stat441w18/Convolutional Neural Networks for Sentence Classification

Presented by

1. Ben Schwarz

2. Cameron Miller

3. Hamza Mirza

4. Pavle Mihajlovic

5. Terry Shi

6. Yitian Wu

7. Zekai Shao

Model

Model Settings

Consider a sentence of length [math]\displaystyle{ n }[/math], represented by [math]\displaystyle{ \boldsymbol{x}_{1:n} }[/math]. Let [math]\displaystyle{ \boldsymbol{x}_i \in \mathbb{R}^k }[/math] be the [math]\displaystyle{ i }[/math]-th word in the sentence and [math]\displaystyle{ \oplus }[/math] be the concatenation operator, where [math]\displaystyle{ \boldsymbol{x}_{1:n} = \boldsymbol{x}_{1} \oplus \boldsymbol{x}_2 \oplus \dots \oplus \boldsymbol{x}_n }[/math]. In general, let [math]\displaystyle{ \boldsymbol{x}_{i:i+j} }[/math] represent the concatenation of words [math]\displaystyle{ \boldsymbol{x}_{i}, \boldsymbol{x}_{i+1}, \dots, \boldsymbol{x}_{i+j} }[/math].

We also consider a filter [math]\displaystyle{ w \in \mathbb{R}^{hk} }[/math].

Datasets and Experimental Setup

Hyperparameters and Training

MR:

SST-1:

SST-2:

Subj:

TREC:

CR:

MPQA:

Model Variations

CNN-rand:

CNN-static:

CNN-static:

CNN-non-static:

CNN-multichannel: