Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

In this paper, we study bidirectional LSTM network for the task of text classification using both supervised and semi-supervised approaches. Several prior works have suggested that either complex pretraining schemes using unsupervised methods such as language modeling (Dai and Le 2015; Miyato, Dai, and Goodfellow 2016) or complicated models (Johnson and Zhang 2017) are necessary to achieve a high classification accuracy... (read more)

PDF Abstract AAAI 2019 2019 PDF AAAI 2019 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Text Classification AG News L MIXED Error 4.95 # 3
Text Classification DBpedia L MIXED Error 0.7 # 3
Sentiment Analysis IMDb L MIXED Accuracy 95.68 # 4

Methods used in the Paper