Training Structured Prediction Energy Networks with Indirect Supervision
This paper introduces rank-based training of structured prediction energy networks (SPENs). Our method samples from output structures using gradient descent and minimizes the ranking violation of the sampled structures with respect to a scalar scoring function defined with domain knowledge. We have successfully trained SPEN for citation field extraction without any labeled data instances, where the only source of supervision is a simple human-written scoring function. Such scoring functions are often easy to provide; the SPEN then furnishes an efficient structured prediction inference procedure.
Code (0)
등록된 구현이 없습니다.
Tasks
PredictionSemantic SegmentationStructured PredictionSimilar Papers 제목 키워드 기반
No Conditional Models for me: Training Joint EBMs on Mixed Continuous and Discrete Data
We propose energy-based models of the joint distribution of data and supervision. While challenging to work with, this approach gives flexibility when designing energy functions and easy parameterization for structured s…
Estimation from Indirect Supervision with Linear Moments
In structured prediction problems where we have indirect supervision of the output, maximum marginal likelihood faces two computational obstacles: non-convexity of the objective and intractability of even a single gradie…
Structured PredictionRethinking Remaining Useful Life Prediction with Scarce Time Series Data: Regression under Indirect Supervision
Supervised time series prediction relies on directly measured target variables, but real-world use cases such as predicting remaining useful life (RUL) involve indirect supervision, where the target variable is labeled a…
PredictionregressionTime SeriesTime Series Prediction+1Learning to Generate Structured Queries from Natural Language with Indirect Supervision
Generating structured query language (SQL) from natural language is an emerging research topic. This paper presents a new learning paradigm from indirect supervision of the answers to natural language questions, instead …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Search-Guided, Lightly-supervised Training of Structured Prediction Energy Networks
In structured output prediction tasks, labeling ground-truth training output is often expensive. However, for many tasks, even when the true output is unknown, we can evaluate predictions using a scalar reward function, …
PredictionStructured Prediction