.png){kind=icon}
返回
Controllable Text Generation Using Semantic Control Grammar
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3252017.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Controllable text generation is the primary technique for controlling specific attributes such as topic, keywords and obtaining augmented data. This work proposes a novel controllable text generation framework to improve the controllability of generation models. First, we introduce semantic control grammar, a controllable input format to generate sentences that satisfy the constraints. Second, we adopt a generation and rerank method to obtain semantically reranked controlled sentences. Extensive experiments and analyses are conducted on benchmark, natural language understanding, data-to-text generation, and text classification datasets. Through automatic evaluations, we show that our method leads to improvement over strong baselines. The results show that our model can control sentence and word attributes and semantically generate natural sentences. Furthermore, our techniques improve the generation quality of the model.
Keyword:
Semantics
Grammar
Generators
Decoding
Task analysis
Controllability
Transformers
Test pattern generators
Natural language processing
Controllable text generation
semantic control grammar
natural language generation
deep learning
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
Seawater paleotemperature and paleosalinity evolution in neritic environments of the Mediterranean margin: Insights from isotope analysis of bivalve shells地中海边缘大陆架环境中海水古温度和古盐度演化：来自双壳类贝壳同位素分析的见解
OAAI
OAAI分享收藏Glucocorticoid receptor number and cortisol excretion in mood, anxiety, and psychotic disorders
PREAI
分享收藏
查看更多内容