Expected F-Measure Training for Shift-Reduce Parsing with Recurrent Neural Networks
نویسندگان
چکیده
We present expected F-measure training for shift-reduce parsing with RNNs, which enables the learning of a global parsing model optimized for sentence-level F1. We apply the model to CCG parsing, where it improves over a strong greedy RNN baseline, by 1.47% F1, yielding state-of-the-art results for shiftreduce CCG parsing.
منابع مشابه
Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training
We propose a discriminatively trained recurrent neural network (RNN) that predicts the actions for a fast and accurate shift-reduce dependency parser. The RNN uses its output-dependent model structure to compute hidden vectors that encode the preceding partial parse, and uses them to estimate probabilities of parser actions. Unlike a similar previous generative model (Henderson and Titov, 2010)...
متن کاملDependency Parsing with LSTMs: An Empirical Evaluation
We propose a transition-based dependency parser using Recurrent Neural Networks with Long Short-Term Memory (LSTM) units. This extends the feedforward neural network parser of Chen and Manning (2014) and enables modelling of entire sequences of shift/reduce transition decisions. On the Google Web Treebank, our LSTM parser is competitive with the best feedforward parser on overall accuracy and n...
متن کاملHierarchical Feature For Scene Parsing Using Fully Recurrent Network
In scene parsing, the wide-range contextual information is not effectively encoded. Scene parsing provides segmentation and determines an scene into different regions associated with semantic categories. The main objective of scene parsing is to reduce semantic gap between humans and computer machines on scene understanding. The scenes parsing applications are object detection, text detection o...
متن کاملMulti-Path Feedback Recurrent Neural Network for Scene Parsing
In this paper, we consider the scene parsing problem. We propose a novel Multi-Path Feedback recurrent neural network (MPF-RNN) to enhance the capability of RNNs on modeling long-range context information at multiple levels and better distinguish pixels that are easy to confuse in pixel-wise classification. In contrast to CNNs without feedback and RNNs with only a single feedback path, MPFRNN p...
متن کاملSARDSRN: A Neural Network Shift-Reduce Parser
Simple Recurrent Networks (SRNs) have been widely used in natural language tasks. SARDSRN extends the SRN by explicitly representing the input sequence in a SARDNET self-organizing map. The distributed SRN component leads to good generalization and robust cognitive properties, whereas the SARDNET map provides exact representations of the sentence constituents. This combination allows SARDSRN to...
متن کامل