Learning class-specific word embeddings

Kuang, Sicong; Davison, Brian D.

doi:10.1007/s11227-019-03024-z

Cited by 11 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The class-specific vector representation of word [7] in corpus is another popular work for text classifying. The modified version of skip-gram model and continuous bag of word (CBOW) model has been proposed for generating class vectors.…”

Section: Related Workmentioning

confidence: 99%

“…The earliest version of model represents a word with single vector, which is not sufficient to address polysemy obstacle in text classification. In the proposed approach, modified skip gram model [7] is used to update context vectors of word using its class-specific embedding, it's architecture is given in Figure 1. The updated objective function for modified skip gram model is given in Equation 1.…”

Section: Related Workmentioning

confidence: 99%

“…Sicong et al [7] has proposed an idea to encapsulate class information into a vector to represent a class. This technique has proved successful in overcoming drawbacks of commonly used context and multiple sense embeddings.…”

Section: Introductionmentioning

confidence: 99%

“…Secondly, approach is class label dependent, means based on meaning of class label. This paper has introduced an approach that overcome the drawback of work mention in [7] and other commonly used techniques. Our approach has generated improved class vectors those are independent of class labels and also aim to classify multi-class categorized datasets.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning Improved Class Vector for Multi-Class Question Type Classification

Gupta¹,

Kumar²

2021

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

Recent research in NLP has exploited word embedding to achieve outstanding results in various tasks such as; spam filtering, text classification and summarization and others. Present word embedding algorithms have power to capture semantic and syntactic knowledge about word, but not enough to portray the distinct meaning of polysemy word. Many work has utilized sense embeddings to integrate all possible meaning to word vector, which is computationally expensive. Context embedding is another way out to identify word's actual meaning, but it is hard to enumerate every context with a small size dataset. This paper has proposed a methodology to generate improved class-specific word vector that enhance the distinctive property of word in a class to tackle light polysemy problem in question classification. The proposed approach is compared with baseline approaches, tested using deep learning models upon TREC, Kaggle and Yahoo questions datasets and respectively attain 93.6%, 91.8% and 89.2% accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning Improved Class Vector for Multi-Class Question Type Classification

Gupta¹,

Kumar²

2021

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

show abstract

“…Having large annotated datasets, one can then train separate word embedding models for each class or learn models that incorporate class distributions in them. This has been achieved in different methods by combining multiple neural networks [14,15,[24][25][26] or by using separate training processes [31] to train different word embedding models for each class in the dataset. This however requires availability of very large collections of labelled data to train separate models, which is possible for classification tasks exploiting distant supervision for data collection, as is the case with sentiment analysis.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Class Labels to Boost Performance on Embedding-based Text Classification

Zubiaga

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Text classification is one of the most frequent tasks for processing textual data, facilitating among others research from large-scale datasets. Embeddings of different kinds have recently become the de facto standard as features used for text classification. These embeddings have the capacity to capture meanings of words inferred from occurrences in large external collections. While they are built out of external collections, they are unaware of the distributional characteristics of words in the classification dataset at hand, including most importantly the distribution of words across classes in training data. To make the most of these embeddings as features and to boost the performance of classifiers using them, we introduce a weighting scheme, Term Frequency-Category Ratio (TF-CR), which can weight high-frequency, category-exclusive words higher when computing word embeddings. Our experiments on eight datasets show the effectiveness of TF-CR, leading to improved performance scores over the well-known weighting schemes TF-IDF and KLD as well as over the absence of a weighting scheme in most cases. CCS CONCEPTS • Information systems → Clustering and classification; • Computing methodologies → Knowledge representation and reasoning; Natural language processing.

show abstract

A non-sequential refinement approach to improve word embeddings using GPU-based string matching algorithms

Naderalvojoud

Özsoy

2021

Cluster Comput

View full text Add to dashboard Cite

Learning class-specific word embeddings

Cited by 11 publications

References 20 publications

Learning Improved Class Vector for Multi-Class Question Type Classification

Learning Improved Class Vector for Multi-Class Question Type Classification

Exploiting Class Labels to Boost Performance on Embedding-based Text Classification

A non-sequential refinement approach to improve word embeddings using GPU-based string matching algorithms

Contact Info

Product

Resources

About