English
Related papers

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

200 papers

Learners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise from any aspect of the model architecture. We investigate…

Computation and Language · Computer Science 2020-01-14 R. Thomas McCoy , Robert Frank , Tal Linzen

The ability to reason with multiple hierarchical structures is an attractive and desirable property of sequential inductive biases for natural language processing. Do the state-of-the-art Transformers and LSTM architectures implicitly…

Computation and Language · Computer Science 2021-11-30 Bill Tuck Weng Pung , Alvin Chan

Ongoing innovations in recurrent neural network architectures have provided a steady influx of apparently state-of-the-art results on language modelling benchmarks. However, these have been evaluated using differing code bases and limited…

Computation and Language · Computer Science 2017-11-21 Gábor Melis , Chris Dyer , Phil Blunsom

Recurrent neural networks (RNNs) are the state of the art in sequence modeling for natural language. However, it remains poorly understood what grammatical characteristics of natural language they implicitly learn and represent as a…

Computation and Language · Computer Science 2018-09-06 Richard Futrell , Ethan Wilcox , Takashi Morita , Roger Levy

Structure-inducing Language Models (SiLM) are trained on a self-supervised language modeling task, and induce a hierarchical sentence representation as a byproduct when processing an input. SiLMs couple strong syntactic generalization…

Computation and Language · Computer Science 2025-12-09 David Arps , Hassan Sajjad , Laura Kallmeyer

In this paper, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units to keep track of more preceding states in recurrent neural networks (RNNs), which are all…

Neural and Evolutionary Computing · Computer Science 2016-05-03 Rohollah Soltani , Hui Jiang

Pretrained neural models such as BERT, when fine-tuned to perform natural language inference (NLI), often show high accuracy on standard datasets, but display a surprising lack of sensitivity to word order on controlled challenge sets. We…

Computation and Language · Computer Science 2020-04-28 Junghyun Min , R. Thomas McCoy , Dipanjan Das , Emily Pitler , Tal Linzen

Systematic generalization is the ability to combine known parts into novel meaning; an important aspect of efficient human learning, but a weakness of neural network learning. In this work, we investigate how two well-known modeling…

Artificial Intelligence · Computer Science 2022-02-23 Laura Ruis , Brenden Lake

We show that both an LSTM and a unitary-evolution recurrent neural network (URN) can achieve encouraging accuracy on two types of syntactic patterns: context-free long distance agreement, and mildly context-sensitive cross serial…

Computation and Language · Computer Science 2022-08-12 Jean-Philippe Bernardy , Shalom Lappin

Recent work has shown that recurrent neural networks (RNNs) can implicitly capture and exploit hierarchical information when trained to solve common natural language processing tasks such as language modeling (Linzen et al., 2016) and…

Computation and Language · Computer Science 2018-08-29 Ke Tran , Arianna Bisazza , Christof Monz

Syntax is a latent hierarchical structure which underpins the robust and compositional nature of human language. In this work, we explore the hypothesis that syntactic dependencies can be represented in language model attention…

Computation and Language · Computer Science 2023-10-24 Jasper Jian , Siva Reddy

Memory-augmented neural networks equip a recurrent neural network with an explicit memory to support tasks that require information storage without interference over long times. A key motivation for such research is to perform classic…

Neural and Evolutionary Computing · Computer Science 2021-07-27 Benjamin Paaßen , Alexander Schulz , Barbara Hammer

The task of linearization is to find a grammatical order given a set of words. Traditional models use statistical methods. Syntactic linearization systems, which generate a sentence along with its syntactic tree, have shown state-of-the-art…

Computation and Language · Computer Science 2018-10-24 Linfeng Song , Yue Zhang , Daniel Gildea

Sequence-based neural networks show significant sensitivity to syntactic structure, but they still perform less well on syntactic tasks than tree-based networks. Such tree-based networks can be provided with a constituency parse, a…

Computation and Language · Computer Science 2020-05-04 Michael A. Lepori , Tal Linzen , R. Thomas McCoy

Recently, recurrent neural networks have become state-of-the-art in acoustic modeling for automatic speech recognition. The long short-term memory (LSTM) units are the most popular ones. However, alternative units like gated recurrent unit…

Audio and Speech Processing · Electrical Eng. & Systems 2018-07-18 Jan Vanek , Josef Michalek , Jan Zelinka , Josef Psutka

Recurrent Neural Networks (RNNs) have long been recognized for their potential to model complex time series. However, it remains to be determined what optimization techniques and recurrent architectures can be used to best realize this…

Machine Learning · Statistics 2015-10-19 Ben Krause

We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system…

Computation and Language · Computer Science 2017-04-27 Hao Peng , Sam Thomson , Noah A. Smith

Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, it is difficult to understand what exactly they learn. Second, they tend to work poorly on sequences requiring long-term…

Machine Learning · Computer Science 2019-05-08 Cheng Wang , Mathias Niepert

The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a…

Computation and Language · Computer Science 2026-03-24 Hadi Pouransari , David Grangier , C Thomas , Michael Kirchhof , Oncel Tuzel

With the advent of powerful neural language models over the last few years, research attention has increasingly focused on what aspects of language they represent that make them so successful. Several testing methodologies have been…

Computation and Language · Computer Science 2023-05-26 Jordan Kodner , Nitish Gupta