Japanese Sentiment Classification using a Tree-Structured Long Short-Term Memory with Attention

04/04/2017
by   Ryosuke Miyazaki, et al.
0

Previous approaches to training syntax-based sentiment classification models required phrase-level annotated corpora, which are not readily available in many languages other than English. Thus, we propose the use of tree-structured Long Short-Term Memory with an attention mechanism that pays attention to each subtree of the parse tree. Experimental results indicate that our model achieves the state-of-the-art performance in a Japanese sentiment classification task.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/17/2016

Cached Long Short-Term Memory Neural Networks for Document-Level Sentiment Classification

Recently, neural networks have achieved great success on sentiment class...
research
02/05/2019

Deep Tree Transductions - A Short Survey

The paper surveys recent extensions of the Long-Short Term Memory networ...
research
11/17/2019

Deep Learning versus Traditional Classifiers on Vietnamese Students' Feedback Corpus

Student's feedback is an important source of collecting students' opinio...
research
03/14/2023

Dual-Attention Model for Aspect-Level Sentiment Classification

I propose a novel dual-attention model(DAM) for aspect-level sentiment c...
research
01/03/2021

Attentive Tree-structured Network for Monotonicity Reasoning

Many state-of-art neural models designed for monotonicity reasoning perf...
research
01/26/2021

"Laughing at you or with you": The Role of Sarcasm in Shaping the Disagreement Space

Detecting arguments in online interactions is useful to understand how c...
research
10/03/2019

A tale of two sentiment scales: Disentangling short-run and long-run components in multivariate sentiment dynamics

We propose a novel approach to sentiment data filtering for a portfolio ...

Please sign up or login with your details

Forgot password? Click here to reset