Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision

By Haoruo Peng, Ming-Wei Chang, Wen-tau Yih. 2017

20 citations recorded by the source corpus.

Neural networks have achieved state-of-the-art performance on several structured-output prediction tasks, trained in a fully supervised fashion. However, annotated examples in structured domains are often costly to obtain, which thus limits the applications of neural networks. In this work, we propose Maximum Margin Reward Networks, a neural network-based framework that aims to learn from both explicit (full structures) and implicit supervision signals (delayed feedback on the correctness of the predicted structure). On named entity recognition and semantic parsing, our model outperforms previous systems on the benchmark datasets, CoNLL-2003 and WebQuestionsSP.

Subfields: Artificial Intelligence, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Reinforcement Learning

Citations in the corpus

Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback (2018, methodology): “emoyer(2013); inter alia). More recently, several works have applied policy gradient techniques such as REINFORCE (Williams,1992) to train neural semantic parsers (Liang et al.(2017);Mou et al.(2017);Peng et al. (2017); inter alia). However, they assume the existence of the true target answers that ”
Search-based Neural Structured Learning for Sequential Question Answering (2017, methodology): “Our framework is suitable for learning from either implicit or explicit supervision, and is detailed in a companion paper (Peng et al., 2017).”
A Survey on Semantic Parsing (2018, unknown): “Visually grounded semantic parsing: Recent work by Ross et al. [2018] involves learning a semantic parser using captioned videos.”