TAILIEUCHUNG - Báo cáo khoa học: "Conditional Random Fields for Word Hyphenation"

Finding allowable places in words to insert hyphens is an important practical problem. The algorithm that is used most often nowadays has remained essentially unchanged for 25 years. This method is the TEX hyphenation algorithm of Knuth and Liang. We present here a hyphenation method that is clearly more accurate. The new method is an application of conditional random fields. We create new training sets for English and Dutch from the CELEX European lexical resource, and achieve error rates for English of less than for correctly allowed hyphens, and less than for Dutch. . | Conditional Random Fields for Word Hyphenation Nikolaos Trogkanis Computer Science and Engineering University of California San Diego La Jolla California 92093-0404 tronikos@ Charles Elkan Computer Science and Engineering University of California San Diego La Jolla California 92093-0404 elkan@ Abstract Finding allowable places in words to insert hyphens is an important practical problem. The algorithm that is used most often nowadays has remained essentially unchanged for 25 years. This method is the TEX hyphenation algorithm of Knuth and Liang. We present here a hyphenation method that is clearly more accurate. The new method is an application of conditional random fields. We create new training sets for English and Dutch from the CELEX European lexical resource and achieve error rates for English of less than for correctly allowed hyphens and less than for Dutch. Experiments show that both the Knuth Liang method and a leading current commercial alternative have error rates several times higher for both languages. 1 Introduction The task that we investigate is learning to split words into parts that are conventionally agreed to be individual written units. In many languages it is acceptable to separate these units with hyphens but it is not acceptable to split words arbitrarily. Another way of stating the task is that we want to learn to predict for each letter in a word whether or not it is permissible for the letter to be followed by a hyphen. This means that we tag each letter with either 1 for hyphen allowed following this letter or 0 for hyphen not allowed after this letter. The hyphenation task is also called orthographic syllabification Bartlett et al. 2008 . It is an important issue in real-world text processing as described further in Section 2 below. It is also useful as a preprocessing step to improve letter-to-phoneme conversion and more generally for text-to-speech conversion. In the well-known NETtalk system for example .

• Báo cáo khoa học
• Conditional Random Fields
• Word Hyphenation
• Nikolaos Trogkanis
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Using Conditional Random Fields
• Extract Contexts
• Answers of Questions from Online Forums
• xử lý ngôn ngữ tự nhiên
• Generalized Expectation Criteria
• Semi Supervised Learning
• Discriminative Word Alignment
• Phil Blunsom and Trevor Cohn
• mô hình ngôn ngữ
• Semi Supervised Conditional Random Fields
• Improved Sequence Segmentation and Labeling
• Feng Jiao
• Training Conditional Random Fields
• Multivariate Evaluation Measures
• Jun Suzuki
• Erik McDermott and Hideki Isozaki
• Improving the Scalability
• Semi Markov Conditional Random Fields
• Named Entity Recognition
• Sentence Boundary
• Detection In Speech
• Scaling Conditional Random Fields
• Error Correcting Codes
• Trevor Cohn Andrew Smith
• Logarithmic Opinion Pools
• Andrew Smith Trevor Cohn Miles Osborne
• Discriminative Language Modeling
• the Perceptron Algorithm
• Using Conditional Random
• Fields to Predict Pitch
• Accents in Conversational Speech
• Fast Full Parsing
• Linear Chain Conditional Random Fields
• Yoshimasa Tsuruoka
• scientific reports
• model language
• process natural language
• Công cụ gán nhãn từ loại tiếng Việt
• Công cụ gán nhãn
• Công cụ gán nhãn dựa trên Conditional Random Fields
• Công cụ gán nhãn dựa trênMaximum Entropy
• Công cụ được cài đặt trên ngôn ngữ Java
• BMC Bioinformatics
• Parallel coordinates
• Graphical probabilistic models
• Aligning sequences
• Báo cáo sinh học hay
• cách trình bày báo cáo
• báo cáo sinh học
• công trình nghiên cứu sinh học
• tài liệu về sinh học
• Nested named entity recognition
• Feature based model
• B I O encoding scheme
• Word shape features
• Machine translation
• Confidence measure
• Confidence estimation
• Binary estimator
• Protein protein interactions
• Pairwise conditional random fields
• Synthetic scores
• Protein complexes
• Bài giảng Xử lý ngôn ngữ tự nhiên
• Kỹ thuật lập trình
• Gán nhãn từ loại
• Sentiment analysis
• Opinion mining
• Comparative sentences
• Support vector machines