Attending to Characters in Neural Sequence Labeling Models

Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining alternative word representations... (read more)

PDF Abstract COLING 2016 PDF COLING 2016 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Grammatical Error Detection FCE Bi-LSTM + charattn F0.5 41.88 # 5
Part-Of-Speech Tagging Penn Treebank Bi-LSTM + charattn Accuracy 97.27 # 15

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet