Dynamic Oracle
Related Papers
Neural Greedy Constituent Parsing with Dynamic Oracles
Dynamic oracle training has shown sub- stantial improvements for dependency parsing in various settings, but has not been explored for constituent parsing. The present article introduces a dynamic ora- cle …...
Dynamic Oracle for Neural Machine Translation in Decoding Phase
The past several years have witnessed the rapid progress of end-to-end Neural Machine Translation (NMT). However, there exists discrepancy between training and inference in NMT when decoding, which may lead …...
Transition-based Neural RST Parsing with Implicit Syntax Features
AbstractSyntax has been a useful source of information for statistical RST discourse parsing. Under the neural setting, a common approach integrates syntax by a recursive neural network (RNN), requiring discrete …...
Parsing Chinese Sentences with Grammatical Relations
AbstractWe report our work on building linguistic resources and data-driven parsers in the grammatical relation (GR) analysis for Mandarin Chinese. Chinese, as an analytic language, encodes grammatical information in a …...
Simultaneous Translation with Flexible Policy via Restricted Imitation Learning
AbstractSimultaneous translation is widely useful but remains one of the most difficult tasks in NLP. Previous work either uses fixed-latency policies, or train a complicated two-staged model using reinforcement learning. …...
Calculating the optimal step of arc-eager parsing for non-projective trees
AbstractIt is shown that the optimal next step of an arc-eager parser relative to a non-projective dependency structure can be calculated in cubic time, solving an open problem in parsing …...
Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle
AbstractSyntax is fundamental to our thinking about language. Failing to capture the structure of input language could lead to generalization problems and over-parametrization. In the present work, we propose a …...