paper-with-me

홈 › Papers

Adversarial Structured Prediction for Multivariate Measures

2017-12-20 · Hong Wang, Ashkan Rezaei, Brian D. Ziebart

Many predicted structured objects (e.g., sequences, matchings, trees) are evaluated using the F-score, alignment error rate (AER), or other multivariate performance measures. Since inductively optimizing these measures using training data is typically computationally difficult, empirical risk minimization of surrogate losses is employed, using, e.g., the hinge loss for (structured) support vector machines. These approximations often introduce a mismatch between the learner's objective and the desired application performance, leading to inconsistency. We take a different approach: adversarially approximate training data while optimizing the exact F-score or AER. Structured predictions under this formulation result from solving zero-sum games between a predictor seeking the best performance and an adversary seeking the worst while required to (approximately) match certain structured properties of the training data. We explore this approach for word alignment (AER evaluation) and named entity recognition (F-score evaluation) with linear-chain constraints.

📄 PDF Abstract BibTeX arXiv:1712.07374

Code (0)

등록된 구현이 없습니다.

Tasks

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)PredictionStructured PredictionWord Alignment

Similar Papers 제목 키워드 기반

Optimizing Ranking Measures for Compact Binary Code Learning

2014-07-04 · Guosheng Lin, Chunhua Shen, Jianxin Wu

Hashing has proven a valuable tool for large-scale information retrieval. Despite much success, existing hashing methods optimize over simple objectives such as the reconstruction error or graph Laplacian related loss fu…

Image RetrievalInformation RetrievalRetrieval

Adversarial Attack and Defense of Structured Prediction Models

2020-10-04 · EMNLP 2020 11 · Wenjuan Han, Liwen Zhang, Yong Jiang, Kewei Tu

Building an effective adversarial attacker and elaborating on countermeasures for adversarial attacks for natural language processing (NLP) have attracted a lot of research in recent years. However, most of the existing …

Adversarial AttackDependency ParsingPart-Of-Speech TaggingPrediction+2

Structured Learning of Binary Codes with Column Generation

2016-02-22 · Guosheng Lin, Fayao Liu, Chunhua Shen, Jianxin Wu 외

Hashing methods aim to learn a set of hash functions which map the original features to compact binary codes with similarity preserving in the Hamming space. Hashing has proven a valuable tool for large-scale information…

Image RetrievalInformation RetrievalRetrievalTriplet

Active Learning in Video Tracking

2019-12-29 · Sima Behpour

Active learning methods, like uncertainty sampling, combined with probabilistic prediction techniques have achieved success in various problems like image classification and text classification. For more complex multivar…

Active LearningComputational EfficiencyGeneral Classificationimage-classification+6

Elastic Similarity and Distance Measures for Multivariate Time Series

2021-02-20 · Ahmed Shifaz, Charlotte Pelletier, Francois Petitjean, Geoffrey I. Webb

This paper contributes multivariate versions of seven commonly used elastic similarity and distance measures for time series data analytics. Elastic similarity and distance measures are a class of similarity measures tha…

ClassificationDynamic Time WarpingGeneral ClassificationOutlier Detection+3