Soft Similarity and Soft Cosine Measure: Similarity of Features in Vector Space Model

By Grigori Sidorov, Alexander Gelbukh, Helena Gómez-Adorno, David Pinto. Journal of Computacion y Sistemas, 2014

397 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/7f74703f583650ec274d25d15e1b51ba084d8661

How researchers see this paper

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

In Artificial Intelligence

1. Soujanya Poria
2. Erik Cambria
3. Alexander Gelbukh
4. Krzysztof Marcin Choromanski
5. Devamanyu Hazarika
6. Adrian Weller
7. Louis-philippe Morency
8. Mark Rowland

Citations in the corpus

• The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings (2017, background): “The angular kernel is important for many applications, including natural language processing (Sidorov et al., 2014), image analysis (Jégou et al.”
• Deep Convolutional Neural Network Textual Features and Multiple Kernel Learning for Utterance-level Multimodal Sentiment Analysis (2015, methodology): “We will continue our study of reasoning over text (Jimenez et al., 2015; Pakray et al., 2011; Sidorov et al., 2014; Sidorov, 2014) and in particular of conceptbased sentiment analysis (Poria et al., 2014b).”
• DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verification (2020, methodology): “Specifically, we adopt soft consine measure (Sidorov et al., 2014) between average word embeddings of both claims and comments as semantic similarity.”