Globally Coherent Text Generation with Neural Checklist Models

Kiddon, Chloé; Zettlemoyer, Luke; Choi, Yejin

doi:10.18653/v1/d16-1032

Cited by 203 publications

(220 citation statements)

References 22 publications

Supporting

Mentioning

220

Contrasting

Order By: Relevance

“…Many techniques have been proposed to improve the performance of basic sequence-to-sequence architecture by allowing more encoder side information during decoding e.g. using attention [Bahdanau et al, 2015], neural checklists [Kiddon et al, 2016], pointer networks [Vinyals et al, 2015a].…”

Section: Related Workmentioning

confidence: 99%

“…Sequence-to-sequence models which consider extra signal from the input sequence to modify the output token generation have been proposed recently in various context e.g. for -18) recipe generation [Kiddon et al, 2016], optimization [Vinyals et al, 2015a], semantic parsing [Jia and Liang, 2016]. However, our argument transfer model is architecturally different from all the aforementioned models.…”

Section: Trainingmentioning

confidence: 99%

See 1 more Smart Citation

Learning Out-of-Vocabulary Words in Intelligent Personal Agents

Ray

Shen

Jin

2018

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Semantic parsers play a vital role in intelligent agents to convert natural language instructions to an actionable logical form representation. However, after deployment, these parsers suffer from poor accuracy on encountering out-of-vocabulary (OOV) words, or significant accuracy drop on previously supported instructions after retraining. Achieving both goals simultaneously is non-trivial. In this paper, we propose novel neural networks based parsers to learn OOV words; one incorporating a new hybrid paraphrase generation model, and an enhanced sequence-to-sequence model. Extensive experiments on both benchmark and custom datasets show our new parsers achieve significant accuracy gain on OOV words and phrases, and in the meanwhile learn OOV words while maintaining accuracy on previously supported instructions.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Trainingmentioning

confidence: 99%

Learning Out-of-Vocabulary Words in Intelligent Personal Agents

Ray

Shen

Jin

2018

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…In terms of network architecture, Wen et al (2015) equip LSTM with a semantic control cell to improve informativeness of generated sentence. Kiddon et al (2016) propose the neural checklist model to explicitly track what has been mentioned and what left to say by splitting these two into different lists. Our model is related to these models with respect to information representation and challenges from coverage and redundancy.…”

Section: Related Workmentioning

confidence: 99%

Natural Answer Generation with Heterogeneous Memory

Fu¹,

Feng²

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

Memory augmented encoder-decoder framework has achieved promising progress for natural language generation tasks. Such frameworks enable a decoder to retrieve from a memory during generation. However, less research has been done to take care of the memory contents from different sources, which are often of heterogeneous formats. In this work, we propose a novel attention mechanism to encourage the decoder to actively interact with the memory by taking its heterogeneity into account. Our solution attends across the generated history and memory to explicitly avoid repetition, and introduce related knowledge to enrich our generated sentences. Experiments on the answer sentence generation task show that our method can effectively explore heterogeneous memory to produce readable and meaningful answer sentences while maintaining high coverage for given answer information.

show abstract

“…However, while neural methods are effective for generation of individual sentences conditioned on some context, they struggle with coherence when used to generate longer texts (Kiddon et al, 2016). In addition, it is challenging to apply neural models in less constrained generation tasks with many valid solutions, such as open-domain dialogue and story continuation.…”

Section: Introductionmentioning

confidence: 99%

Quality Signals in Generated Stories

Sagarkar¹,

Wieting

et al. 2018

Proceedings of the Seventh Joint Conference on Lexical And Computational Semantics

View full text Add to dashboard Cite

We study the problem of measuring the quality of automatically-generated stories. We focus on the setting in which a few sentences of a story are provided and the task is to generate the next sentence ("continuation") in the story. We seek to identify what makes a story continuation interesting, relevant, and have high overall quality. We crowdsource annotations along these three criteria for the outputs of story continuation systems, design features, and train models to predict the annotations. Our trained scorer can be used as a rich feature function for story generation, a reward function for systems that use reinforcement learning to learn to generate stories, and as a partial evaluation metric for story generation.

show abstract

Globally Coherent Text Generation with Neural Checklist Models

Cited by 203 publications

References 22 publications

Learning Out-of-Vocabulary Words in Intelligent Personal Agents

Learning Out-of-Vocabulary Words in Intelligent Personal Agents

Natural Answer Generation with Heterogeneous Memory

Quality Signals in Generated Stories

Contact Info

Product

Resources

About