Word Representations For Gender Classification Using Deep Learning

Ritesh,; Bhagvati, Chakravarthy

doi:10.1016/j.procs.2018.05.015

Cited by 12 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LSTM: we only use the LSTM model to the QA and use the one-hot representation [46] to assign each word a unique id. This is the baseline of our experiment.…”

Section: E Experimental Results Of Modelsmentioning

confidence: 99%

A Hybrid Network Model for Tibetan Question Answering

Sun

Xia

2019

IEEE Access

View full text Add to dashboard Cite

Currently, research on question answering (QA) with deep learning methods is a hotspot in natural language processing. In addition, most of the research mainly focused on English or Chinese since there are large-scale open corpora, such as WikiQA or DoubanQA. However, how to use deep learning methods to QA of the low resource languages, like Tibetan becomes a challenge. In this paper, we propose a hybrid network model for the Tibetan QA, which combines the convolutional neural network and long short memory network (LSTM) to extract effective features from small-scale corpora. Meanwhile, since the strong grammar rules of Tibetan, we use the language model to decode the output of the LSTM layer which makes the answer more accurate and smoother. In addition, we add the batch normalization to accelerate deep network training and prevent overfitting. Finally, the experiments show that the ACC@1 value of the proposed model in Tibetan QA is 126.2% higher than the baseline model. INDEX TERMS Tibetan question answering, hybrid network, convolutional neural network, long short memory network, language model.

show abstract

“…LSTM: we only use the LSTM model to the QA and use the one-hot representation [46] to assign each word a unique id. This is the baseline of our experiment.…”

Section: E Experimental Results Of Modelsmentioning

confidence: 99%

A Hybrid Network Model for Tibetan Question Answering

Sun

Xia

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Although this accounts for temporal label changes and locale-adaptation, the method remains context-unaware. As an alternative to lookup-based approaches, neural networks trained on gender-labeled names have also been explored (Bhagvati & Bhagvati, 2018;Septiandri, 2017;Wood-Doughty et al, 2018). However, such methods do not incorporate context-sensitivity in any form.…”

Section: Related Workmentioning

confidence: 99%

“…Utilizing the different distributions of names across the genders (Bhagvati & Bhagvati, 2018;Blevins & Mullen, 2015;Santamaría & Mihaljevic, 2018) to label names as feminine, masculine, or "neutral" is the most popular approach. 2 These methods rely on a large database of names along with their corresponding gender labels to perform name-gender inference.…”

Section: Introductionmentioning

confidence: 99%

Gender tagging of named entities using retrieval‐assisted multi‐context aggregation: An unsupervised approach

Das

Paik

2023

Asso for Info Science & Tech

View full text Add to dashboard Cite

Inferring the gender of named entities present in a text has several practical applications in information sciences. Existing approaches toward name gender identification rely exclusively on using the gender distributions from labeled data. In the absence of such labeled data, these methods fail. In this article, we propose a two-stage model that is able to infer the gender of names present in text without requiring explicit name-gender labels. We use coreference resolu-

show abstract

Gendec: A Machine Learning-Based Framework for Gender Detection from Japanese Names

Tien Pham,

Thanh Nguyen

2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Word Representations For Gender Classification Using Deep Learning

Cited by 12 publications

References 13 publications

A Hybrid Network Model for Tibetan Question Answering

A Hybrid Network Model for Tibetan Question Answering

Gender tagging of named entities using retrieval‐assisted multi‐context aggregation: An unsupervised approach

Gendec: A Machine Learning-Based Framework for Gender Detection from Japanese Names

Contact Info

Product

Resources

About