paper-with-me

홈 › Papers

Context-Free Transductions with Neural Stacks

2018-09-08 · WS 2018 11 · Yiding Hao, William Merrill, Dana Angluin, Robert Frank, Noah Amsel, Andrew Benz, Simon Mendelsohn

This paper analyzes the behavior of stack-augmented recurrent neural network (RNN) models. Due to the architectural similarity between stack RNNs and pushdown transducers, we train stack RNN models on a number of tasks, including string reversal, context-free language modelling, and cumulative XOR evaluation. Examining the behavior of our networks, we show that stack-augmented RNNs can discover intuitive stack-based strategies for solving our tasks. However, stack RNNs are more difficult to train than classical architectures such as LSTMs. Rather than employ stack-based strategies, more complex networks often find approximate solutions by using the stack as unstructured memory.

📄 PDF Abstract BibTeX arXiv:1809.02836

Code (2)

viking-sudo-rm/StackNN 공식 구현 pytorch
suzgunmirac/marnns pytorch

Tasks

Language Modelling

Similar Papers 제목 키워드 기반

Regular transductions with MCFG input syntax

2019-09-01 · WS 2019 9 · Mark-Jan Nederhof, Heiko Vogler

We show that regular transductions for which the input part is generated by some multiple context-free grammar can be simulated by synchronous multiple context-free grammars. We prove that synchronous multiple context-fr…

Quantifier-free tree transductions

2020-01-01 · SCiL 2020 1 · Shiori Ikawa, Akane Ohtaka, Adam Jardine

Weighting Finite-State Transductions With Neural Context

2016-06-01 · NAACL 2016 6 · Pushpendre Rastogi, Ryan Cotterell, Jason Eisner
LemmatizationStructured PredictionTransliteration

Nondeterministic Stacks in Neural Networks

2023-04-25 · Brian DuSell

Human language is full of compositional syntactic structures, and although neural networks have contributed to groundbreaking improvements in computer systems that process language, widely-used neural network architectur…

Language ModelingLanguage Modelling

Deep Tree Transductions - A Short Survey

2019-02-05 · Davide Bacciu, Antonio Bruno

The paper surveys recent extensions of the Long-Short Term Memory networks to handle tree structures from the perspective of learning non-trivial forms of isomorph structured transductions. It provides a discussion of mo…

Survey