paper-with-me

Papers

Syntax-Infused Variational Autoencoder for Text Generation

2019-06-05 · ACL 2019 7 · Xinyuan Zhang, Yi Yang, Siyang Yuan, Dinghan Shen, Lawrence Carin

We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences. Distinct from existing VAE-based text generative models, SIVAE contains two separate latent spaces, for sentences and syntactic trees. The evidence lower bound objective is redesigned correspondingly, by optimizing a joint distribution that accommodates two encoders and two decoders. SIVAE works with long short-term memory architectures to simultaneously generate sentences and syntactic trees. Two versions of SIVAE are proposed: one captures the dependencies between the latent variables through a conditional prior network, and the other treats the latent variables independently such that syntactically-controlled sentence generation can be performed. Experimental results demonstrate the generative superiority of SIVAE on both reconstruction and targeted syntactic evaluations. Finally, we show that the proposed models can be used for unsupervised paraphrasing given different syntactic tree templates.

📄 PDF Abstract BibTeX arXiv:1906.02181

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceText Generation

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Text Modeling with Syntax-Aware Variational Autoencoders

2019-08-27 · Yijun Xiao, William Yang Wang

Syntactic information contains structures and rules about how text sentences are arranged. Incorporating syntax into text modeling methods can potentially benefit both representation learning and generation. Variational …

Representation Learning

APo-VAE: Text Generation in Hyperbolic Space

2020-04-30 · NAACL 2021 4 · Shuyang Dai, Zhe Gan, Yu Cheng, Chenyang Tao 외

Natural language often exhibits inherent hierarchical structure ingrained with complex syntax and semantics. However, most state-of-the-art deep generative models learn embeddings only in Euclidean vector space, without …

Language ModelingLanguage ModellingResponse GenerationText Generation

Syntax-Directed Variational Autoencoder for Structured Data

2018-02-24 · ICLR 2018 1 · Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena 외

Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer prog…

DecoderTranslationvalid

Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding

2019-11-10 · Dhanasekar Sundararaman, Vivek Subramanian, Guoyin Wang, Shijing Si 외

Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates abstract representations of tokens inpu…

Machine TranslationNatural Language UnderstandingPOSTranslation

Towards Visually Explaining Variational Autoencoders

2019-11-18 · CVPR 2020 6 · Wenqian Liu, Runze Li, Meng Zheng, Srikrishna Karanam 외

Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have…

Disentanglement