| Download | - View final version: End-to-end multi-view networks for text classification (PDF, 946 KiB)
|
|---|
| Author | Search for: Guo, Hongyu1; Search for: Cherry, Colin1; Search for: Su, Jiang1 |
|---|
| Affiliation | - National Research Council of Canada. Information and Communication Technologies
|
|---|
| Format | Text, Article |
|---|
| Subject | computation and language; learning; neural and evolutionary computing |
|---|
| Abstract | We propose a multi-view network for text classification. Our method automatically creates various views of its input text, each taking the form of soft attention weights that distribute the classifier's focus among a set of base features. For a bag-of-words representation, each view focuses on a different subset of the text's words. Aggregating many such views results in a more discriminative and robust representation. Through a novel architecture that both stacks and concatenates views, we produce a network that emphasizes both depth and width, allowing training to converge quickly. Using our multi-view architecture, we establish new state-of-the-art accuracies on two benchmark tasks. |
|---|
| Publication date | 2017-04-19 |
|---|
| Publisher | Cornell University Library |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | No |
|---|
| NPARC number | 23002277 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 0c6ea103-6166-460f-90ac-06eff86608d0 |
|---|
| Record created | 2017-09-28 |
|---|
| Record modified | 2020-05-30 |
|---|
