2 |
A Call for More Rigor in Unsupervised Cross-lingual Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
On the Cross-lingual Transferability of Monolingual Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Learning to Compose Words into Sentences with Reinforcement Learning ...
|
|
|
|
Abstract:
We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or predicted using supervision from explicit treebank annotations, the tree structures in this work are optimized to improve performance on a downstream task. Experiments demonstrate the benefit of learning task-specific composition orders, outperforming both sequential encoders and recursive encoders based on treebank annotations. We analyze the induced trees and show that while they discover some linguistically intuitive structures (e.g., noun phrases, simple verb phrases), they are different than conventional English syntactic structures. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1611.09100 https://arxiv.org/abs/1611.09100
|
|
BASE
|
|
Hide details
|
|
7 |
Learning Word Representations with Hierarchical Sparse Coding ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Learning Word Representations with Hierarchical Sparse Coding ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Learning Word Representations with Hierarchical Sparse Coding ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Predicting a Scientific Community’s Response to an Article ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Predicting a Scientific Community’s Response to an Article ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Part-of-Speech Tagging for Twitter: Annotation, Features, and Experiments
|
|
|
|
In: DTIC (2010)
|
|
BASE
|
|
Show details
|
|
|
|