Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus
Join the channel membership:
https://www.youtube.com/c/AIPursuit/join
Subscribe to the channel:
https://www.youtube.com/c/AIPursuit?sub_confirmation=1
Support and Donation:
Paypal ⇢ https://paypal.me/tayhengee
Patreon ⇢ https://www.patreon.com/hengee
BTC ⇢ bc1q2r7eymlf20576alvcmryn28tgrvxqw5r30cmpu
ETH ⇢ 0x58c4bD4244686F3b4e636EfeBD159258A5513744
Doge ⇢ DSGNbzuS1s6x81ZSbSHHV5uGDxJXePeyKy
Wanted to own BTC, ETH, or even Dogecoin? Kickstart your crypto portfolio with the largest crypto market Binance with my affiliate link:
https://accounts.binance.com/en/register?ref=27700065 Continue to support the channel: https://paypal.me/aipursuit
Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus
NAACL-HLT 2019
Paper: https://arxiv.org/pdf/1903.10671.pdf
Abstract:
Text style transfer rephrases a text from a
source style (e.g., informal) to a target style
(e.g., formal) while keeping its original meaning. Despite the success existing works have
achieved using a parallel corpus for the two
styles, transferring text style has proven significantly more challenging when there is no
parallel training corpus. In this paper, we address this challenge by using a reinforcementlearning-based generator-evaluator architecture. Our generator employs an attentionbased encoder-decoder to transfer a sentence
from the source style to the target style. Our
evaluator is an adversarially trained style discriminator with semantic and syntactic constraints that score the generated sentence for
style, meaning preservation, and fluency. Experimental results on two different style transfer tasks (sentiment transfer and formality
transfer) show that our model outperforms
state-of-the-art approaches. Furthermore, we
perform a manual evaluation that demonstrates
the effectiveness of the proposed method using
subjective metrics of generated text quality.
Видео Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus канала DSAI by Dr. Osbert Tay
https://www.youtube.com/c/AIPursuit/join
Subscribe to the channel:
https://www.youtube.com/c/AIPursuit?sub_confirmation=1
Support and Donation:
Paypal ⇢ https://paypal.me/tayhengee
Patreon ⇢ https://www.patreon.com/hengee
BTC ⇢ bc1q2r7eymlf20576alvcmryn28tgrvxqw5r30cmpu
ETH ⇢ 0x58c4bD4244686F3b4e636EfeBD159258A5513744
Doge ⇢ DSGNbzuS1s6x81ZSbSHHV5uGDxJXePeyKy
Wanted to own BTC, ETH, or even Dogecoin? Kickstart your crypto portfolio with the largest crypto market Binance with my affiliate link:
https://accounts.binance.com/en/register?ref=27700065 Continue to support the channel: https://paypal.me/aipursuit
Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus
NAACL-HLT 2019
Paper: https://arxiv.org/pdf/1903.10671.pdf
Abstract:
Text style transfer rephrases a text from a
source style (e.g., informal) to a target style
(e.g., formal) while keeping its original meaning. Despite the success existing works have
achieved using a parallel corpus for the two
styles, transferring text style has proven significantly more challenging when there is no
parallel training corpus. In this paper, we address this challenge by using a reinforcementlearning-based generator-evaluator architecture. Our generator employs an attentionbased encoder-decoder to transfer a sentence
from the source style to the target style. Our
evaluator is an adversarially trained style discriminator with semantic and syntactic constraints that score the generated sentence for
style, meaning preservation, and fluency. Experimental results on two different style transfer tasks (sentiment transfer and formality
transfer) show that our model outperforms
state-of-the-art approaches. Furthermore, we
perform a manual evaluation that demonstrates
the effectiveness of the proposed method using
subjective metrics of generated text quality.
Видео Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus канала DSAI by Dr. Osbert Tay
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Knowledge Enhanced Contextual Word Representations | EMNLP-IJCNLP2019
NYU Deep Learning Week 14 – Lecture: Structured prediction with energy-based models | Yann LeCun
Yoshua Bengio | Meta-transfer Learning | ICLR 2019
Towards an Understanding of Wide, Deep Neural Networks | NeurIPS 2019 | Yasaman Bahri
Continuous Optimization for Structure Learning | NeurIPS 2018
Reinforcement Learning: Past, Present, and Future Perspectives (w/ slides) | NeurIPS 2019
3D | Deep Learning for 3D Vision
Graph Neural Network | Tutorial on Graph-based Deep Learning in NLP | Part 2
ICLR 2020 | Yoshua Bengio, Yann LeCun Reflections (Self-Supervised Learning)
NLP | Text Data Augmentation with PyTorch datasets
NeurIPS 2019 Track 1 Session 4
Yoshua Bengio: Deep Learning Priors Associated With Conscious Processing | ICLR 2020
Causal Inference and Stable Learning by Peng Cui
Convolutional Neural Networks (CNN) What & How it works - Brandon Rohrer
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | NAACL BEST PAPERS
Deep Learning with Label Noise | Kevin McGuinness
NYU Deep Learning Week 13 – Practicum: Graph Convolutional Networks (GCNs)
Social Intelligence | Blaise Aguera y Arcas | NeurIPS 2019
Graph Neural Network | Tutorial on Benchmarking GNN by Xavier Bresson & Yoshua Bengio
ICLR 2020 | Q & A w/ Yoshua Bengio, Yann LeCun Reflections ft. Dawn Song