• No results found

[PDF] Top 20 Compound Embedding Features for Semi supervised Learning

Has 10000 "Compound Embedding Features for Semi supervised Learning" found on our website. Below are the top 20 most common "Compound Embedding Features for Semi supervised Learning".

Compound Embedding Features for Semi supervised Learning

Compound Embedding Features for Semi supervised Learning

... pound features on NER is that they made linear models better separate named entities (NEs) and non-NEs, which are more difficult to be linearly separated when embeddings are directly used as ...as features, ... See full document

6

Semi supervised Speech Act Recognition in Emails and Forums

Semi supervised Speech Act Recognition in Emails and Forums

... investigated semi-supervised speech act recognition in email and forum ...of learning to recognize speech acts us- ing labeled and unlabeled ...that semi-supervised learning of ... See full document

10

Learning New Semi Supervised Deep Auto encoder Features for Statistical Machine Translation

Learning New Semi Supervised Deep Auto encoder Features for Statistical Machine Translation

... original features, has been proved as a feasible feature gen- eration approach for ...feature learning than shal- low models like ...non-parametric features, which has the sim- ilar evolution in ... See full document

11

Extractive Summarization Using Supervised and Semi Supervised Learning

Extractive Summarization Using Supervised and Semi Supervised Learning

... Traditionally, features for summarization were studied separately. Radev et al. (2004) reported that position and length are useful surface fea- tures. They observed that sentences located at the document head ... See full document

8

Semi supervised Multitask Learning for Sequence Labeling

Semi supervised Multitask Learning for Sequence Labeling

... to learn more general language features from the available text. In many sequence labeling tasks, the relevant labels in the dataset are very sparse and most of the words contribute very little to the training ... See full document

10

Semi-described and semi-supervised learning with Gaussian processes

Semi-described and semi-supervised learning with Gaussian processes

... a semi- supervised GP framework where features are extracted from all available information and, subsequently, are given as inputs to a discriminative ... See full document

11

Semi supervised tensor based graph embedding learning and its application to visual discriminant tracking

Semi supervised tensor based graph embedding learning and its application to visual discriminant tracking

... transfer-learning-based semi-supervised improvement in an iterative ...discriminative embedding space into which the information about the earlier changes in object appearance is ...learned ... See full document

31

A Review on health care examination records using data mining

A Review on health care examination records using data mining

... by Semi Supervised Learning. Semi-Supervised Learning is a situation in which in your training data some of the samples are not ...The semi-supervised estimators ... See full document

5

Protein complex detection with semi-supervised learning in protein interaction networks

Protein complex detection with semi-supervised learning in protein interaction networks

... While the existing methods identify protein complexes with strong assumptions about their topology (dense subgraph), our proposed method utilizes multiple fea- tures that define protein complexes in protein-protein ... See full document

9

Semi Supervised Learning of Concatenative Morphology

Semi Supervised Learning of Concatenative Morphology

... Morphological analysis is required in many natu- ral language processing problems. Especially, in agglutinative and compounding languages, where each word form consists of a combination of stems and affixes, the number ... See full document

9

Semi Supervised Learning for Relation Extraction

Semi Supervised Learning for Relation Extraction

... evaluation, we have adopted a state-of-the-art lin- ear kernel as similarity measurements. In our linear kernel, we apply the same feature set as described in a state-of-the-art feature-based system (Zhou et al 2005): ... See full document

8

Towards Automated Semi-Supervised Learning

Towards Automated Semi-Supervised Learning

... phenomenon is crucial for SSL and needs to be alleviated in automated SSL. Recently, a scheme termed safe SSL (Li and Zhou 2015) has been presented to alleviate the per- formance deterioration issue in SSL. They are ... See full document

8

Semi supervised learning of morphological paradigms and lexicons

Semi supervised learning of morphological paradigms and lexicons

... In the next step we ranked all nouns in SALDO (79.6k lemmas) according to our confidence score, which indicates how well a noun fits a given paradigm. We then evaluated the paradigm assign- ment for the top-1000 lemmas. ... See full document

10

Grouping Product Features Using Semi Supervised Learning with Soft Constraints

Grouping Product Features Using Semi Supervised Learning with Soft Constraints

... thesaurus dictionaries can help to some extent, they are far from sufficient due to a few reasons. First, many words and phrases that are not syn- onyms in a dictionary may refer to the same fea- ture in an application ... See full document

9

Semi Supervised Noun Compound Analysis with Edge and Span Features

Semi Supervised Noun Compound Analysis with Edge and Span Features

... The phrase structure grammars dominated English parsing research for a long time although dependency parsing has seen rapid progress in the last decade. The most influential annotated corpus for the phrase structure ... See full document

18

Revisiting Embedding Features for Simple Semi supervised Learning

Revisiting Embedding Features for Simple Semi supervised Learning

... proposed embedding features have stronger abil- ity for handling rare words, we first conduct anal- ysis for the tagging errors of words with differ- ent frequency in the unlabeled ...three embedding ... See full document

11

End-user feature labeling: Supervised and semi-supervised approaches based on locally-weighted logistic regression

End-user feature labeling: Supervised and semi-supervised approaches based on locally-weighted logistic regression

... these features, such as stopwords and punctuation, had previously been removed from the vocabulary but were partially reintroduced by ...participants. Features such as multiple word phrases (n-grams) and ... See full document

38

Three phase training to address data sparsity in Neural Machine Translation

Three phase training to address data sparsity in Neural Machine Translation

... Data sparsity is a challenging problem in NMT, especially for resource-scarce language pairs. In this paper, we proposed an inte- grated approach to reduce the impact of data sparsity in NMT, using only little amount of ... See full document

10

Semi-Supervised Learning with Measure Propagation

Semi-Supervised Learning with Measure Propagation

... Label Priors: This is more akin to the classical integration of priors within a Bayesian learn- ing setting. There has been some work in the past directed towards integrating priors for para- metric (non-graph-based) SSL ... See full document

60

Large Margin Semi-supervised Learning

Large Margin Semi-supervised Learning

... as semi-supervised learning, which differs from a conventional “missing data” problem in that the size of unlabeled data greatly exceeds that of labeled data, and missing occurs only in ...In ... See full document

25

Show all 10000 documents...