latency, non-autoregressive machine translation (NAT) suffers severe performance deterioration due to the naive independence assumption. This assumption is further strengthened by cross-entropy loss, which encourages a strict match between the hypothesis and the reference token by token. To alleviate this issue, we propose multi-granularity optimization for NAT, which collects model behaviors on translation segments of various granularities and integrates feedback for backpropagation. Experiments on four WMT benchmarks show that the proposed method significantly outperforms the bas…
Ateneo de Manila University（马尼拉雅典耀大学）；Heidelberg University（海德堡大学）
We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator, and the effect of the quality of reward estimates on the overall RL task. Our analysis of cardinal (5-point ratings) and ordinal (pairwise preferences) feedback shows that their intra- and inter-annotator $α$-agreement is comparable. Best reliability is obtained for standardized…
Amazon Development Center Germany（亚马逊德国开发中心）；Heidelberg University（海德堡大学）
We introduce and describe the results of a novel shared task on bandit learning for machine translation. The task was organized jointly by Amazon and Heidelberg University for the first time at the Second Conference on Machine Translation (WMT 2017). The goal of the task is to encourage research on learning machine translation from weak user feedback instead of human references or post-edits. On each of a sequence of rounds, a machine translation system is required to propose a translation for an input, and receives a real-valued estimate of the quality of the proposed translation for learning…
Counterfactual learning is a natural scenario to improve web-based machine translation services by offline learning from feedback logged during user interactions. In order to avoid the risk of showing inferior translations to users, in such scenarios mostly exploration-free deterministic logging policies are in place. We analyze possible degeneracies of inverse and reweighted propensity scoring estimators, in stochastic and deterministic settings, and relate them to recently proposed techniques for counterfactual learning under deterministic logging.
Exploring the effectiveness of ChatGPT-based feedback compared with teacher feedback and self-feedback: Evidence from Chinese to English translation
School of Foreign Languages, Southeast University（东南大学外国语学院）；The Hong Kong Polytechnic University（香港理工大学）；School of Languages, Literature, Cultures and Linguistics, Monash University（莫纳什大学语言、文学、文化与语言学学院）
In many machine learning scenarios, supervision by gold labels is not available and consequently neural models cannot be trained directly by maximum likelihood estimation (MLE). In a weak supervision scenario, metric-augmented objectives can be employed to assign feedback to model outputs, which can be used to extract a supervision signal for training. We present several objectives for two separate weakly supervised tasks, machine translation and semantic parsing. We show that objectives should actively discourage negative outputs in addition to promoting a surrogate gold structure. This notio…
Style transfer is the task of transferring an attribute of a sentence (e.g., formality) while maintaining its semantic content. The key challenge in style transfer is to strike a balance between the competing goals, one to preserve meaning and the other to improve the style transfer accuracy. Prior research has identified that the task of meaning preservation is generally harder to attain and evaluate. This paper proposes two extensions of the state-of-the-art style transfer models aiming at improving the meaning preservation in style transfer. Our evaluation shows that these extensions help t…
ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback
Tencent AI Lab（腾讯人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）
University of Science and Technology of China（中国科学技术大学）；University of California Santa Barbara（加州大学圣巴巴拉分校）；Alibaba DAMO Academy（阿里巴巴达摩院）；Tencent AI Lab（腾讯人工智能实验室）
End-to-End Speech Translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency, and fewer parameters. However, the effectiveness of neural-based approaches to this task is severely limited by the available training corpus, especially for domain adaptation where in-domain triplet training data is scarce or nonexistent. In this paper, we propose a novel non-parametric method that leverages domain-specific text translation corpus to achieve domain adaptation for the E2E-ST system. To this end, we first incorporate an additional encoder i…
Nanjing University of Information Science and Technology（南京信息工程大学）；University of Leeds（利兹大学）
This paper explores the use of Deep Learning methods for automatic estimation of quality of human translations. Automatic estimation can provide useful feedback for translation teaching, examination and quality control. Conventional methods for solving this task rely on manually engineered features and external knowledge. This paper presents an end-to-end neural model without feature engineering, incorporating a cross attention mechanism to detect which parts in sentence pairs are most relevant for assessing quality. Another contribution concerns of prediction of fine-grained scores for measur…
