1 |
Syntactic Nuclei in Dependency Parsing -- A Multilingual Exploration ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Attention Can Reflect Syntactic Structure (If You Let It) ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Schrödinger's Tree -- On Syntax and Neural Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Do Neural Language Models Show Preferences for Syntactic Formalisms? ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing -- A Tale of Two Parsers Revisited ...
|
|
|
|
Abstract:
Transition-based and graph-based dependency parsers have previously been shown to have complementary strengths and weaknesses: transition-based parsers exploit rich structural features but suffer from error propagation, while graph-based parsers benefit from global optimization but have restricted feature scope. In this paper, we show that, even though some details of the picture have changed after the switch to neural networks and continuous representations, the basic trade-off between rich features and global optimization remains essentially the same. Moreover, we show that deep contextualized word embeddings, which allow parsers to pack information about global sentence structure into local feature representations, benefit transition-based parsers more than graph-based parsers, making the two approaches virtually equivalent in terms of both accuracy and error profile. We argue that the reason is that these representations help prevent search errors and thereby allow transition-based parsers to better ... : Accepted at EMNLP 2019 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1908.07397 https://arxiv.org/abs/1908.07397
|
|
BASE
|
|
Hide details
|
|
9 |
Encoders Help You Disambiguate Word Senses in Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
82 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Models ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
An Analysis of Attention Mechanisms: The Case of Word Sense Disambiguation in Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|