Search-based structured prediction

Daumé, Hal; Langford, John; Marcu, Daniel

doi:10.1007/s10994-009-5106-x

Cited by 349 publications

(385 citation statements)

References 33 publications

Supporting

Mentioning

383

Contrasting

Order By: Relevance

“…The use of sequential predictions-feeding the output of predictors from a previous stage to the next-has been revisited in the literature from time to time. Methods such as [23,24] applied sequential prediction to natural language processing tasks. While [25] explored the use of context from neighboring pixel classifiers for computer vision tasks.…”

Section: Related Workmentioning

confidence: 99%

Pose Machines: Articulated Pose Estimation via Inference Machines

Ramakrishna

Munoz

Hebert

et al. 2014

Lecture Notes in Computer Science

202

131

View full text Add to dashboard Cite

Abstract. State-of-the-art approaches for articulated human pose estimation are rooted in parts-based graphical models. These models are often restricted to tree-structured representations and simple parametric potentials in order to enable tractable inference. However, these simple dependencies fail to capture all the interactions between body parts. While models with more complex interactions can be defined, learning the parameters of these models remains challenging with intractable or approximate inference. In this paper, instead of performing inference on a learned graphical model, we build upon the inference machine framework and present a method for articulated human pose estimation. Our approach incorporates rich spatial interactions among multiple parts and information across parts of different scales. Additionally, the modular framework of our approach enables both ease of implementation without specialized optimization solvers, and efficient inference. We analyze our approach on two challenging datasets with large pose variation and outperform the state-of-the-art on these benchmarks.

show abstract

Section: Related Workmentioning

confidence: 99%

Pose Machines: Articulated Pose Estimation via Inference Machines

Ramakrishna

Munoz

Hebert

et al. 2014

Lecture Notes in Computer Science

202

131

View full text Add to dashboard Cite

show abstract

“…Such algorithms decompose a joint prediction task into a sequence of action predictions, such as predicting the label of the next word in sequence labeling or predicting a shift/reduce action in dependency parsing 3 ; these predictions are tied by features and/or internal state. Algorithms in this family have recently met with success in neural networks (Bengio et al, 2015;Wiseman and Rush, 2016), though date back to models typically based on linear policies (Collins and Roark, 2004;Daumé III and Marcu, 2005;Xu et al, 2007;Daumé III et al, 2009;Ross et al, 2010;Ross and Bagnell, 2014;Doppa et al, 2014;Chang et al, 2015).…”

Section: Learning With Bandit Feedbackmentioning

confidence: 99%

Structured Prediction via Learning to Search under Bandit Feedback

Sharaf

Daumé

2017

Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing

View full text Add to dashboard Cite

We present an algorithm for structured prediction under online bandit feedback. The learner repeatedly predicts a sequence of actions, generating a structured output. It then observes feedback for that output and no others. We consider two cases: a pure bandit setting in which it only observes a loss, and more fine-grained feedback in which it observes a loss for every action. We find that the fine-grained feedback is necessary for strong empirical performance, because it allows for a robust variance-reduction strategy. We empirically compare a number of different algorithms and exploration methods and show the efficacy of BLS on sequence labeling and dependency parsing tasks.

show abstract

“…Imitation learning 1 algorithms such as SEARN (Daumé III et al, 2009) and DAGGER (Ross et al, 2011) have been applied successfully to a variety of structured prediction tasks due to their flexibility in incorporating features and their ability to learn with non-decomposable loss functions. Sample applications include biomedical event extraction (Vlachos and Craven, 2011), dynamic feature selection (He et al, 2013), and machine translation (Grissom II et al, 2014).…”

Section: Imitation Learningmentioning

confidence: 99%

Extracting Relations between Non-Standard Entities using Distant Supervision and Imitation Learning

Augenstein¹,

Vlachos²,

Maynard³

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Distantly supervised approaches have become popular in recent years as they allow training relation extractors without textbound annotation, using instead known relations from a knowledge base and a large textual corpus from an appropriate domain. While state of the art distant supervision approaches use off-theshelf named entity recognition and classification (NERC) systems to identify relation arguments, discrepancies in domain or genre between the data used for NERC training and the intended domain for the relation extractor can lead to low performance. This is particularly problematic for "non-standard" named entities such as album which would fall into the MISC category. We propose to ameliorate this issue by jointly training the named entity classifier and the relation extractor using imitation learning which reduces structured prediction learning to classification learning. We further experiment with Web features different features and compare against using two off-the-shelf supervised NERC systems, Stanford NER and FIGER, for named entity classification. Our experiments show that imitation learning improves average precision by 4 points over an one-stage classification model, while removing Web features results in a 6 points reduction. Compared to using FIGER and Stanford NER, average precision is 10 points and 19 points higher with our imitation learning approach.

show abstract

Search-based structured prediction

Cited by 349 publications

References 33 publications

Pose Machines: Articulated Pose Estimation via Inference Machines

Pose Machines: Articulated Pose Estimation via Inference Machines

Structured Prediction via Learning to Search under Bandit Feedback

Extracting Relations between Non-Standard Entities using Distant Supervision and Imitation Learning

Contact Info

Product

Resources

About