AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We present Emb2Emb, a framework that reduces conditional text generation tasks to learning in the embedding space of a pretrained autoencoder

Plug and Play Autoencoders for Conditional Text Generation

EMNLP 2020, pp.6076-6092, (2020)

Cited by: 0|Views381
Full Text
Bibtex
Weibo

Abstract

Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only require learning a mapping within the autoencoder’s embedding space, training embedding-to-embedding (Emb2Emb). This reduces the need for labeled tr...More
0
Introduction
  • Conditional text generation1 encompasses a large number of natural language processing tasks such as text simplification (Nisioi et al, 2017; Zhang and Lapata, 2017), summarization (Rush et al, 2015; Nallapati et al, 2016), machine translation (Bahdanau et al, 2015; Kumar and Tsvetkov, 2019) and style transfer (Shen et al, 2017; Fu et al, 2018).
  • When training data is available, the state of the art includes encoder-decoder models with an attention mechanism (Bahdanau et al, 2015; Vaswani et al, 2017) which are both extensions of the original sequence-to-sequence framework with a fixed bottleneck introduced by Sutskever et al (2014).
  • There are no style transfer methods, to the best of the knowledge, that were designed to leverage autoencoder pretraining, and only few can be used in this way (Shen et al, 2020; Wang et al, x AAAB9XicbVDLSgMxFL1TX7W+qi7dBIvgqsxIQd0V3bisYB/QjiWTSdvQTDIkGbUM/Q83LhRx67+482/MtLPQ1gMhh3PuJScniDnTxnW/ncLK6tr6RnGztLW9s7tX3j9oaZkoQptEcqk6AdaUM0GbhhlOO7GiOAo4bQfj68xvP1ClmRR3ZhJTP8JDwQaMYGOl+14geagnkb3Sp2m/XHGr7gxomXg5qUCORr/81QslSSIqDOFY667nxsZPsTKMcDot9RJNY0zGeEi7lgocUe2ns9RTdGKVEA2kskcYNFN/b6Q40lk0OxlhM9KLXib+53UTM7jwUybixFBB5g8NEo6MRFkFKGSKEsMnlmCimM2KyAgrTIwtqmRL8Ba/vExaZ1WvVr28rVXqV3kdRTiCYzgFD86hDjfQgCYQUPAMr/DmPDovzrvzMR8tOPnOIfyB8/kDVyyTFQ==
Highlights
  • Conditional text generation1 encompasses a large number of natural language processing tasks such as text simplification (Nisioi et al, 2017; Zhang and Lapata, 2017), summarization (Rush et al, 2015; Nallapati et al, 2016), machine translation (Bahdanau et al, 2015; Kumar and Tsvetkov, 2019) and style transfer (Shen et al, 2017; Fu et al, 2018)
  • We evaluate our model on an unsupervised style transfer task
  • With fast gradient iterative modification (FGIM), our model shows an advantage at the high-accuracy end of the curve, increasing content preservation by 68% while reaching 98% of FGIM’s transfer accuracy, though this is
  • Et al, 2020), who learn small adapters with few parameters for a pretrained VAE to generate latent codes that decode into text with a specific attribute. These models cannot be conditioned on input text, and are not applicable to style transfer
  • We present Emb2Emb, a framework that reduces conditional text generation tasks to learning in the embedding space of a pretrained autoencoder
Methods
  • The authors conduct controlled experiments to measure the benefits of the various aspects of the approach.
  • The authors use a one-layer LSTM as encoder and decoder, respectively.
  • The authors pretrain it on the text data of the target task as a denoising autoencoder (DAE; Vincent et al, 2010) with the noise function from Shen et al (2020).
  • Additional training and model details can be found in Appendix A
Results
  • With FGIM, the model shows an advantage at the high-accuracy end of the curve, increasing content preservation by 68% while reaching 98% of FGIM’s transfer accuracy, though this is computationally expensive
  • This confirms that the training framework, while being very flexible, is a strong alternative in the supervised, and in the unsupervised case.
  • The results in Figure 9 show that OffsetNet reaches better transfer accuracy than the MLP at comparable self-BLEU scores.
Conclusion
  • The authors present Emb2Emb, a framework that reduces conditional text generation tasks to learning in the embedding space of a pretrained autoencoder.
  • The authors propose an adversarial method and a neural architecture that are crucial for the method’s success by making learning stay on the manifold of the autoencoder.
  • Since the framework can be used with any pretrained autoencoder, it will benefit from large-scale pretraining in future research
Tables
  • Table1: Text simplification performance of model variants of end2end training on the test set. “Time” is wall time of one training epoch, relative to our model, Emb2Emb
  • Table2: Self-BLEU (“s-BLEU”) on the Yelp sentiment transfer test set for the configurations in Figure 5 with highest transfer accuracy (“Acc.”). “+Time” reports the inference-time slowdown factor due to each model’s additional computation (relative to our method)
  • Table3: Text simplification performance of model variants of seq2seq training on the development set. |Θ| denotes the number of parameters for each model
  • Table4: Input: i will never be back
  • Table5: Input: the cash register area was empty and no one was watching the store front . Reference: the store front was well attended multiplier / λsty
  • Table6: Input: the cash register area was empty and no one was watching the store front . Reference: the service was quick and responsive multiplier / λsty
  • Table7: Input: definitely disappointed that i could not use my birthday gift ! Reference: definitely not disappointed that i could use my birthday gift !
Download tables as Excel
Related work
Funding
  • Florian Mai was supported by the Swiss National Science Foundation under the project LAOS, grant number “FNS-30216”
  • Nikolaos Pappas was supported by the Swiss National Science Foundation under the project UNISON, grant number “P400P2 183911”
  • This work was also partially supported by US NSF grant 1562364
Study subjects and analysis
training pairs: 296402
The training data contains pairs of input and output sentences (xi, yi), where xi denotes the input sentence in English and yi denotes the output sentence in simple English. We evaluate on the English WikiLarge corpus introduced by Zhang and Lapata (2017), which consists of 296,402 training pairs, and development and test datasets adopted from Xu et al (2016). Following convention, we report two scores: BLEU (Papineni et al, 2002), which correlates with grammaticality (Xu et al, 2016), and SARI (Xu et al, 2016), found to correlate well with human judgements of simplicity

Reference
  • Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Kyunghyun Cho. 2018. Unsupervised neural machine translation. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Gayatri Bhat, Sachin Kumar, and Yulia Tsvetkov. 2019. A margin-based loss with synthetic negative samples for continuous-output machine translation. In Proceedings of the 3rd Workshop on Neural Generation and Translation, pages 199–205.
    Google ScholarLocate open access versionFindings
  • Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew Dai, Rafal Jozefowicz, and Samy Bengio. 2016. Generating sentences from a continuous space. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pages 10–21, Berlin, Germany. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Ondrej Cıfka, Aliaksei Severyn, Enrique Alfonseca, and Katja Filippova. 2018. Eval all, trust a few, do wrong to none: Comparing sentence generation models. arXiv preprint arXiv:1804.07972.
    Findings
  • Bin Dai and David Wipf. 2019. Diagnosing and enhancing VAE models. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Ning Dai, Jianze Liang, Xipeng Qiu, and Xuanjing Huang. 2019. Style transformer: Unpaired text style transfer without disentangled latent representation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5997–6007, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. Plug and play language models: A simple approach to controlled text generation. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 201BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Yu Duan, Canwen Xu, Jiaxin Pei, Jialong Han, and Chenliang Li. 2020. Pre-train and plug-in: Flexible conditional text generation with variational autoencoders. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 253–262, Online. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Jesse Engel, Matthew Hoffman, and Adam Roberts. 2018. Latent constraints: Learning to generate conditionally from unconditional generative models. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Thibault Fevry and Jason Phang. 2018. Unsupervised sentence compression using denoising autoencoders. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 413–422, Brussels, Belgium. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. 2018. Style transfer in text: Exploration and evaluation. In Thirty-Second AAAI Conference on Artificial Intelligence.
    Google ScholarLocate open access versionFindings
  • Jules Gagnon-Marchand, Hamed Sadeghi, Md Akmal Haidar, and Mehdi Rezagholizadeh. 2019. Salsatext: self attentive latent space based adversarial text generation. In Canadian Conference on Artificial Intelligence, pages 119–131. Springer.
    Google ScholarLocate open access versionFindings
  • Partha Ghosh, Mehdi S. M. Sajjadi, Antonio Vergari, Michael Black, and Bernhard Scholkopf. 2020. From variational to deterministic autoencoders. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems, pages 2672–2680.
    Google ScholarLocate open access versionFindings
  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770– 778.
    Google ScholarLocate open access versionFindings
  • Irina Higgins, Loıc Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew M Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-vae: Learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Toward controlled generation of text. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pages 1587–1596. JMLR. org.
    Google ScholarLocate open access versionFindings
  • Zhijing Jin, Di Jin, Jonas Mueller, Nicholas Matthews, and Enrico Santus. 2019. IMaT: Unsupervised text attribute transfer via iterative matching and translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3097–3109, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Diederik P Kingma and Max Welling. 2014. Autoencoding variational bayes. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Canasai Kruengkrai. 2019. Learning to flip the sentiment of reviews from non-parallel corpora. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6312–6317.
    Google ScholarLocate open access versionFindings
  • Sachin Kumar and Yulia Tsvetkov. 2019. Von MisesFisher loss for training sequence to sequence models with continuous outputs. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Guillaume Lample, Sandeep Subramanian, Eric Smith, Ludovic Denoyer, Marc’Aurelio Ranzato, and YLan Boureau. 2019. Multiple-attribute text rewriting. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Dianqi Li, Yizhe Zhang, Zhe Gan, Yu Cheng, Chris Brockett, Bill Dolan, and Ming-Ting Sun. 2019. Domain adaptive text style transfer. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, pages 3302–3311. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Juncen Li, Robin Jia, He He, and Percy Liang. 2018.
    Google ScholarFindings
  • Delete, retrieve, generate: a simple approach to sentiment and style transfer. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers), pages 1865–1874. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Danyang Liu and Gongshen Liu. 2019. A transformerbased variational autoencoder for sentence generation. In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–7. IEEE.
    Google ScholarLocate open access versionFindings
  • Dayiheng Liu, Jie Fu, Yidan Zhang, Chris Pal, and Jiancheng Lv. 2020. Revision in continuous space: Unsupervised text style transfer without adversarial learning. In AAAI.
    Google ScholarFindings
  • Lajanugen Logeswaran, Honglak Lee, and Samy Bengio. 2018. Content preserving text generation with attribute controls. In Advances in Neural Information Processing Systems, pages 5103–5113.
    Google ScholarLocate open access versionFindings
  • Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, and Ian Goodfellow. 2016. Adversarial autoencoders. In International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Alexander Mathews, Lexing Xie, and Xuming He. 2018. Simplifying sentences with sequence to sequence models. arXiv preprint arXiv:1805.05557.
    Findings
  • Ramesh Nallapati, Bowen Zhou, Cicero dos Santos, Caglar GuI‡lcehre, and Bing Xiang. 2016. Abstractive text summarization using sequence-to-sequence RNNs and beyond. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pages 280–290, Berlin, Germany. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Sergiu Nisioi, Sanja Stajner, Simone Paolo Ponzetto, and Liviu P. Dinu. 2017. Exploring neural text simplification models. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 85–91, Vancouver, Canada. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Kishore Papineni, Salim Roukos, Todd Ward, and WeiJing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting on association for computational linguistics, pages 311–318. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2227–2237, New Orleans, Louisiana. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Matthew E. Peters, Sebastian Ruder, and Noah A. Smith. 2019. To tune or not to tune? Adapting pretrained representations to diverse tasks. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), pages 7–14, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Gabriele Prato, Mathieu Duchesneau, Sarath Chandar, and Alain Tapp. 2019. Towards lossless encoding of sentences. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1577–1583, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners.
    Google ScholarFindings
  • D. E. Rumelhart, G. E. Hinton, and R. J. Williams. 1986. Learning Internal Representations by Error Propagation, page 318–362. MIT Press, Cambridge, MA, USA.
    Google ScholarFindings
  • Alexander M. Rush, Sumit Chopra, and Jason Weston. 2015. A neural attention model for abstractive sentence summarization. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 379–389, Lisbon, Portugal.
    Google ScholarLocate open access versionFindings
  • Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108.
    Findings
  • Stanislau Semeniuta, Aliaksei Severyn, and Erhardt Barth. 2017. A hybrid convolutional variational autoencoder for text generation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 627–637, Copenhagen, Denmark. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In Advances in neural information processing systems, pages 6830–6841.
    Google ScholarLocate open access versionFindings
  • Tianxiao Shen, Jonas Mueller, Regina Barzilay, and Tommi Jaakkola. 2020. Educating text autoencoders: Latent representation guidance via denoising. In Proceedings of the 37th International Conference on Machine Learning, Proceedings of Machine Learning Research, Online. PMLR.
    Google ScholarLocate open access versionFindings
  • Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and TieYan Liu. 2019. MASS: Masked sequence to sequence pre-training for language generation. In Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 5926–5936, Long Beach, California, USA. PMLR.
    Google ScholarLocate open access versionFindings
  • Akhilesh Sudhakar, Bhargav Upadhyay, and Arjun Maheswaran. 2019. “Transforming” delete, retrieve, generate approach for controlled text style transfer. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3269– 3279, Hong Kong, China. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • representations in a deep network with a local denoising criterion. Journal of machine learning research, 11(Dec):3371–3408.
    Google ScholarLocate open access versionFindings
  • Ke Wang, Hang Hua, and Xiaojun Wan. 2019. Controllable unsupervised text attribute transfer via editing entangled latent representation. In Advances in Neural Information Processing Systems, pages 11034– 11044.
    Google ScholarLocate open access versionFindings
  • Chao Xing, Dong Wang, Chao Liu, and Yiye Lin. 2015. Normalized word embedding and orthogonal transform for bilingual word translation. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1006–1011.
    Google ScholarLocate open access versionFindings
  • Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, and Chris Callison-Burch. 2016. Optimizing statistical machine translation for text simplification. Transactions of the Association for Computational Linguistics, 4:401–415.
    Google ScholarLocate open access versionFindings
  • Zichao Yang, Zhiting Hu, Chris Dyer, Eric P Xing, and Taylor Berg-Kirkpatrick. 2018. Unsupervised text style transfer using language models as discriminators. In Advances in Neural Information Processing Systems, pages 7287–7298.
    Google ScholarLocate open access versionFindings
  • Xingxing Zhang and Mirella Lapata. 2017. Sentence simplification with deep reinforcement learning. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 584–594, Copenhagen, Denmark. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Junbo Jake Zhao, Yoon Kim, Kelly Zhang, Alexander M Rush, Yann LeCun, et al. 2018. Adversarially regularized autoencoders. In Proceedings of the 35th International Conference on Machine Learning, Proceedings of Machine Learning Research. PMLR.
    Google ScholarLocate open access versionFindings
  • Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems, pages 3104–3112.
    Google ScholarLocate open access versionFindings
  • Dusan Varisand Ondrej Bojar. 2019. Unsupervised pretraining for neural machine translation using elastic weight consolidation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 130–135, Florence, Italy. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008.
    Google ScholarLocate open access versionFindings
  • Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, and Pierre-Antoine Manzagol. 2010. Stacked denoising autoencoders: Learning useful
    Google ScholarFindings
  • Implementation. We used Python 3.7 with PyTorch 1.4 for all our experiments. Our open-source implementation is available at https://github.com/florianmai/emb2emb.
    Findings
  • We evaluate on the WikiLarge dataset by Zhang and Lapata (2017), which consists of sentence pairs extracted from Wikipedia, where the input is in English and the output is in simple English. It contains of 296,402 training pairs, 2,000 development pairs, and 359 pairs for testing. The 2,359 development and test pairs each come with 8 human-written reference sentences to compute the BLEU and SARI overlap with. The dataset can be downloaded from https://github.com/XingxingZhang/dress.
    Findings
  • 7https://www.nltk.org/api/nltk. translate.html#module-nltk.translate. bleu_score
    Findings
  • For computing SARI score, we use the implementation provided by (Xu et al., 2016) at https://github.com/cocoxu/simplification/blob/master/SARI.py. A.4.3 SARI Score by λadv Experimental details. We measure the performance of our model on the development set of WikiLarge in terms of SARI score. These results are for the same training run for which we reported the BLEU score, hence, the stopping criterion for early stopping was BLEU, and we report the results for all 10 exponentially increasing values of λadv. The best value when using BLEU score as stopping criterion is λadv=0.032. Results. The results in Figure 7 show the same pattern as for the BLEU score, although with a smaller relative gain of 23%when using the adversarial term.
    Findings
Author
Florian Mai
Florian Mai
Ivan Montero
Ivan Montero
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科