Bofang Li, Tao Liu, Zhe Zhao,et al published a paper at AAAI2017

Feb 4th - 9th,2017

Bofang Li, Tao Liu, Zhe Zhao, Puwei Wang and Xiaoyong Du published a paper named “Neural bag-of-n-grams” at the 31th AAAI Conference on Artificial Intelligence (AAAI) between Feb 4th and 9th,2017.

In this paper, they introduce the concept of Neural Bag-of-ngrams (Neural-BoN), which replaces sparse one-hot n-gram representation in traditional BoN with dense and rich-semantic n-gram representations. They first propose context guided n-gram representation by adding n-grams to word embeddings model. However, the context guided learning strategy of word embeddings is likely to miss some semantics for text-level tasks. Text guided ngram representation and label guided n-gram representation are proposed to capture more semantics like topic or sentiment tendencies. Neural-BoN with the latter two n-gram representations achieve state-of-the-art results on 4 documentlevel classification datasets and 6 semantic relatedness categories.

AAAI is called Association for the Advancement of Artificial Intelligence. It is a long-standing international conference in the field of artificial intelligence. It attracts thousands of scholars from around the world to discuss the development frontier of artificial intelligence. This year is the 28th session, held in Quebec City, Canada in July. A total of 1,406 submissions were received this year, and 398 were eventually accepted, with a recruitment rate of 28%.