.png){kind=icon}
Return
Text Generation From Data With Dynamic Planning
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2021.3129346.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Transcribing structural data into readable text (data-to-text) is a fundamental language generation task. One of its challenges is to plan the input records for text realization. Recent works tackle this problem with a static planner, which performs record planning in advance for text realization. However, they cannot revise plans to cope with unexpected realized text and require golden plans for supervised training. To address these issues, we first propose a model that contains a dynamic planner. It decomposes text generation into two alternately procedures, record planning and text realization. We also devise a novel likelihood-driven training strategy for the planner. This strategy exploits sentence likelihood to select input records, which requires no annotated plan. Besides, we design a metric based on the set similarity to evaluate the quality of predicted plans. We conduct comprehensive experiments on two data-to-text datasets, E2E and EPW. Our best model considerably outperforming previous works on both text metrics and plan metrics. The likelihood-driven strategy also exhibits competitiveness for training the dynamic planner.
Keywords:
Planning
Decoding
Training
Measurement
Vocabulary
Task analysis
Speech processing
Data-to-text
planning
dynamic planner
E2E
EPW
Journal
I
IF:
5.1
Papers:
2.6K
Citations:
1.1W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSaveShareSaveShareSaveShareSave
View more