Multimedia-text team report_2015-07-31
?Download as PPTX, PDF?
1 like?461 views
The document discusses techniques for extracting information from Chinese language documents, including named entity recognition and relation extraction. It describes using conditional random fields to recognize named entities and recursive neural networks to identify relationships between entities by representing words as vectors and modeling the context using matrices. Future work could involve extracting information across multiple sentences, documents, and languages.
Multimedia-text team report_2015-07-31
- 1. MM text team 蔡捷恩 莊文立 溫鈺瑋 2015@Delta Research Center
- 2. Fully automatic F/T matrix analysis from patent data 蔡捷恩
- 3. Function/Technology MatrixUsing keyword “ ” “The Patent-Classification Technology/Function Matrix - A Systematic Method for Design Around”, Cheng et al. Mar-2013, CSIR
- 4. Problem reduce ? detecting problem/solution pairs in a patent document “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 5. Problem term detection ? Step1. finding key frames ? Step2. feature extraction – Unsupervised feature – Supervised feature ? Step3. classifier training “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 6. Step1. key frames detection ? We define key frames to be “ ” “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 7. Step2 – unsupervised feature (language model) ? The model: Maximize likelihood evaluation(MLE) “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 8. Step2 – supervised feature (linguistic model) ? By part-of-speech(POS) statistic on labeled patents “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 9. Step2 – supervised feature (linguistic model) ? The model: Delta function = 1 only when the current key frame matches the given pattern “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 10. Step3. classifier training ? Simply concatenate the features mention above => LIBSVM “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 11. Solution term detection ? Step1. key frame detection ? Step2. feature extraction – Unsupervised feature – Supervised feature: based on problem terms ? Step3. classifier training “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 12. Problems ? Lacked of labeled data? => the linguistic model proposed in the paper seems general enough => believe it directly with porter stemming “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 13. Further improvement ? Coreference resolution – “the method solves the problem of overfitting.” ? Semantic based clustering – Okapi BM25 ”The Probabilistic Relevance Framework: BM25 and Beyond”, Robertson et al., 2009 – Word vector “Efficient Estimation of Word Representations in Vector Space” T. Mikolov, ICLR, 2013. – Document vector “Distributed Representations of Words and Phrases and their Compositionality”,NIPS, 2013. In my opinion: okapi > word vector > document vector “Automatic Discovery of Technology Trends from Patent”, Y. Kim et al. 2009, ACMSAC
- 14. Thank you
- 15. 中文領域術語提取 溫鈺瑋
- 16. 範例 ×目前 此車 铣 設備 由 绮 發 機械 提供 ?目前 此 車铣 設備 由 绮發機械 提供 ×L 固定 板會 有 擺動 過大 疑慮 ?L固定板 會 有 擺動 過大 疑慮
- 17. 方法 ? Collocation – 利用Mutual information (簡稱MI) 得知「字跟字」及 「詞跟字」搭配成詞的機率, 詞的內部結合強度 – 例: c = “自然語言處理”, a = “自然語言處” b = “然語言處理”
- 18. 方法 ? Adaptation 目前 此車 铣 設備 由 绮 發 機械 提供 b e b e s b e s s s b e b e 目前此車铣設備由绮發機械提供 CKIP, stanford, jieba… 手動調整 目前 此 車铣 設備 由 绮發機械 提供 b e s b e b e s b m m e b e CRF-based DELTA word segmentor Input : L 固定 板會 有 擺動 過大 疑慮 Output : L固定板 會 有 擺動 過大 疑慮
- 19. Thank you
- 20. 台達資料的知識萃取 莊文立
- 21. Information Extraction ? Named Entity Recognition (NER) – 專有名詞的辨識和分類 ? 公司、人物、產品、地點…等等 ? Relation Extraction (RE) – 從文字裡找出named entities之間的關係，例如 ? 競爭 ? 合作 ? 客戶 ? 上游廠商 – 通常用(subject,relation,object)三元組來表示
- 22. SALES拜訪記錄： 對於BV3418專案價格的了解，欣特協寶姚經理給出的回應是，周總 認為，台達的價格比西門子808低階機種NC控制器的價格高。 ? NER ? 西門子/Organization ? 欣特協寶/Organization ? 台達/Organization ? 姚經理/Person ? 周總/Person ? RE # Subject Relation Object 1 台達 COMPETE_WITH 西門子 2 台達 IS_VENDOR 欣特協寶 3 西門子 IS_VENDOR 欣特協寶 4 欣特協寶 SUBORDINATE 姚經理 5 欣特協寶 SUBORDINATE 周總
- 23. Named Entity Recognition ? 資料處理 – 中文需要良好的斷詞結果 – 人工標記 ? 模型： Conditional Random Fields (CRF) – 從每個字的特徵裡，學習專有名詞使用的規律 ? 本身的詞、詞性 ? 上下文的詞、詞性 ? 文法剖析樹 ? 搭配用法 ? 稱謂、姓氏 ? 專有名詞資料庫
- 24. Relation Extraction ? 還是需要人工標記 ? ? Deep Learning! – 讓機器自己發現最適合的表達方法 ? Recursive Neural Network – 順著文法剖析樹往上”爬” – 每個字用 矩陣 +向量 表示 ? 向量表示本身詞義 ? 矩陣表示上下文資訊 – 兩個named entity交會處輸出的向量，放入分類器 1 ?3 4 ? 5 ● ● ●● ●●
- 26. Future work ? Cross sentence ? Cross document ? Cross language
- 27. Thank you