图 书 馆
诗歌机器：孟加拉语诗歌自动生成的计算创造力Poetic Machine: Computational Creativity for Automatic Poetry Generation in Bengali |
|
| 课程网址: | http://videolectures.net/iccc2014_gamback_poetic_machine/ |
| 主讲教师: | Björn Gambäck |
| 开课单位: | 挪威科技大学 |
| 开课时间: | 2014-04-08 |
| 课程语种: | 英语 |
| 中文简介: |  本文报道了孟加拉语的计算机诗歌生成的初步研究。孟加拉语是一种语法丰富的词法语言，部分音素。诗歌生成任务已被定义为基于用户输入的后续节奏序列生成。设计过程包括从给定的输入中了解节奏，并通过音节/语音映射和自然语言生成技术来跟踪韵律生成。为了理解给定的输入音韵，已经开发了基于音素到音素映射的音节化引擎。然后，基于支持向量机的分类器预测生成的后续音节/语音模式，并根据音节模式自动选择候选单词。通过与基于权重的聚合的n gram匹配，生成最终的有节奏的诗意跟进句子。根据诗意，语法和意义三个标准对自动生成的韵律的质量进行了评估。 |
| 课程简介: | The paper reports an initial study on computational poetry generation for Bengali. Bengali is a morpho-syntactically rich language and partially phonemic. The poetry generation task has been defined as a follow-up rhythmic sequence generation based on user input. The design process involves rhythm understanding from the given input and follow-up rhyme generation by leveraging syllable/phonetic mapping and natural language generation techniques. A syllabification engine based on grapheme-to-phoneme mapping has been developed in order to understand the given input rhyme. A Support Vector Machine-based classifier then predicts the follow-up syllable/phonetic pattern for the generation and candidate words are chosen automatically, based on the syllable pattern. The final rhythmic poetical follow-up sentence is generated through n-gram matching with weight-based aggregation. The quality of the automatically generated rhymes has been evaluated according to three criteria: poeticness, grammaticality, and meaningfulness. |
| 关 键 词: | 自然语言; 孟加拉语 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-04-21：zyk |
| 最后编审: | 2021-04-21：zyk |
| 阅读次数: | 42 |