of the European Chapter of the Association for Computational Linguistics

By Adam Kilgarriff, Marco Baroni. 2006

400 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/1c929b8e9a999ef086e3df54b003df66f22d4ceb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Mohit Bansal
2. Duyu Tang
3. Saif M. Mohammad
4. Bing Liu
5. Percy Liang
6. Zhe Gan
7. Lei Zhang
8. B. Liu

Citations in the corpus

• A comprehensive survey on feature selection in the various fields of machine learning (2021, background): “Semantic orientation score [88] – Sentiment orientation score is calculated for each word, which tells how much word is associated with positive or negative sentiments.”
• BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network (2012, background): “, the one proposed in [16]), we found this very simple approach worked surprisingly well – i.”
• The Meteor metric for automatic evaluation of machine translation (2009, methodology): “2006) and CDER (Leusch et al. 2006), were developed specifically to address these weaknesses identified in Bleu.”
• Adaptive Regularization of Labels (2019, methodology): “For all datasets, we evaluate four methods of text classification with or without our proposed regularization, including FastText [10], TextRNN [13], CharCNN [29], and Transformer [23].”
• Opinion Mining and Sentiment Analysis (2008, background): “In addition to classification based on affect and emotion, another related area of research that addresses non-topic-based categorization is that of determining the genreof texts [97, 98, 150, 153, 182, 278].”
• Sentiment Analysis and Opinion Mining (2012, methodology): “Other methods based on graphs include those in Takamura et al. (2005, 2006, 2007).”
• Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases (2020, background): “racy in an semi-supervised manner by following a lexicon induction strategy [35].”
• Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization (2021, background): “Dialogue quality is inherently multi-faceted [7, 38, 51], including fluency, coherence, diversity, consistency, etc.”