42 |
Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss ...
|
|
|
|
Abstract:
Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data set size, and label noise. We address these issues and evaluate bi-LSTMs with word, character, and unicode byte embeddings for POS tagging. We compare bi-LSTMs to traditional POS taggers across languages and data sizes. We also present a novel bi-LSTM model, which combines the POS tagging loss function with an auxiliary loss function that accounts for rare words. The model obtains state-of-the-art performance across 22 languages, and works especially well for morphologically complex languages. Our analysis suggests that bi-LSTMs are less sensitive to training data size and label corruptions (at small noise levels) than previously assumed. ... : In ACL 2016 (short) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1604.05529 https://arxiv.org/abs/1604.05529
|
|
BASE
|
|
Hide details
|
|
43 |
TwiSty: a multilingual Twitter Stylometry corpus for gender and personality profiling ...
|
|
|
|
BASE
|
|
Show details
|
|
44 |
TwiSty: a multilingual Twitter Stylometry corpus for gender and personality profiling ...
|
|
|
|
BASE
|
|
Show details
|
|
45 |
Keystroke dynamics as signal for shallow syntactic parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|