English
Related papers

Related papers: Bearing Syntactic Fruit with Stack-Augmented Neura…

200 papers

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 architectures still exhibit…

Computation and Language · Computer Science 2023-05-19 Brian DuSell

Learning hierarchical structures in sequential data -- from simple algorithmic patterns to natural language -- in a reliable, generalizable way remains a challenging problem for neural language models. Past work has shown that recurrent…

Computation and Language · Computer Science 2022-12-01 Brian DuSell , David Chiang

Programming language modeling has attracted extensive attention in recent years, and it plays an essential role in program processing fields. Statistical language models, which are initially designed for natural languages, have been…

Software Engineering · Computer Science 2020-02-12 Fang Liu , Lu Zhang , Zhi Jin

Syntactic rules in natural language typically need to make reference to hierarchical sentence structure. However, the simple examples that language learners receive are often equally compatible with linear rules. Children consistently…

Computation and Language · Computer Science 2018-06-11 R. Thomas McCoy , Robert Frank , Tal Linzen

When acquiring syntax, children consistently choose hierarchical rules over competing non-hierarchical possibilities. Is this preference due to a learning bias for hierarchical structure, or due to more general biases that interact with…

Computation and Language · Computer Science 2023-06-07 Aditya Yedetore , Tal Linzen , Robert Frank , R. Thomas McCoy

Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this…

Machine Learning · Computer Science 2020-08-21 Tao Li , Vivek Srikumar

Neural network architectures have been augmented with differentiable stacks in order to introduce a bias toward learning hierarchy-sensitive regularities. It has, however, proven difficult to assess the degree to which such a bias is…

Computation and Language · Computer Science 2019-06-05 William Merrill , Lenny Khazan , Noah Amsel , Yiding Hao , Simon Mendelsohn , Robert Frank

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…

Neural and Evolutionary Computing · Computer Science 2018-09-11 Yiding Hao , William Merrill , Dana Angluin , Robert Frank , Noah Amsel , Andrew Benz , Simon Mendelsohn

We introduce three memory-augmented Recurrent Neural Networks (MARNNs) and explore their capabilities on a series of simple language modeling tasks whose solutions require stack-based mechanisms. We provide the first demonstration of neural…

Computation and Language · Computer Science 2019-11-11 Mirac Suzgun , Sebastian Gehrmann , Yonatan Belinkov , Stuart M. Shieber

We present a differentiable stack data structure that simultaneously and tractably encodes an exponential number of stack configurations, based on Lang's algorithm for simulating nondeterministic pushdown automata. We call the combination…

Computation and Language · Computer Science 2022-12-01 Brian DuSell , David Chiang

Traditional recurrent neural networks (RNNs) have a fixed, finite number of memory cells. In theory (assuming bounded range and precision), this limits their formal language recognition power to regular languages, and in practice, RNNs have…

Computation and Language · Computer Science 2023-03-14 Brian DuSell , David Chiang

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to…

Computation and Language · Computer Science 2020-03-04 Qian Chen , Xiaodan Zhu , Zhenhua Ling , Si Wei , Hui Jiang , Diana Inkpen

State-of-the-art LSTM language models trained on large corpora learn sequential contingencies in impressive detail and have been shown to acquire a number of non-local grammatical dependencies with some success. Here we investigate whether…

Computation and Language · Computer Science 2019-04-09 Ethan Wilcox , Peng Qian , Richard Futrell , Miguel Ballesteros , Roger Levy

Deep learning sequence models have led to a marked increase in performance for a range of Natural Language Processing tasks, but it remains an open question whether they are able to induce proper hierarchical generalizations for…

Computation and Language · Computer Science 2019-06-11 Ethan Wilcox , Roger Levy , Richard Futrell

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce…

Computation and Language · Computer Science 2020-10-13 Ethan Wilcox , Peng Qian , Richard Futrell , Ryosuke Kohita , Roger Levy , Miguel Ballesteros

While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic…

Computation and Language · Computer Science 2020-05-26 Jennifer Hu , Jon Gauthier , Peng Qian , Ethan Wilcox , Roger P. Levy

How do neural language models acquire a language's structure when trained for next-token prediction? We address this question by deriving theoretical scaling laws for neural network performance on synthetic datasets generated by the Random…

Machine Learning · Computer Science 2025-05-13 Francesco Cagnetta , Alessandro Favero , Antonio Sclocchi , Matthieu Wyart

In this work we use the recent advances in representation learning to propose a neural architecture for the problem of natural language inference. Our approach is aligned to mimic how a human does the natural language inference process…

Computation and Language · Computer Science 2017-01-30 Biswajit Paria , K. M. Annervaz , Ambedkar Dukkipati , Ankush Chatterjee , Sanjay Podder

We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture…

Computation and Language · Computer Science 2019-04-05 Subhojeet Pramanik , Aman Hussain

Characterizing the computational power of neural network architectures in terms of formal language theory remains a crucial line of research, as it describes lower and upper bounds on the reasoning capabilities of modern AI. However, when…

Computation and Language · Computer Science 2025-04-15 Alexandra Butoi , Ghazal Khalighinejad , Anej Svete , Josef Valvoda , Ryan Cotterell , Brian DuSell
‹ Prev 1 2 3 10 Next ›