3.2.1. Word representation using CNNs
As shown in Fig. 3, our word representations employ both handcrafted and
automatically learned features.
Handcrafted features. We use the POS tag of the word and multiple features
that check whether the word contains special characters, whether the word is a
number, and look at capitalization patterns of the word.
Automatically learned features. We use both word embeddings and
character embeddings. Convolutional neural networks are then used to extract
features from the matrix formed from character embeddings.
Fig. 3. Word representation using CNNsThe final representation of a word is the concatenation of three components:
Bạn đang xem 3. - QUESTION ANALYSIS TOWARDS A VIETNAMESE QUESTION ANSWERING SYSTEM IN THE EDUCATION DOMAIN