Learning to Select, Track, and Generate for Data-to-Text
| Autor: | Tatsuya Ishigaki, Eiji Aramaki, Hiroshi Noji, Yui Uehara, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura, Hayate Iso, Ichiro Kobayashi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Computer science Track (disk drive) Writing process Realization (linguistics) 02 engineering and technology Tracking (particle physics) computer.software_genre 03 medical and health sciences 0302 clinical medicine 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing State (computer science) Data mining computer Computation and Language (cs.CL) |
| Zdroj: | Scopus-Elsevier |
| DOI: | 10.48550/arxiv.1907.09699 |
| Popis: | We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. Our model is considered to simulate the human-like writing process that gradually selects the information by determining the intermediate variables while writing the summary. In addition, we also explore the effectiveness of the writer information for generation. Experimental results show that our model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization. Comment: ACL 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|