本文關(guān)鍵詞：基于深度學(xué)習(xí)技術(shù)的中國傳統(tǒng)詩歌生成方法研究　出處：《中國科學(xué)技術(shù)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 神經(jīng)網(wǎng)絡(luò) 詩歌生成 注意力機(jī)制 規(guī)劃 編碼器-解碼器

【摘要】：中國傳統(tǒng)詩歌是我國古代文化的一項(xiàng)重要的遺產(chǎn)。它有很多不同的類型,例如唐詩和宋詞。每種類型的詩歌都必須遵循特定的結(jié)構(gòu),押韻和平仄。中國傳統(tǒng)詩歌的自動(dòng)生成是自然語言處理領(lǐng)域中一項(xiàng)非常有挑戰(zhàn)性的工作。本文提出了一種基于規(guī)劃的詩歌生成方法:先規(guī)劃詩歌的主題("說什么"),再生成詩歌的具體內(nèi)容("怎么說")。具體來說,給定由關(guān)鍵詞,句子甚至文檔組成的用戶寫作意圖文本,第一步是使用詩歌規(guī)劃模型來決定每句的子主題,即給每句分配一個(gè)主題詞。規(guī)劃模型將用戶的寫作意圖轉(zhuǎn)換成了一個(gè)與主題相關(guān)的子主題序列。詩歌生成模型則基于每一行分配的子主題和之前已經(jīng)生成的內(nèi)容來逐行地進(jìn)行詩歌生成,它在基于注意力機(jī)制的編碼器-解碼器神經(jīng)網(wǎng)絡(luò)模型上做了改進(jìn)以保證可以同時(shí)編碼子主題和之前已經(jīng)生成的內(nèi)容。本文工作的主要貢獻(xiàn)概括如下:·首先,本文嘗試模擬人類的創(chuàng)作過程,將人類創(chuàng)作中的規(guī)劃思想引入到詩歌生成中,提出了一種可以明確規(guī)劃詩歌主題的詩歌生成方法。同時(shí)在基于注意力機(jī)制的編碼器-解碼器神經(jīng)網(wǎng)絡(luò)模型的基礎(chǔ)上做了改進(jìn),使其可以同時(shí)支持編碼詩歌子主題和歷史生成內(nèi)容并逐行進(jìn)行詩歌生成�！て浯�,本文提出了將基于規(guī)劃的詩歌生成模型應(yīng)用到特定詩歌生成任務(wù)的具體方法�！ぷ詈�,本文進(jìn)行了模型評(píng)估實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明本文提出的模型不僅超過目前最好的詩歌生成方法,而且生成的詩歌質(zhì)量在某種程度上可以媲美人類詩人。
[Abstract]:Chinese traditional poetry is an important heritage of ancient Chinese culture. It has many different types, such as Tang poetry and Song ci. Each type of poetry must follow a specific structure. The automatic generation of Chinese traditional poetry is a very challenging task in the field of natural language processing. This paper presents a method of poetry generation based on planning: first planning the theme of poetry (. "say what"). Specifically, given a user's intended text consisting of keywords, sentences, and even documents, the first step is to use the poetry planning model to determine the subthemes of each sentence. The planning model converts the user's writing intention into a subtopic sequence related to the topic. The poetry generation model is based on the subtopic assigned by each line and the previously generated content. To generate poetry line by line. It is improved on the encoder-decoder neural network model based on attention mechanism to ensure that it can encode subtopics and previously generated content simultaneously. The main contributions of this paper are summarized as follows: first of all. This paper attempts to simulate the process of human creation and introduce the planning thought of human creation into poetry generation. This paper proposes a poetry generation method which can clearly plan the theme of poetry, and improves the neural network model of encoder and decoder based on attention mechanism. So that it can support the coding of poetry sub-themes and historical generation of content and poetry generation line by line. This paper proposes a specific method of applying the plan-based poetry generation model to a specific poetry generation task. Finally, this paper carries out a model evaluation experiment. The experimental results show that the model proposed in this paper not only exceeds the best methods of poetry generation, but also has a quality comparable to that of human poets to some extent.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.1;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 周昌樂;游維;丁曉君;;一種宋詞自動(dòng)生成的遺傳算法及其機(jī)器實(shí)現(xiàn)[J];軟件學(xué)報(bào);2010年03期

，

本文編號(hào)：1410912