Creativity: Generating Diverse Questions Using Variational Autoencoders

Jain, Unnat; Zhang, Ziyu; Schwing, Alexander G.

doi:10.1109/cvpr.2017.575

Cited by 122 publications

(131 citation statements)

References 42 publications

Supporting

Mentioning

127

Contrasting

Order By: Relevance

“…Articles on generative applications utilize latent spaces to synthesize specific types of outputs. Examples include synthesizing images [YYSL16], sentences [JZS17], music [HNP17], and molecules [JBJ18]. • Understand data.…”

Section: Uses and Interpretation Goalsmentioning

confidence: 99%

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Liu

Jun

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

Latent spaces—reduced‐dimensionality vector space embeddings of data, fit via machine learning—have been shown to capture interesting semantic properties and support data analysis and synthesis within a domain. Interpretation of latent spaces is challenging because prior knowledge, sometimes subtle and implicit, is essential to the process. We contribute methods for “latent space cartography”, the process of mapping and comparing meaningful semantic dimensions within latent spaces. We first perform a literature survey of relevant machine learning, natural language processing, and scientific research to distill common tasks and propose a workflow process. Next, we present an integrated visual analysis system for supporting this workflow, enabling users to discover, define, and verify meaningful relationships among data points, encoded within latent space dimensions. Three case studies demonstrate how users of our system can compare latent space variants in image generation, challenge existing findings on cancer transcriptomes, and assess a word embedding benchmark.

show abstract

Section: Uses and Interpretation Goalsmentioning

confidence: 99%

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Liu

Jun

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…al [23]. For BLEU score the improvement is around 20% over [38], 5% over [23]. But it's still quite far from human performance.…”

Section: Comparison With State-of-the-art Methods and Ablation Analysismentioning

confidence: 91%

“…We evaluate the proposed method in the following ways: First, we evaluate our proposed MC-BMN against other variants described in section 4.2. Second, we further compare our network with state-of-the-art methods such as Natural [38] and Creative [23]. Third, we have shown in figure 4, the variance plots for different samples drawn from the posterior for Bayesian and Non-Bayesian methods.…”

Section: Methodsmentioning

confidence: 99%

“…In [38], the authors used an encoder-decoder based framework that has been further adopted in our work by considering various contexts. In [23], the authors extend it by using a Variational Autoencoder based sequential routine to obtain natural questions by performing sampling of the latent variable. In a very recent work by [43], the authors use an exemplar based multimodal encoder-decoder approach to generate natural questions.…”

Section: Related Workmentioning

confidence: 99%

“…Each image in the dataset contains five natural questions and five ground truth captions. It is worth noting that the work of [23] also used the questions from VQA dataset [ for training purpose, whereas the work by [38] uses only the VQG-COCO dataset. We understand that the size of this dataset is small and there are other datasets like VQA [1], Visual7W [66] and Visual Genome [29] which have thousands of images and questions.…”

Section: Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Multimodal Differential Network for Visual Question Generation

Patro¹,

Kumar²,

Kurmi³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Generating natural questions from an image is a semantic task that requires using vision and language modalities to learn multimodal representations. Images can have multiple visual and language cues such as places, captions, and tags. In this paper, we propose a principled deep Bayesian learning framework that combines these cues to produce natural questions. We observe that with the addition of more cues and by minimizing uncertainty in the among cues, the Bayesian network becomes more confident. We propose a Minimizing Uncertainty of Mixture of Cues (MUMC), that minimizes uncertainty present in a mixture of cues experts for generating probabilistic questions. This is a Bayesian framework and the results show a remarkable similarity to natural questions as validated by a human study. We observe that with the addition of more cues and by minimizing uncertainty among the cues, the Bayesian framework becomes more confident. Ablation studies of our model indicate that a subset of cues is inferior at this task and hence the principled fusion of cues is preferred. Further, we observe that the proposed approach substantially improves over state-of-the-art benchmarks on the quantitative metrics (BLEU-n, METEOR, ROUGE, and CIDEr). Here we provide project link for Deep Bayesian VQG https: //delta-lab-iitk.github.io/BVQG/.

show abstract

Question generation based on chat‐response conversion

Zhong

Peng

Liu

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary Today, thanks to the major breakthrough of sequences to sequences model in the field of natural language, most of the dialogue generation tasks are focused on generating more effective responses. However, the responses proposed by the chat‐bot are only a passive answer or assentation, which does not arouse the desire of people to continue communicating. How to transform the chat robot from a passive reply to an active questioner has become an urgent problem. In this paper, a question generalization method with four types of question proposing schemes are designed, implemented, and tested to automate question generation process. The proposed system is controlled by a probability‐triggered multiple conversion mechanism to actively propose different types of questions. We embed our methods in the mainstream dialogue generation model and demonstrate its effectiveness in dialogue response generalization on a standard dataset. In addition, it achieves good performance in subjective conversational assessment.

show abstract

Creativity: Generating Diverse Questions Using Variational Autoencoders

Cited by 122 publications

References 42 publications

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Multimodal Differential Network for Visual Question Generation

Question generation based on chat‐response conversion

Contact Info

Product

Resources

About