Imitation Learning for Neural Morphological String Transduction
arXiv:1808.10701
Abstract
We employ imitation learning to train a neural transition-based string transducer for morphological tasks such as inflection generation and lemmatization. Previous approaches to training this type of model either rely on an external character aligner for the production of gold action sequences, which results in a suboptimal model due to the unwarranted dependence on a single gold action sequence despite spurious ambiguity, or require warm starting with an MLE model. Our approach only requires a simple expert policy, eliminating the need for a character aligner or warm start. It also addresses familiar MLE training biases and leads to strong and state-of-the-art performance on several benchmarks.
arXiv comment6 pages; accepted to EMNLP 2018
References in corpus (7)
- ADADELTA: An Adaptive Learning Rate Method
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Sequence Transduction with Recurrent Neural Networks
- An Actor-Critic Algorithm for Sequence Prediction
- Sequence-to-Sequence Learning as Beam-Search Optimization
- Search-based Structured Prediction
- Training with Exploration Improves a Greedy Stack-LSTM Parser