Text Understanding from Scratch
Xiang Zhang, Yann LeCun

TL;DR
This paper demonstrates that deep temporal convolutional networks can effectively understand text from raw character inputs to abstract concepts across multiple languages and tasks without relying on traditional linguistic structures.
Contribution
It introduces the application of temporal ConvNets for text understanding directly from characters, achieving high performance without linguistic feature engineering.
Findings
ConvNets perform well on large-scale text classification tasks
Models work effectively for both English and Chinese
Achieves high accuracy without syntactic or semantic preprocessing
Abstract
This article demontrates that we can apply deep learning to text understanding from character-level inputs all the way up to abstract text concepts, using temporal convolutional networks (ConvNets). We apply ConvNets to various large-scale datasets, including ontology classification, sentiment analysis, and text categorization. We show that temporal ConvNets can achieve astonishing performance without the knowledge of words, phrases, sentences and any other syntactic or semantic structures with regards to a human language. Evidence shows that our models can work for both English and Chinese.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Advanced Text Analysis Techniques · Sentiment Analysis and Opinion Mining
