Abstract | ||
---|---|---|
We present a formal language with expressions denoting general symbol structures and queries which access information in those structures. A sequence-to-sequence network processing this language learns to encode symbol structures and query them. The learned representation (approximately) shares a simple linearity property with theoretical techniques for performing this task. |
Year | Venue | Field |
---|---|---|
2018 | ICLR | ENCODE,Formal language,Expression (mathematics),Computer science,Symbol,Artificial intelligence,Natural language processing,Network processing,Machine learning,Encoding (memory) |
DocType | Volume | Citations |
Journal | abs/1803.03834 | 0 |
PageRank | References | Authors |
0.34 | 5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Roland Fernandez | 1 | 198 | 10.08 |
Asli Çelikyilmaz | 2 | 407 | 39.06 |
Rishabh Singh | 3 | 684 | 48.19 |
Paul Smolensky | 4 | 215 | 93.76 |