以遠程監督式學習從中文文本進行關係自動擷取

Simple item page
dc.contributor柯佳伶zh_TW
dc.contributorKoh, Jia-Lingen_US
dc.contributor.author江明潔zh_TW
dc.contributor.authorChiang, Ming-Chiehen_US
dc.date.accessioned2020-12-14T09:07:57Z
dc.date.available2020-01-09
dc.date.available2020-12-14T09:07:57Z
dc.date.issued2020
dc.description.abstract本論文研究從中文文本進行關係擷取，以類神經網路架構為基礎，採用遠程監督式學習的概念，預測文本句子中是否具有特定關係，並擷取出句子中具有此特定關係的實體詞配對。本論文將詞嵌入向量和詞性嵌入向量作為模型輸入特徵，分別訓練關係偵測模型和鑑別模型，前者使用具有時序性的雙向長短期記憶網路模型，用來預測文本句子中是否具有特定關係，並在模型中使用多維注意力機制，針對符合某特定關係的句子們找出句子中相對重要的字作為候選實體詞；後者使用實體詞配對之向量差，利用鑑別模型輸出該實體詞配對是否具有某特定關係。經過上述兩個模型得到的結果，透過回饋學習機制，增加關係偵測模型的訓練資料，並調整關係偵測模型的訓練參數以提升關係分類效果。zh_TW
dc.description.abstractIn this paper, we study the problem of relation extraction from a Chinese corpus through distant-supervised learning. We constructed two models based on the recurrent neural networks to solve the problem. The two models use the word embedding and POS embedding as inputs. The first one is the relation detection model, which detects the relation of a sentence and selects the candidate entity words with multi-level structured (2-D matrix) attention mechanism. The candidate entity words will be combined to be entity pairs, which are inputted to the discriminative model. The second one is the discriminative model, which uses the vector difference of an entity pair to determine if an entity pair satisfies a relation. The results of the discriminative model can find more entity pairs of relations. These pairs can be used as additional training data of the relation detection model to improve the performance of the relation detection model through the feedback for learning.en_US
dc.description.sponsorship資訊工程學系zh_TW
dc.identifierG060647022S
dc.identifier.urihttp://etds.lib.ntnu.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=id=%22G060647022S%22.&
dc.identifier.urihttp://rportal.lib.ntnu.edu.tw:80/handle/20.500.12235/111706
dc.language中文
dc.subject關係擷取zh_TW
dc.subject雙向長短期記憶模型zh_TW
dc.subject多維注意力機制zh_TW
dc.subject回饋學習機制zh_TW
dc.subjectrelation extractionen_US
dc.subjectbi-LSTM modelen_US
dc.subjectmulti-level structured attentionen_US
dc.subjectfeedback for learningen_US
dc.title以遠程監督式學習從中文文本進行關係自動擷取zh_TW
dc.titleAutomatic Relation Extraction from a Chinese Corpus through Distant-supervised Learningen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
060647022s01.pdf
Size:
2.18 MB
Format:
Adobe Portable Document Format
Download

Collections

學位論文