Learning Transductions and Alignments with RNN Seq2seq Models

• URL: http://arxiv.org/abs/2303.06841v4
• Date: Sun, 21 Apr 2024 14:45:00 GMT
• Title: Learning Transductions and Alignments with RNN Seq2seq Models
• Authors: Zhengxiang Wang,
• Abstract summary: We study the capabilities of Recurrent-Neural-Network sequence to sequence (RNN seq2seq) models in learning four transduction tasks. We find that RNN seq2seq models are only able to approximate a mapping that fits the training or in-distribution data, instead of learning the underlying functions.
• Score: 0.8158530638728501
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The paper studies the capabilities of Recurrent-Neural-Network sequence to sequence (RNN seq2seq) models in learning four transduction tasks: identity, reversal, total reduplication, and quadratic copying. These transductions are traditionally well studied under finite state transducers and attributed with increasing complexity. We find that RNN seq2seq models are only able to approximate a mapping that fits the training or in-distribution data, instead of learning the underlying functions. Although attention makes learning more efficient and robust, it does not overcome the out-of-distribution generalization limitation. We establish a novel complexity hierarchy for learning the four tasks for attention-less RNN seq2seq models, which may be understood in terms of the complexity hierarchy of formal languages, instead of string transductions. RNN variants also play a role in the results. In particular, we show that Simple RNN seq2seq models cannot count the input length.

Related papers

• Attention as an RNN [66.5420926480473]
  We show that attention can be viewed as a special Recurrent Neural Network (RNN) with the ability to compute its textitmany-to-one RNN output efficiently. We introduce a new efficient method of computing attention's textitmany-to-many RNN output based on the parallel prefix scan algorithm. We show Aarens achieve comparable performance to Transformers on $38$ datasets spread across four popular sequential problem settings.
  arXiv  Detail & Related papers  (2024-05-22T19:45:01Z)
• Learning Useful Representations of Recurrent Neural Network Weight Matrices [30.583752432727326]
  Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. How to learn useful representations of RNN weights that facilitate RNN analysis as well as downstream tasks? We consider several mechanistic approaches for RNN weights and adapt the permutation equivariant Deep Weight Space layer for RNNs. Our two novel functionalist approaches extract information from RNN weights by 'interrogating' the RNN through probing inputs.
  arXiv  Detail & Related papers  (2024-03-18T17:32:23Z)
• Quantized Approximately Orthogonal Recurrent Neural Networks [6.524758376347808]
  We explore the quantization of the weight matrices in ORNNs, leading to Quantized approximately Orthogonal RNNs (QORNNs) We propose and investigate two strategies to learn QORNN by combining quantization-aware training (QAT) and computation projections. The most efficient models achieve results similar to state-of-the-art full-precision ORNN, LSTM and FastRNN on a variety of standard benchmarks, even with 4-bits quantization.
  arXiv  Detail & Related papers  (2024-02-05T09:59:57Z)
• Recurrent Neural Language Models as Probabilistic Finite-state Automata [66.23172872811594]
  We study what classes of probability distributions RNN LMs can represent. We show that simple RNNs are equivalent to a subclass of probabilistic finite-state automata. These results present a first step towards characterizing the classes of distributions RNN LMs can represent.
  arXiv  Detail & Related papers  (2023-10-08T13:36:05Z)
• On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networks [59.85314067235965]
  We extend the theoretical foundation for the $2nd$-order recurrent network ($2nd$ RNN) We prove there exists a class of a $2nd$ RNN that is Turing-complete with bounded time. We also demonstrate that $2$nd order RNNs, without memory, outperform modern-day models such as vanilla RNNs and gated recurrent units in recognizing regular grammars.
  arXiv  Detail & Related papers  (2023-09-26T06:06:47Z)
• Hierarchical Phrase-based Sequence-to-Sequence Learning [94.10257313923478]
  We describe a neural transducer that maintains the flexibility of standard sequence-to-sequence (seq2seq) models while incorporating hierarchical phrases as a source of inductive bias during training and as explicit constraints during inference. Our approach trains two models: a discriminative derivation based on a bracketing grammar whose tree hierarchically aligns source and target phrases, and a neural seq2seq model that learns to translate the aligned phrases one-by-one.
  arXiv  Detail & Related papers  (2022-11-15T05:22:40Z)
• Learning Hierarchical Structures with Differentiable Nondeterministic Stacks [25.064819128982556]
  We present a stack RNN model based on the recently proposed Nondeterministic Stack RNN (NS-RNN) We show that the NS-RNN achieves lower cross-entropy than all previous stack RNNs on five context-free language modeling tasks. We also propose a restricted version of the NS-RNN that makes it practical to use for language modeling on natural language.
  arXiv  Detail & Related papers  (2021-09-05T03:25:23Z)
• Learning and Generalization in RNNs [11.107204912245841]
  We prove that simple recurrent neural networks can learn functions of sequences. New ideas enable us to extract information from the hidden state of the RNN in our proofs.
  arXiv  Detail & Related papers  (2021-05-31T18:27:51Z)
• Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units [86.9207811656179]
  We show that memory-augmented neural networks (NNs) can achieve higher-order, memory-augmented extrapolation, stable performance, and faster convergence. Our models achieve a 1.53% average improvement over current state-of-the-art methods in equation verification and achieve a 2.22% Top-1 average accuracy and 2.96% Top-5 average accuracy for equation completion.
  arXiv  Detail & Related papers  (2021-04-07T03:50:11Z)
• A Formal Hierarchy of RNN Architectures [88.38859874233944]
  hierarchy is based on two formal properties: space, which measures the RNN's memory, and rational recurrence, defined as whether the recurrent update can be described by a weighted finite-state machine. We show how these models' expressive capacity is expanded by stacking multiple layers or composing them with different pooling functions. We hypothesize that the practical learnable capacity of unsaturated RNNs obeys a similar hierarchy.
  arXiv  Detail & Related papers  (2020-04-18T00:57:54Z)

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.