• No results found

n-gram language modeling

Show Some Love to Your n grams: A Bit of Progress and Stronger n gram Language Modeling Baselines

Show Some Love to Your n grams: A Bit of Progress and Stronger n gram Language Modeling Baselines

... As our main large-scale experiment we use a typo- logically diverse set of 50 languages. These LM datasets cover many languages which are challeng- ing in terms of data size, as well as the type-token ratio. In a less ...

6

Language Modeling with Power Low Rank Ensembles

Language Modeling with Power Low Rank Ensembles

... for n-gram language modeling where ensembles of low rank matrices and tensors are used to obtain smoothed probability estimates of words in ...of n- gram modeling to ...

12

Incorporation of WordNet Features to n-gram Features in a Language Modeler

Incorporation of WordNet Features to n-gram Features in a Language Modeler

... Abstract. n-gram language modeling is a popular technique used to improve performance of various NLP ...trigram language modeler has been developed to address this ...English ...

10

Language Identification of Short Text Segments with N-gram Models

Language Identification of Short Text Segments with N-gram Models

... an n-gram model grows rapidly with increasing n and training corpus ...exclude n-grams that occur fewer times than a given cut-off count. The n-grams that contribute only little to the ...

8

Auto Sizing Neural Networks: With Applications to n gram Language Models

Auto Sizing Neural Networks: With Applications to n gram Language Models

... for language modeling for a long ...character n-gram model using neural networks which they used for text ...word n-gram model and demonstrated improvements over con- ventional ...

9

Modeling unstructured document using N gram consecutive and wordnet dictionary

Modeling unstructured document using N gram consecutive and wordnet dictionary

... and N-gram by Kathleen [15] is about to improve performance of various NLP applications with the combination of WordNet and ...one language modeler been developed by generating proxy trigrams using ...

10

Modeling of term distance and term occurrence information for improving n gram language model performance

Modeling of term distance and term occurrence information for improving n gram language model performance

... used n -gram model (Bahl et ...Although n -gram models are simple and effective, modeling long history-contexts lead to severe data scarcity ...

5

A Challenge Set for Advancing Language Modeling

A Challenge Set for Advancing Language Modeling

... an N-gram language model to do this rank- ...weight. N-gram statistics were also very effective - according to one of the scoring paradigms - in (Giu- liano et ...that ...

8

N gram and Neural Language Models for Discriminating Similar Languages

N gram and Neural Language Models for Discriminating Similar Languages

... statistical language identification has received much attention in Natural Language ...character n-gram modeling has traditionally been very success- ful for this application (Cavnar ...

8

Sampling Informative Training Data for RNN Language Models

Sampling Informative Training Data for RNN Language Models

... statistical language modeling seeks to learn a joint probability distribution over se- quences of natural language ...(RNN) language models (Mikolov et ...sentence-level language ...

5

Character n-Gram Embeddings to Improve RNN Language Models

Character n-Gram Embeddings to Improve RNN Language Models

... (RNN) language model that takes advantage of character ...character n-grams based on research in the field of word embedding construction (Wieting et ...character n- gram embeddings and ...

9

A study of N gram and Embedding Representations for Native Language Identification

A study of N gram and Embedding Representations for Native Language Identification

... The last few years saw the field of NLI advance in both the directions of feature engineering and modeling. However, irrespective of what model- ing choices were made, results seem to show that word level features ...

9

An Empirical Comparison Between N gram and Syntactic Language Models for Word Ordering

An Empirical Comparison Between N gram and Syntactic Language Models for Word Ordering

... and N-gram language mod- els on the task of word ordering (Wan et ...a gram- matical and fluent ...abstract language modeling problem, although methods have been explored ...

10

Grammatical Machine Translation

Grammatical Machine Translation

... on n- gram based automatic evaluation scores (Papineni et ...parsing-based language modeling can im- prove grammaticality of translations, even if these improvements are not recorded under ...

8

A Hybrid Approach to Adaptive Statistical Language Modeling

A Hybrid Approach to Adaptive Statistical Language Modeling

... A HYBRID APPROACH TO ADAPTIVE STATISTICAL LANGUAGE MODELING A HYBRID APPROACH TO ADAPTIVE STATISTICAL LANGUAGE MODELING Ronald Rosenfeld School of Computer Science C a r n e g i e M e l l o n U n i v[.] ...

6

Beyond N Grams: Can Linguistic Sophistication Improve Language Modeling?

Beyond N Grams: Can Linguistic Sophistication Improve Language Modeling?

... Beyond N Grams Can Linguistic Sophistication Improve Language Modeling? Beyond N Grams Can Linguistic Sophistication Improve Language Modeling? Eric Brill, R a d u F l o r i a n , J o h n C H e n d e[.] ...

5

Mining Search Engine Clickthrough Log for Matching N gram Features

Mining Search Engine Clickthrough Log for Matching N gram Features

... query n-grams can be correlated with sequences of URL ...ral Language Processing (NLP) technique of us- ing n-grams to deal with unseen ...using n-gram substrings, novel items can be ...

10

Subsegmental language detection in Celtic language text

Subsegmental language detection in Celtic language text

... character language models using IRSTLM (Federico et ...character language model we replaced spaces with the underscore symbol ‘ ’, and then placed a space character between each ...‘i n’, ‘n ...

5

HIVEC: A Hierarchical Approach for Vector Representation Learning of Graphs

HIVEC: A Hierarchical Approach for Vector Representation Learning of Graphs

... There have been plenty of research done in this domain. The pioneer work in this area is DeepWalk by Perrozi et.al. [1] in their work on learning latent vector representations of vertices in graphs. Their work is ...

7

Neural Network Based Bilingual Language Model Growing for Statistical Machine Translation

Neural Network Based Bilingual Language Model Growing for Statistical Machine Translation

... adding n-grams selected by different criteria from a monolingual corpus (Ristad and Thomas, 1995; Niesler and Woodland, 1996; Siu and Ostendorf, 2000; Si- ivola et ...

7

Show all 10000 documents...

Related subjects