Coactive Learning for Interactive Machine Translation
نویسندگان
چکیده
Coactive learning describes the interaction between an online structured learner and a human user who corrects the learner by responding with weak feedback, that is, with an improved, but not necessarily optimal, structure. We apply this framework to discriminative learning in interactive machine translation. We present a generalization to latent variable models and give regret and generalization bounds for online learning with a feedback-based latent perceptron. We show experimentally that learning from weak feedback in machine translation leads to convergence in regret and translation error.
منابع مشابه
A Coactive Learning View of Online Structured Prediction in Statistical Machine Translation
We present a theoretical analysis of online parameter tuning in statistical machine translation (SMT) from a coactive learning view. This perspective allows us to give regret and generalization bounds for latent perceptron algorithms that are common in SMT, but fall outside of the standard convex optimization scenario. Coactive learning also introduces the concept of weak feedback, which we app...
متن کاملOnline Learning for Effort Reduction in Interactive Neural Machine Translation
Neural machine translation systems require large amounts of training data and resources. Even with this, the quality of the translations may be insufficient for some users or domains. In such cases, the output of the system must be revised by a human agent. This can be done in a post-editing stage or following an interactive machine translation protocol. We explore the incremental update of neu...
متن کاملOnline Learning for Interactive Statistical Machine Translation
State-of-the-art Machine Translation (MT) systems are still far from being perfect. An alternative is the so-called Interactive Machine Translation (IMT) framework. In this framework, the knowledge of a human translator is combined with a MT system. The vast majority of the existing work on IMT makes use of the well-known batch learning paradigm. In the batch learning paradigm, the training of ...
متن کاملUsing Agents to Investigate Strategies for Human Collaborative
Given the cost and effort involved in investigating different methods or protocols for human collaborative learning, this paper proposes the use of software learning agents to simulate and test various protocols. The best performing protocols would then be tested on human subjects. The paper presents a new form of cooperative learning, called coactive learning. After arguing that humans could b...
متن کاملCoactive Learning for Distributed Data Mining
We introduce coactive learning as a distributed learning approach to data mining in networked and distributed databases. The coactive learning algorithms act on independent data sets and cooperate by communicating training information, which is used to guide the algorithms’ hypothesis construction. The exchanged training information is limited to examples and responses to examples. It is shown ...
متن کامل