基於非監督式詞義消歧之日語旅遊意見詞翻譯

Japanese Opinion Word Translation Based on Unsupervised Word Sense Disambiguation in the Travel Domain

本論文提出了一個加上特徵詞字典與相依性關係詞的非監督式意見詞翻譯方法，我們的方法包含了在測試階段前的語料庫準備、特徵詞字典產生以及加權方式，不同於當今機器翻譯的方式，不須另外準備平行語料庫、標記語料庫甚至是剖析樹語料庫。本研究僅需一個可信賴的線上雙語字典即可完成，所需成本極小但是效果較現時諸多線上翻譯系統來得準確。此外也可以從評論中擷取出關鍵資訊，幫助使用者更加了解評論之內容。我們設計三種組態，並挑選四個在日語中出現頻率非常高的意見詞進行實驗。由實驗結果顯示，相依性關係與特徵詞字典確實對於意見詞翻譯是有效的，而此種方法除了能解決一字多義現象也能提高準確率，幫助使用者了解日語之意見內容助其進行決策。

This paper proposes a Japanese opinion word translation method based on unsupervised word sense disambiguation. The method comprises the corpus preparation, opinion word dictionary construction, and weighting method. Different from the machine translation, our method does not need parallel corpora, tagged corpora or parsing tree banks. Our method is low-cost but effective, and requires a well-made bilingual dictionary only. Besides, our method can extract key information from the opinions to help users understand the opinions. We construct four configurations and evaluate our method on four Japanese opinion words with high frequency. The evaluation result shows that the dependency grammar and opinion word dictionary is effective on opinion word translation. Our method can deal with the translation disambiguation problem and improve the translation precision to help user realize Japanese opinions.