Sökning: "transition-based parsing"
Hittade 3 uppsatser innehållade orden transition-based parsing.
1. Attention Mechanisms for Transition-based Dependency Parsing
Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologiSammanfattning : Transition-based dependency parsing is known to compute the syntactic structure of a sentence efficiently, but is less accurate to predict long-distance relations between tokens as it lacks global information about the sentence. Our main contribution is the integration of attention mechanisms to replace the static token selection with a dynamic approach that takes the complete sequence into account. LÄS MER
2. Evaluating Globally Normalized Transition Based Neural Networks for Multilingual Natural Language Understanding
Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)Sammanfattning : We analyze globally normalized transition-based neural network models for dependency parsing on English, German, Spanish, and Catalan. We compare the results with FreeLing, an open source language analysis tool developed at the UPC natural language processing research group. LÄS MER
3. Transition-Based Dependency Parsing with Neural Networks
Kandidat-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystemSammanfattning : Dependency parsing is important in contemporary speech and language processing systems. Current dependency parsers typically use the multi-class perceptron machine learning component, which classifies based on millions of sparse indicator features, making developing and maintaining these systems expensive and error-prone. LÄS MER