Latent Predictor Networks for Code Generation

Wang, Ling; Blunsom, Phil; Grefenstette, Edward; Hermann, Karl Moritz; Kočiský, Tomáš; Wang, Fumin; Senior, Andrew W.

doi:10.18653/v1/p16-1057

Cited by 255 publications

(260 citation statements)

References 17 publications

Supporting

Mentioning

258

Contrasting

Order By: Relevance

“…<s.food> to food or type of food, and (2) replacing delexicalised values by the actual attribute values of the entity currently selected by the DB pointer. This is similar in spirit to the Latent Predictor Network (Ling et al, 2016) where the token generation process is augmented by a set of pointer networks to transfer entity specific information into the response.…”

Section: Generation Networkmentioning

confidence: 99%

A Network-based End-to-End Trainable Task-oriented Dialogue System

Wen¹,

Vandyke²,

Mrkšić³

et al. 2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

422

270

View full text Add to dashboard Cite

Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing taskoriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce a neural network-based text-in, textout end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework. This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand. The results show that the model can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

show abstract

Section: Generation Networkmentioning

confidence: 99%

A Network-based End-to-End Trainable Task-oriented Dialogue System

Wen¹,

Vandyke²,

Mrkšić³

et al. 2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

422

270

View full text Add to dashboard Cite

show abstract

“…LSTMs in Dam et al [17]) describe context distributed representations while sequentially generating code. Ling et al [18] and Allamanis et al [19] combine the code-context distributed representation with distributed representations of other modalities (e.g., natural language) to synthesize code.…”

Section: A Deep Code Representationmentioning

confidence: 99%

Multi-modal Attention Network Learning for Semantic Source Code Retrieval

Wan

Shu

Sui

et al. 2019

2019 34th IEEE/ACM International Conference on Automated Software Engineering (ASE)

123

View full text Add to dashboard Cite

We propose a more comprehensive multi-modal representation method for source code, with one LSTM for the sequential content of source code, a Tree-LSTM for the AST of source code and a GGNN for the CFG of source code. Furthermore, a multi-modal fusion layer is applied to integrate these three representations.• To the best of our knowledge, it is the first time that we propose an attention network to assign different weights to different parts of each modality of source code, providing an explainability of our deep multi-modal neural network for representation.

show abstract

“…Ling et al [34] focus on the problem of generating valid code from natural language descriptions on Hearthstone and Magic cards. This is in a sense the other side of the coin, and would be needed as a part of a functioning card generation system, to use the code for these decks for artificial agents that can playtest new cards.…”

Section: Generating Cardsmentioning

confidence: 99%

The Many AI Challenges of Hearthstone

Hoover

Togelius

Lee³

et al. 2019

Künstl Intell

View full text Add to dashboard Cite

Games have benchmarked AI methods since the inception of the field, with classic board games such as Chess and Go recently leaving room for video games with related yet different sets of challenges. The set of AI problems associated with video games has in recent decades expanded from simply playing games to win, to playing games in particular styles, generating game content, modeling players etc. Different games pose very different challenges for AI systems, and several different AI challenges can typically be posed by the same game. In this article we analyze the popular collectible card game Hearthstone (Blizzard 2014) and describe a varied set of interesting AI challenges posed by this game. Collectible card games are relatively understudied in the AI community, despite their popularity and the interesting challenges they pose. Analyzing a single game in-depth in the manner we do here allows us to see the entire field of AI and Games through the lens of a single game, discovering a few new variations on existing research topics.

show abstract

Latent Predictor Networks for Code Generation

Cited by 255 publications

References 17 publications

A Network-based End-to-End Trainable Task-oriented Dialogue System

A Network-based End-to-End Trainable Task-oriented Dialogue System

Multi-modal Attention Network Learning for Semantic Source Code Retrieval

The Many AI Challenges of Hearthstone

Contact Info

Product

Resources

About