• Corpus ID: 35933354


  author={David Alvarez-Melis and T. Jaakkola},
We propose a neural network architecture for generating tree-structured objects from encoded representations. The core of the method is a doubly recurrent neural network model comprised of separate width and depth recurrences that are combined inside each cell (node) to generate an output. The topology of the tree is modeled explicitly together with the content. That is, in response to an encoded vector representation, co-evolving recurrences are used to realize the associated tree and the… 

Ain't Nobody Got Time For Coding: Structure-Aware Program Synthesis From Natural Language

SAPS is presented, an end-to-end neural network capable of mapping relatively complex, multi-sentence NL specifications to snippets of executable code, and uses a fixed-dimensional latent representation as the only link between the NL analyzer and source code generator.



Top-down Tree Long Short-Term Memory Networks

This paper develops Tree Long Short-Term Memory (TreeLSTM), a neural network model based on LSTM, which is designed to predict a tree rather than a linear sequence, and reports results on dependency parsing reranking achieving competitive performance.

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

The Tree-LSTM is introduced, a generalization of LSTMs to tree-structured network topologies that outperform all existing systems and strong LSTM baselines on two tasks: predicting the semantic relatedness of two sentences and sentiment classification.

Learning task-dependent distributed representations by backpropagation through structure

  • C. GollerA. Küchler
  • Computer Science
    Proceedings of International Conference on Neural Networks (ICNN'96)
  • 1996
A connectionist architecture together with a novel supervised learning scheme which is capable of solving inductive inference tasks on complex symbolic structures of arbitrary size is presented.

Sequence to Sequence Learning with Neural Networks

This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

Sequence Level Training with Recurrent Neural Networks

This work proposes a novel sequence level training algorithm that directly optimizes the metric used at test time, such as BLEU or ROUGE, and outperforms several strong baselines for greedy generation.

Recurrent Neural Network Regularization

This paper shows how to correctly apply dropout to LSTMs, and shows that it substantially reduces overfitting on a variety of tasks.

Parsing Natural Scenes and Natural Language with Recursive Neural Networks

A max-margin structure prediction architecture based on recursive neural networks that can successfully recover such structure both in complex scene images as well as sentences is introduced.

Easy-First Dependency Parsing with Hierarchical Tree LSTMs

A compositional vector representation of parse trees that relies on a recursive combination of recurrent-neural network encoders is suggested, achieving very strong accuracies for English and Chinese, without relying on external word embeddings.

Language to Logical Form with Neural Attention

This paper presents a general method based on an attention-enhanced encoder-decoder model that encode input utterances into vector representations, and generate their logical forms by conditioning the output sequences or trees on the encoding vectors.

Long Short-Term Memory

A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.