Latent semantics in language models

Brychcín, Tomáš; Konopík, Miloslav

doi:10.1016/j.csl.2015.01.004

Cited by 8 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We estimated the n-gram frequencies from Wikipedia. We used the language model from (Brychcín and Konopík, 2015), Stanford CoreNLP for part-of-speech tags (Toutanova et al, 2003), the MIT Java Wordnet Interface (Finlayson, 2014), and the Brainy implementation of maximum entropy classifier (Konkol, 2014).…”

Section: Methodsmentioning

confidence: 99%

UWB at SemEval-2016 Task 11: Exploring Features for Complex Word Identification

Konkol¹

2016

Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

View full text Add to dashboard Cite

In this paper, we present our system developed for the SemEval 2016 Task 11: Complex Word Identification. Our team achieved the 3rd place among 21 participants. Our systems ranked 4th and 13th among 42 submitted systems. We proposed multiple features suitable for complex word identification, evaluated them, and discussed their properties. According to the results of our experiments, our final system used maximum entropy classifier with a single feature-document frequency.

show abstract

Section: Methodsmentioning

confidence: 99%

UWB at SemEval-2016 Task 11: Exploring Features for Complex Word Identification

Konkol¹

2016

Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

View full text Add to dashboard Cite

show abstract

“…Word-based semantic spaces provide impressive performance in a variety of NLP tasks, such as language modeling [2], named entity recognition [14], sentiment analysis [11], and many others.…”

Section: Distributional Semantic Modelsmentioning

confidence: 99%

Enriching Word Embeddings with Global Information and Testing on Highly Inflected Language

Svoboda

Brychcín

2019

CyS

Self Cite

View full text Add to dashboard Cite

In this paper we evaluate our new approach based on the Continuous Bag-of-Words and Skip-gram models enriched with global context information on highly inflected Czech language and compare it with English results. As a source of information we use Wikipedia, where articles are organized in a hierarchy of categories. These categories provide useful topical information about each article. Both models are evaluated on standard word similarity and word analogy datasets. Proposed models outperform other word representation methods when similar size of training data is used. Model provide similar performance especially with methods trained on much larger datasets.

show abstract

“…Similar techniques have been explored for topic identification and dynamic language model adaptation using vector space model [12], LSA [13], relevance language model [14], semi-supervised language models [15] and topic tracking language model [16]. LDA technique has been widely explored to form unsupervised adapted language model [17] and topic-specific language models for inflectional languages [18]. For many languages the linguistic word level approach [19], syntactico-statistical approach [19] and statistic phrase level approach [20] has been used to build an adapted language model for improving the speech recognition rate.…”

Section: Related Workmentioning

confidence: 99%

Efficient Search Mechanism from Large Scale Corpora for Domain-Specific Language Modeling in Speech Recognition

2019

ijeat

View full text Add to dashboard Cite

With the Internet and the World Wide Web revolution, large corpora in variety of forms are germinating ceaselessly that can be manifested as big data. One obligatory area for the usage of such large corpora is language modeling for large vocabulary continuous speech recognition. Language modeling is an indispensable module in speech recognition architecture, which plays a vital role in reducing the search space during the recognition process. Additionally, the language model that is contiguous to the domain of the speech can dwindle the search space and escalate the recognition accuracy. In this paper, an efficient searching mechanism for domain-specific document retrieval from the large corpora has been elucidated using Elasticsearch which is a distributed and an efficient search engine for big data. This assisted us in tuning the language model in accordance with the domain and also by reducing the search time by more than 90% in comparison to conventional search and retrieval mechanism used in our earlier work. A word level and a phrase level retrieval process for creating domain-specific language model has been implemented. The evaluation of the system is performed on the basis of word error rate (WER) and perplexity (PPL) of the speech recognition system. The results shows nearly 10% decrease on WER and a major reduction in the PPL that helped in boosting the performance of the speech recognition process. From the results, it can be consummated that Elasticsearch is an efficient mechanism for domain specific document retrieval from large corpora rather than using topic modeling toolkits

show abstract

Latent semantics in language models

Cited by 8 publications

References 31 publications

UWB at SemEval-2016 Task 11: Exploring Features for Complex Word Identification

UWB at SemEval-2016 Task 11: Exploring Features for Complex Word Identification

Enriching Word Embeddings with Global Information and Testing on Highly Inflected Language

Efficient Search Mechanism from Large Scale Corpora for Domain-Specific Language Modeling in Speech Recognition

Contact Info

Product

Resources

About