Related papers: Counterfactual Learning from Bandit Feedback under…
Machine Translation is one of the major oldest and the most active research area in Natural Language Processing. Currently, Statistical Machine Translation (SMT) dominates the Machine Translation research. Statistical Machine Translation is…
Methods for offline A/B testing and counterfactual learning are seeing rapid adoption in search and recommender systems, since they allow efficient reuse of existing log data. However, there are fundamental limits to using existing log data…
Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…
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…
Prompting has emerged as the dominant paradigm for adapting large, pre-trained transformer-based models to downstream tasks. The Prompting Decision Transformer (PDT) enables large-scale, multi-task offline Reinforcement Learning (RL)…
Much of the recent literature on bandit learning focuses on algorithms that aim to converge on an optimal action. One shortcoming is that this orientation does not account for time sensitivity, which can play a crucial role when learning an…
We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning…
An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…
Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate translations (Tu et al. 2016b; Tu et al.…
We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying learning signal may be different between these two data…
Recent advances in simultaneous speech translation (SST) focus on the decision policies that enable the use of offline-trained ST models for simultaneous inference. These decision policies not only control the quality-latency trade-off in…
Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…
Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs.…
Counterfactual reasoning from logged data has become increasingly important for many applications such as web advertising or healthcare. In this paper, we address the problem of learning stochastic policies with continuous actions from the…
Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…
Metamorphic Testing is a software testing paradigm which aims at using necessary properties of a system-under-test, called metamorphic relations, to either check its expected outputs, or to generate new test cases. Metamorphic Testing has…
In recent years, reinforcement learning and bandits have transformed a wide range of real-world applications including healthcare, finance, recommendation systems, robotics, and last but not least, the speech and natural language…
Motivated by a range of applications, we study in this paper the problem of transfer learning for nonparametric contextual multi-armed bandits under the covariate shift model, where we have data collected on source bandits before the start…
Stochastic linear bandits are a natural and well-studied model for structured exploration/exploitation problems and are widely used in applications such as online marketing and recommendation. One of the main challenges faced by…
Data-driven decision making frequently relies on predicting counterfactual outcomes. In practice, researchers commonly train counterfactual prediction models on a source dataset to inform decisions on a possibly separate target population.…