SOTAVerified

Aspect Extraction

Aspect extraction is the task of identifying and extracting terms relevant for opinion mining and sentiment analysis, for example terms for product attributes or features.

Papers

Showing 1120 of 92 papers

TitleStatusHype
Improving BERT Performance for Aspect-Based Sentiment AnalysisCode1
DILBERT: Customized Pre-Training for Domain Adaptation with Category Shift, with an Application to Aspect ExtractionCode1
YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain ReviewsCode1
Automatic Controllable Product Copywriting for E-CommerceCode1
Adversarial Training for Aspect-Based Sentiment Analysis with BERTCode1
BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment AnalysisCode1
Hyperbolic Disentangled Representation for Fine-Grained Aspect ExtractionCode0
Double Embeddings and CNN-based Sequence Labeling for Aspect ExtractionCode0
Improving Aspect Extraction based on Rules through Deep Syntax-Semantics CommunicationCode0
A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment AnalysisCode0
Show:102550
← PrevPage 2 of 10Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InstructABSALaptop (F1)92.3Unverified
2ACELaptop (F1)87.4Unverified
3PH-SUMLaptop (F1)86.09Unverified
4BATLaptop (F1)85.57Unverified
5DE-CNNRestaurant (F1)85.2Unverified
6Wei et al. (2020)Laptop (F1)82.7Unverified
#ModelMetricClaimedVerifiedStatus
1ACERestaurant (F1)80.3Unverified
2Wei et al. (2020)Restaurant (F1)72.7Unverified
3DE-CNNRestaurant (F1)68.28Unverified
#ModelMetricClaimedVerifiedStatus
1DE-CNNLaptop (F1)81.59Unverified
#ModelMetricClaimedVerifiedStatus
1DE-CNNRestaurant (F1)74.37Unverified
#ModelMetricClaimedVerifiedStatus
1RACL - LaptopsF123Unverified