target-oriented opinion words extraction
7 papers with code • 0 benchmarks • 0 datasets
The objective of TOWE is to extract the corresponding opinion words describing or evaluating the target from the review.
Benchmarks
These leaderboards are used to track progress in target-oriented opinion words extraction
Most implemented papers
Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling
In this paper, we propose a novel sequence labeling subtask for ABSA named TOWE (Target-oriented Opinion Words Extraction), which aims at extracting the corresponding opinion words for a given opinion target.
Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction
1429904852/LOTN
•
•
In this paper, we propose a novel model to transfer these opinions knowledge from resource-rich review sentiment classification datasets to low-resource task TOWE.
Attention-based Relational Graph Convolutional Network for Target-Oriented Opinion Words Extraction
wcwowwwww/towe-eacl
•
•
EACL 2021
It aims to extract the corresponding opinion words for a given opinion target in a review sentence.
Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction
Many recent works on ABSA focus on Target-oriented Opinion Words (or Terms) Extraction (TOWE), which aims at extracting the corresponding opinion words for a given opinion target.
An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction
samensah/encoders_towe_emnlp2021
•
•
EMNLP 2021
Target-oriented opinion words extraction (TOWE) (Fan et al., 2019b) is a new subtask of target-oriented sentiment analysis that aims to extract opinion words for a given aspect in text.
Training Entire-Space Models for Target-oriented Opinion Words Extraction
Moreover, the performance of these models on the first type of instance cannot reflect their performance on entire space.
Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction
towessl/towessl
•
•
COLING 2022
Limited labeled data increase the risk of distribution shift between test data and training data.
