Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing
Pruning hypotheses during dynamic programming is commonly used to speed up inference in settings such as parsing. Unlike prior work, we train a pruning policy under an objective that measures end-to-end performance: we search for a fast and accurate policy. This poses a difficult machine learning problem, which we tackle with the lols algorithm. lols training must continually compute the effects of changing pruning decisions: we show how to make this efficient in the constituency parsing setting, via dynamic programming and change propagation algorithms. We find that optimizing end-to-end performance in this way leads to a better Pareto frontier{---}i.e., parsers which are more accurate for a given runtime.
Code (0)
등록된 구현이 없습니다.
Tasks
Constituency ParsingDecision MakingMachine TranslationStructured PredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Viable Dependency Parsing as Sequence Labeling
We recast dependency parsing as a sequence labeling problem, exploring several encodings of dependency trees as labels. While dependency parsing by means of sequence labeling had been attempted in existing work, results …
Dependency ParsingLearning-Guided Sparsification of Dynamic Graphs in Robotic Exploration
Many robotic exploration algorithms rely on graph structures for frontier-based exploration and dynamic path planning. However, these graphs grow rapidly, accumulating redundant information and impacting performance. We …
fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP
We present fastHan, an open-source toolkit for four basic tasks in Chinese natural language processing: Chinese word segmentation (CWS), Part-of-Speech (POS) tagging, named entity recognition (NER), and dependency parsin…
Chinese Word SegmentationDependency Parsingnamed-entity-recognitionNamed Entity Recognition+5Pruning Neural Machine Translation for Speed Using Group Lasso
Unlike most work on pruning neural networks, we make inference faster. Group lasso regularisation enables pruning entire rows, columns or blocks of parameters that result in a smaller dense network. Because the network i…
DecoderMachine TranslationTranslation