Optimal Shift-Reduce Constituent Parsing with Structured Perceptron
نویسندگان
چکیده
We present a constituent shift-reduce parser with a structured perceptron that finds the optimal parse in a practical runtime. The key ideas are new feature templates that facilitate state merging of dynamic programming and A* search. Our system achieves 91.1 F1 on a standard English experiment, a level which cannot be reached by other beam-based systems even with large beam sizes.1
منابع مشابه
Shift-Reduce CCG Parsing using Neural Network Models
We present a neural network based shiftreduce CCG parser, the first neural-network based parser for CCG. We also study the impact of neural network based tagging models, and greedy versus beam-search parsing, by using a structured neural network model. Our greedy parser obtains a labeled F-score of 83.27%, the best reported result for greedy CCG parsing in the literature (an improvement of 2.5%...
متن کاملTransition-Based Left-Corner Parsing for Identifying PTB-Style Nonlocal Dependencies
This paper proposes a left-corner parser which can identify nonlocal dependencies. Our parser integrates nonlocal dependency identification into a transition-based system. We use a structured perceptron which enables our parser to utilize global features captured by nonlocal dependencies. An experimental result demonstrates that our parser achieves a good balance between constituent parsing and...
متن کاملDistributed Training Strategies for the Structured Perceptron
Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the structured perceptron can be costly to train as training complexity is proportional to inference, which is frequently non-linear in example sequence length. In this paper we investigate distributed training strategies ...
متن کاملFrontier Pruning for Shift-Reduce CCG Parsing
We apply the graph-structured stack (GSS) to shift-reduce parsing in a Combinatory Categorial Grammar (CCG) parser. This allows the shift-reduce parser to explore all possible parses in polynomial time without resorting to heuristics, such as beam search. The GSSbased shift-reduce parser is 34% slower than CKY in the finely-tuned C&C parser. We perform frontier pruning on the GSS, increasing th...
متن کاملRegularized Structured Perceptron: A Case Study on Chinese Word Segmentation, POS Tagging and Parsing
Structured perceptron becomes popular for various NLP tasks such as tagging and parsing. Practical studies on NLP did not pay much attention to its regularization. In this paper, we study three simple but effective task-independent regularization methods: (1) one is to average weights of different trained models to reduce the bias caused by the specific order of the training examples; (2) one i...
متن کامل