Learning Dynamic Feature Selection for Fast Sequential Prediction
We present paired learning and inference algorithms for significantly reducing computation and increasing speed of the vector dot products in the classifiers that are at the heart of many NLP components. This is accomplished by partitioning the features into a sequence of templates which are ordered such that high confidence can often be reached using only a small fraction of all features. Parameter estimation is arranged to maximize accuracy and early confidence in this sequence. Our approach is simpler and better suited to NLP than other related cascade methods. We present experiments in left-to-right part-of-speech tagging, named entity recognition, and transition-based dependency parsing. On the typical benchmarking datasets we can preserve POS tagging accuracy above 97% and parsing LAS above 88.5% both with over a five-fold reduction in run-time, and NER F1 above 88 with more than 2x increase in speed.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingDependency Parsingfeature selectionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERparameter estimationPart-Of-Speech TaggingPOSPOS TaggingPredictionTransition-Based Dependency ParsingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Training for Fast Sequential Prediction Using Dynamic Feature Selection
We present paired learning and inference algorithms for significantly reducing computation and increasing speed of the vector dot products in the classifiers that are at the heart of many NLP components. This is accompli…
feature selectionparameter estimationPart-Of-Speech TaggingAircraft Engines Remaining Useful Life Prediction with an Improved Online Sequential Extreme Learning Machine
The efficient data investigation for fast and accurate remaining useful life prediction of aircraft engines can be considered as a very important task for maintenance operations. In this context, the key issue is how an …
Estimating Conditional Mutual Information for Dynamic Feature Selection
Dynamic feature selection, where we sequentially query features to make accurate predictions with a minimal budget, is a promising paradigm to reduce feature acquisition costs and provide transparency into a model's pred…
feature selectionMulti-task Learning-based Joint CSI Prediction and Predictive Transmitter Selection for Security
In mobile communication scenarios, the acquired channel state information (CSI) rapidly becomes outdated due to fast-changing channels. Opportunistic transmitter selection based on current CSI for secrecy improvement may…
DiversityMulti-Task LearningSafe Active Feature Selection for Sparse Learning
We present safe active incremental feature selection~(SAIF) to scale up the computation of LASSO solutions. SAIF does not require a solution from a heavier penalty parameter as in sequential screening or updating the ful…
feature selectionSparse Learning