1. A Fast Unified Model for Parsing and Sentence Understanding
- Author
-
Raghav Gupta, Samuel R. Bowman, Christopher D. Manning, Jon Gauthier, Christopher Potts, and Abhinav Rastogi
- Subjects
FOS: Computer and information sciences ,Computer Science - Computation and Language ,Parsing ,Interpretation (logic) ,Artificial neural network ,Computer science ,business.industry ,02 engineering and technology ,computer.software_genre ,Machine learning ,Logical consequence ,Syntax ,Task (project management) ,030507 speech-language pathology & audiology ,03 medical and health sciences ,TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,0305 other medical science ,business ,Computation and Language (cs.CL) ,computer ,Natural language processing ,Sentence - Abstract
Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences. However, they suffer from two key technical problems that make them slow and unwieldy for large-scale NLP tasks: they usually operate on parsed sentences and they do not directly support batched computation. We address these issues by introducing the Stack-augmented Parser-Interpreter Neural Network (SPINN), which combines parsing and interpretation within a single tree-sequence hybrid model by integrating tree-structured sentence interpretation into the linear sequential structure of a shift-reduce parser. Our model supports batched computation for a speedup of up to 25 times over other tree-structured models, and its integrated parser can operate on unparsed data with little loss in accuracy. We evaluate it on the Stanford NLI entailment task and show that it significantly outperforms other sentence-encoding models., To appear at ACL 2016
- Published
- 2016
- Full Text
- View/download PDF