A Short Texts Matching Method Using Shallow Features and Deep Features

By Longbiao Kang, Baotian Hu, Xiangping Wu, Qingcai Chen, Yan He. 2014

15 citations recorded by the source corpus.

How researchers see this paper

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

1. Cedric De Boom
2. Steven Van Canneyt
3. Thomas Demeester
4. Bart Dhoedt
5. Steven Bohez
6. Alfirna Rizqi Lahitani
7. Dimitrios Bountouridis
8. Pasquale Minervini

Citations in the corpus

• Representation learning for very short texts using weighted word embedding aggregation (2016, methodology): “Finally, Kang et al. (2014) calculate a cosine similarity matrix between the words of two sentences that are sorted based on their idf value, which they use as a feature vector for an MLP.”
• Learning Semantic Similarity for Very Short Texts (2015, background): “Many authors choose to average or maximize across the embeddings in a text [8], [9], [10] or combine them through a multi-layer perceptron [6], [11], by clustering [12], or by trimming the text to a fixed length [11].”