• Publications
  • Influence
SemEval-2014 Task 4: Aspect Based Sentiment Analysis
TLDR
Sentiment analysis is increasingly viewed as a vital task both from an academic and a commercial standpoint. Expand
  • 699
  • 107
  • PDF
An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition
TLDR
This article provides an overview of the first BioASQ challenge, a competition on large-scale biomedical semantic indexing and question answering, which took place between March and September 2013. Expand
  • 248
  • 16
  • PDF
Deep Learning for User Comment Moderation
TLDR
We show that an RNN with a novel classification-specific attention mechanism improves further the overall performance of the RNN. Expand
  • 62
  • 10
  • PDF
Deeper Attention to Abusive User Content Moderation
TLDR
An RNN operating on word embeddings outpeforms the previous state of the art in moderation, which used logistic regression or an MLP classifier with character or word n-grams. Expand
  • 56
  • 10
  • PDF
Aspect Term Extraction for Sentiment Analysis: New Datasets, New Evaluation Measures and an Improved Unsupervised Method
TLDR
We make publicly available three new ATE datasets, arguing that they are better than previously available ones. Expand
  • 28
  • 2
  • PDF
Multi-Granular Aspect Aggregation in Aspect-Based Sentiment Analysis
TLDR
We introduce the problem of aspect aggregation at multiple granularities. Expand
  • 13
  • 2
  • PDF
AUEB NLP Group at ImageCLEFmed Caption 2020
TLDR
This article concerns the participation of AUEB’s NLP Group in the ImageCLEFmed Caption task of 2020. Expand
  • 9
  • 2
  • PDF
ConvAI at SemEval-2019 Task 6: Offensive Language Identification and Categorization with Perspective and BERT
TLDR
This paper presents the application of two strong baseline systems for toxicity detection and evaluates their performance in identifying and categorizing offensive language in social media. Expand
  • 10
  • 2
  • PDF
aueb.twitter.sentiment at SemEval-2016 Task 4: A Weighted Ensemble of SVMs for Twitter Sentiment Analysis
TLDR
This paper describes the system with which we participated in SemEval-2016 Task 4 (Sentiment Analysis in Twitter) and specifically the Message Polarity Classification subtask. Expand
  • 12
  • 1
  • PDF
A Survey on Biomedical Image Captioning
TLDR
We present a survey of biomedical image captioning methods, datasets, evaluation measures, and state of the art methods. Expand
  • 13
  • 1
  • PDF