Doc2Im: document to image conversion through self-attentive embedding
Text classification is a fundamental task in NLP applications. Latest research in this field has largely been divided into two major sub-fields. Learning representations is one sub-field and learning deeper models, both sequential and convolutional, which again connects back to the representation is the other side. We posit the idea that the stronger the representation is, the simpler classifier models are needed to achieve higher performance. In this paper we propose a completely novel direction to text classification research, wherein we convert text to a representation very similar to images, such that any deep network able to handle images is equally able to handle text. We take a deeper look at the representation of documents as an image and subsequently utilize very simple convolution based models taken as is from computer vision domain. This image can be cropped, re-scaled, re-sampled and augmented just like any other image to work with most of the state-of-the-art large convolution based models which have been designed to handle large image datasets. We show impressive results with some of the latest benchmarks in the related fields. We perform transfer learning experiments, both from text to text domain and also from image to text domain. We believe this is a paradigm shift from the way document understanding and text classification has been traditionally done, and will drive numerous novel research ideas in the community.
Author

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Mithun Das Gupta (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

1. (comment) 11/11/18 06:07PM

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
11/08/18 06:04PM
5,544
1,839
Tweets
arxiv_pop: 2018/11/08 投稿 5位 CL(Computation and Language) Doc2Im: document to image conversion through self-attentive embedding https://t.co/rTY4LANwKM 23 Tweets 14 Retweets 30 Favorites
StBlMuc: RT @arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
arxiv_cscv: Doc2Im: document to image conversion through self-attentive embedding https://t.co/xYW9funr5s
mdg1208: RT @arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
arxiv_cscl: Doc2Im: document to image conversion through self-attentive embedding https://t.co/F3eFf3W677
Montreal_AI: RT @arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
shubh_300595: RT @arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
arxiv_cscv: Doc2Im: document to image conversion through self-attentive embedding https://t.co/xYW9funr5s
arxiv_cscl: Doc2Im: document to image conversion through self-attentive embedding https://t.co/F3eFf3W677
arxiv_cscv: Doc2Im: document to image conversion through self-attentive embedding https://t.co/xYW9fuF1X0
ceobillionaire: RT @arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
IntuitMachine: RT @arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
kuronekodaisuki: RT @arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
suneelmarthi: RT @arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
arxiv_org: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/8d1JVaonQa https://t.co/ivmxqa4U3A
arxiv_cscv: Doc2Im: document to image conversion through self-attentive embedding https://t.co/xYW9funr5s
arxiv_cscl: Doc2Im: document to image conversion through self-attentive embedding https://t.co/F3eFf3W677
arxiv_cscv: Doc2Im: document to image conversion through self-attentive embedding https://t.co/xYW9funr5s
ComputerPapers: Doc2Im: document to image conversion through self-attentive embedding. https://t.co/3tPgSGDYk8
udoooom: RT @arxiv_cscv: Doc2Im: document to image conversion through self-attentive embedding https://t.co/xYW9funr5s
arxiv_cscl: Doc2Im: document to image conversion through self-attentive embedding https://t.co/F3eFf3W677
arxiv_cscv: Doc2Im: document to image conversion through self-attentive embedding https://t.co/xYW9funr5s
arxivml: "Doc2Im: document to image conversion through self-attentive embedding", Mithun Das Gupta https://t.co/AymyhSa8gf
arxiv_cscl: Doc2Im: document to image conversion through self-attentive embedding https://t.co/F3eFf3W677
arxiv_cscv: Doc2Im: document to image conversion through self-attentive embedding https://t.co/xYW9funr5s
nmfeeds: [O] https://t.co/40YeCHFb2V Doc2Im: document to image conversion through self-attentive embedding. Text classification is ...
nmfeeds: [CV] https://t.co/40YeCHFb2V Doc2Im: document to image conversion through self-attentive embedding. Text classification is...
nmfeeds: [CL] https://t.co/40YeCHFb2V Doc2Im: document to image conversion through self-attentive embedding. Text classification is...
arxiv_cscl: Doc2Im: document to image conversion through self-attentive embedding https://t.co/F3eFf4dGYF
arxiv_cscl: Doc2Im: document to image conversion through self-attentive embedding https://t.co/F3eFf3W677
BrundageBot: Doc2Im: document to image conversion through self-attentive embedding. Mithun Das Gupta https://t.co/33jgNWvduC
Images
Related