Báo cáo khoa học: "Feature Lattices for Maximum Entropy Modelling" pot

Báo cáo khoa học: "Feature Lattices for Maximum Entropy Modelling" pot

Báo cáo khoa học: "Feature Lattices for Maximum Entropy Modelling" pot

... the lex- icon information for the words before and after the period, their capitalization and spellings. For training we collected from the WSJ cor- pus 51,000 samples of the form (Y, F F) ... for building maximum entropy models. Our approach uses the feature collocation lattice and builds com- plex candidate features without resorting to it- erative scaling. 1 Introduction...

Ngày tải lên: 23/03/2014, 19:20

7 183 0
Báo cáo khoa học: "Transductive learning for statistical machine translation" potx

Báo cáo khoa học: "Transductive learning for statistical machine translation" potx

... over all possible valid translations t for a particular input sentence s. We can initialize this probability distribution to the uniform distribu- tion for each sentence s in the unlabeled data ... of sentences from U will have the maximum entropy. Under certain precise conditions, as described in (Abney, 2004), we can analyze Algorithm 1 as minimizing the entropy of the distribution...

Ngày tải lên: 08/03/2014, 02:21

8 417 0
Báo cáo khoa học: "Pronunciation Modeling for Improved Spelling Correction" potx

Báo cáo khoa học: "Pronunciation Modeling for Improved Spelling Correction" potx

... presents a method for incor- porating word pronunciation information in a noisy channel model for spelling cor- rection. The proposed method builds an explicit error model for word pronuncia- tions. ... correspond to nothing (i.e., are silent). For example, the entry in NETtalk (when we remove the empties, which contain information for phone level alignment) for the word able is A...

Ngày tải lên: 17/03/2014, 08:20

8 301 0
Báo cáo khoa học: "Domain Adaptation of Maximum Entropy Language Models" potx

Báo cáo khoa học: "Domain Adaptation of Maximum Entropy Language Models" potx

... Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Domain Adaptation of Maximum Entropy Language Models Tanel Alum ¨ ae ∗ Adaptive Informatics Research Centre School of Science ... less adaptation data than in interpolated ME models. 2 Review of Conditional Maximum Entropy Language Models Maximum entropy (ME) modeling is a framework that has been used in...

Ngày tải lên: 23/03/2014, 16:20

6 297 0
Báo cáo khoa học: "Extractive Summaries for Educational Science Content" potx

Báo cáo khoa học: "Extractive Summaries for Educational Science Content" potx

... basis for the construction of knowledge maps useful both as computational knowledge representations and as learning re- sources for presentation to the student. 2 Related Work Our work is informed ... of very fine granularity and therefore graphs that may not be suitable for presentation to a student. Multi-document summarization (MDS) re- search also informs our work. XDoX analy...

Ngày tải lên: 23/03/2014, 17:20

4 196 0
Báo cáo khoa học: "Multi-Tagging for Lexicalized-Grammar Parsing" pot

Báo cáo khoa học: "Multi-Tagging for Lexicalized-Grammar Parsing" pot

... improve performance. However, for grammar formalisms which use more fine-grained grammatical cate- gories, for example TAG and CCG, tagging accuracy is much lower. In fact, for these formalisms, ... of the forward- backward algorithm, for example Manning and Schutze (1999), is usually given for an HMM-style tagger. However, it is straightforward to adapt the algorithm to the Maximum...

Ngày tải lên: 23/03/2014, 18:20

8 321 0
Báo cáo khoa học: "Topic Analysis for Psychiatric Document Retrieval" potx

Báo cáo khoa học: "Topic Analysis for Psychiatric Document Retrieval" potx

... to different suggestions decided by experts. Therefore, an ideal retrieval system for consultation documents should consider such topic information so as to improve the retrieval precision. ... extraction of topic informa- tion is described briefly. The detailed process is described in (Wu et al. 2005a) for symptom and relation identification, and in (Yu et al., 2007) for event id...

Ngày tải lên: 23/03/2014, 18:20

8 338 0
Báo cáo khoa học: "Discourse Cues for Broadcast News Segmentation" potx

Báo cáo khoa học: "Discourse Cues for Broadcast News Segmentation" potx

... Figure 1) or MS-NBC. For example, the structure for the Jim Lehrer News Hour provides not only segmentation information but also content information for each segment. Thus, the order of stories ... content-based information browsing, retrieval, extraction, and summarization to ensure their value for tasks such as real-time profiling and retrospective search. Whereas image proc...

Ngày tải lên: 23/03/2014, 19:20

4 366 0
Báo cáo khoa học: "A Model For Generating Better Explanations" pot

Báo cáo khoa học: "A Model For Generating Better Explanations" pot

... these goals, the information in the model of the user, and on external conditions such as deadlines for changing status in a course. For example purposes, the domain information is read in ... of the simplified domain plan for getting a degree. Consider the first clause of the counts_ .for_ credit predicate. This clause states that a course will count for credit if it is a 500 l...

Ngày tải lên: 24/03/2014, 02:20

6 267 0
Báo cáo khoa học: "Feature-Rich Part-of-speech Tagging for Morphologically Complex Languages: Application to Bulgarian" docx

Báo cáo khoa học: "Feature-Rich Part-of-speech Tagging for Morphologically Complex Languages: Application to Bulgarian" docx

... cardinal numbers, foreign words, existen- tial there, etc., but also to the desire to encode morphological information as part of the tags. For example, there are six tags for verbs in the Penn ... definite article (which has a short and a long form for sin- gular masculine), and lacks verb infinitive forms. It further uses special evidential verb forms to ex- press unwitnessed, retold, a...

Ngày tải lên: 08/03/2014, 21:20

11 493 0
w