DC 欄位 |
值 |
語言 |
DC.contributor | 軟體工程研究所 | zh_TW |
DC.creator | 莊家閔 | zh_TW |
DC.creator | Chia-Min Chuang | en_US |
dc.date.accessioned | 2020-7-31T07:39:07Z | |
dc.date.available | 2020-7-31T07:39:07Z | |
dc.date.issued | 2020 | |
dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=107525009 | |
dc.contributor.department | 軟體工程研究所 | zh_TW |
DC.description | 國立中央大學 | zh_TW |
DC.description | National Central University | en_US |
dc.description.abstract | 跨語言文本摘要是透過機器將一種語言的文章轉換成另
一種語言的摘要,先前的研究大多將該任務以兩步驟方法處
理──「先翻譯後摘要」或「先摘要後翻譯」。但是,這兩
種方法皆會有翻譯錯誤的問題,且其中的機器翻譯模型難以
隨著摘要任務繼續更新微調(fine-tune)。針對上述問題,
我們採用預訓練跨語言編碼器以向量表示(represent)不同
語言的輸入,將其映射至相同的向量空間。預訓練方法已被
廣泛應用在各種自然語言生成任務中,並取得優異的模型表
現。此編碼器使得模型在學習摘要能力的過程中,同時保有
跨語言能力。本研究中,我們實驗三種不同的微調方法,
證明預訓練跨語言編碼器可以學習單詞階層(word-level)
的語意特徵。在我們所有的模型組態裡,最優異的模型可
在ROUGE-1分數上,超越基準模型3分。 | zh_TW |
dc.description.abstract | Cross-lingual text summarization (CLTS) is the task to generate a summary in one language given a document in a another language. Most of the previous work consider CLTS as two sub-tasks: translate-then-summarize and summarize-then-translate. Both of them are suffered from translation error and the translation system is hard to be fine-tuned with text summarization directly. To
deal with the above problems, we utilize a pretrained cross-lingual encoder, which has been demonstrated the effectiveness in natural language generation, to represent text inputs from from different languages. We augment a standard sequence-to-sequence (Seq2Seq) network with our pretrained cross-lingual encoder so as to capture cross-lingual contextualized word representation. We show that the pretrained cross-lingual encoder can be fine-tuned on a text summarization dataset while keeping the cross-lingual ability. We experiment three different fine-tune strategies and show that the pretrained encoder can capture cross-lingual semantic features. The best of the proposed models obtains 42.08 Rouge-1 on ZH2ENSUM datasets [Zhu et al., 2019], significantly improving
our baseline model by more than 3 Rouge-1. | en_US |
DC.subject | 文本摘要 | zh_TW |
DC.subject | 預訓練模型 | zh_TW |
DC.subject | 跨語言處理 | zh_TW |
DC.subject | Summarization | en_US |
DC.subject | Pretraining language model | en_US |
DC.subject | Cross-lingual | en_US |
DC.title | 使用預訓練編碼器提升跨語言摘要能力 | zh_TW |
dc.language.iso | zh-TW | zh-TW |
DC.title | Improving Cross-Lingual Text Summarization using Pretrained Encoder | en_US |
DC.type | 博碩士論文 | zh_TW |
DC.type | thesis | en_US |
DC.publisher | National Central University | en_US |