Assessing the Unitary RNN as an End-to-End Compositional Model of Syntax

• URL: http://arxiv.org/abs/2208.05719v1
• Date: Thu, 11 Aug 2022 09:30:49 GMT
• Title: Assessing the Unitary RNN as an End-to-End Compositional Model of Syntax
• Authors: Jean-Philippe Bernardy (University of Gothenburg), Shalom Lappin (University of Gothenburg, Queen Mary University of London, and King's College London)
• Abstract summary: We show that both an LSTM and a unitary-evolution recurrent neural network (URN) can achieve encouraging accuracy on two types of syntactic patterns.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 dependencies. This work extends recent experiments on deeply nested context-free long distance dependencies, with similar results. URNs differ from LSTMs in that they avoid non-linear activation functions, and they apply matrix multiplication to word embeddings encoded as unitary matrices. This permits them to retain all information in the processing of an input string over arbitrary distances. It also causes them to satisfy strict compositionality. URNs constitute a significant advance in the search for explainable models in deep learning applied to NLP.

Related papers

• Nearest Neighbor Speculative Decoding for LLM Generation and Attribution [87.3259169631789]
  Nearest Speculative Decoding (NEST) is capable of incorporating real-world text spans of arbitrary length into the LM generations and providing attribution to their sources. NEST significantly enhances the generation quality and attribution rate of the base LM across a variety of knowledge-intensive tasks. In addition, NEST substantially improves the generation speed, achieving a 1.8x speedup in inference time when applied to Llama-2-Chat 70B.
  arXiv  Detail & Related papers  (2024-05-29T17:55:03Z)
• B-LSTM-MIONet: Bayesian LSTM-based Neural Operators for Learning the Response of Complex Dynamical Systems to Length-Variant Multiple Input Functions [6.75867828529733]
  Multiple-input deep neural operators (MIONet) extended DeepONet to allow multiple input functions in different Banach spaces. MIONet offers flexibility in training dataset grid spacing, without constraints on output location. This work redesigns MIONet, integrating Long Short Term Memory (LSTM) to learn neural operators from time-dependent data.
  arXiv  Detail & Related papers  (2023-11-28T04:58:17Z)
• Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues [32.783917920167205]
  We show that combining architectures with both real or complex linear diagonal recurrences leads to arbitrarily precise approximation of sequence-to-sequence maps. We prove that employing complex eigenvalues near unit disk - i.e., the most successful strategy in S4 - greatly helps the RNN in storing information.
  arXiv  Detail & Related papers  (2023-07-21T20:09:06Z)
• Return of the RNN: Residual Recurrent Networks for Invertible Sentence Embeddings [0.0]
  This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our approach employs a regression-based output layer to reconstruct the input sequence's word vectors. The model achieves high accuracy and fast training with the ADAM, a significant finding given that RNNs typically require memory units, such as LSTMs, or second-order optimization methods.
  arXiv  Detail & Related papers  (2023-03-23T15:59:06Z)
• Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
  State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-28T17:50:19Z)
• Learning First-Order Rules with Differentiable Logic Program Semantics [12.360002779872373]
  We introduce a differentiable inductive logic programming model, called differentiable first-order rule learner (DFOL) DFOL finds the correct LPs from relational facts by searching for the interpretable matrix representations of LPs. Experimental results indicate that DFOL is a precise, robust, scalable, and computationally cheap differentiable ILP model.
  arXiv  Detail & Related papers  (2022-04-28T15:33:43Z)
• NSL: Hybrid Interpretable Learning From Noisy Raw Data [66.15862011405882]
  This paper introduces a hybrid neural-symbolic learning framework, called NSL, that learns interpretable rules from labelled unstructured data. NSL combines pre-trained neural networks for feature extraction with FastLAS, a state-of-the-art ILP system for rule learning under the answer set semantics. We demonstrate that NSL is able to learn robust rules from MNIST data and achieve comparable or superior accuracy when compared to neural network and random forest baselines.
  arXiv  Detail & Related papers  (2020-12-09T13:02:44Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)
• Distance and Equivalence between Finite State Machines and Recurrent Neural Networks: Computational results [0.348097307252416]
  We show some results related to the problem of extracting Finite State Machine based models from trained RNN Language models. Our reduction technique from 3-SAT makes this latter fact easily generalizable to other RNN architectures.
  arXiv  Detail & Related papers  (2020-04-01T14:48:59Z)
• Supervised Learning for Non-Sequential Data: A Canonical Polyadic Decomposition Approach [85.12934750565971]
  Efficient modelling of feature interactions underpins supervised learning for non-sequential tasks. To alleviate this issue, it has been proposed to implicitly represent the model parameters as a tensor. For enhanced expressiveness, we generalize the framework to allow feature mapping to arbitrarily high-dimensional feature vectors.
  arXiv  Detail & Related papers  (2020-01-27T22:38:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.