A Fast Unified Model for Parsing and Sentence Understanding

Samuel R. Bowman, Jon Gauthier, Abhinav Rastogi, Raghav Gupta, Christopher D. Manning +1 more
3/19/2016
cs.CL

Official code: stanfordnlp/spinn (208 stars, MIT, last commit 2018-03-15).

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.

View on arXivView PDF

Code Implementations(1)

stanfordnlp/spinnOfficial100%
MIT

SPINN (Stack-augmented Parser-Interpreter Neural Network): fast, batchable, context-aware TreeRNNs

20882C++, TeXOct 14, 20158 years agoMIT

Similar Papers

The Lifted Matrix-Space Model for Semantic Composition

83% match2 repos1082017

TreePiece: Faster Semantic Parsing via Tree Tokenization

82% match2023

Strongly Incremental Constituency Parsing with Graph Neural Networks

82% match1 repo382020

Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State

81% match1 repo172019

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

80% match1 repo8922015

Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations

80% match1 repo102018

Cite this paper

@article{bowman2016fast,
  title  = {A Fast Unified Model for Parsing and Sentence Understanding},
  author = {Samuel R. Bowman and Jon Gauthier and Abhinav Rastogi and Raghav Gupta and Christopher D. Manning and Christopher Potts},
  year   = {2016},
  eprint = {1603.06021},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1603.06021}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1603.06021.svg)](https://codeofpaper.com/paper/1603.06021)

Discussion