Neural Network Token Segmentation for Sequence Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current neural network training methods for generating output sequences are limited in accuracy and computational efficiency, particularly in tasks like translation and speech recognition, as they assume a fixed output sequence decomposition and are computationally expensive due to long decoder lengths.

Innovation Solution

A method for training neural networks to generate score distributions over sets of tokens including n-grams of multiple sizes, where the networks process inputs to adjust parameters based on valid decompositions of target sequences, allowing for more accurate and efficient generation of output sequences by conditioning on network inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If neural networks use fixed output sequence decomposition, then training is simpler, but accuracy is limited

Engineering Contradiction:
ImproveaccuracyVSAvoidtraining complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies dynamics by transforming the fixed decomposition approach into a dynamic one where the decomposition is learned adaptively during training. The network learns to decompose output sequences into variable-length tokens based on the input context, allowing the decomposition structure to change and optimize for each specific translation task rather than being predetermined.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent applies segmentation by dividing the output sequence into multiple variable-length tokens (subwords, characters, or complete words) that can be dynamically determined during training. This segmentation allows the network to learn optimal token boundaries and representations, improving accuracy while managing complexity through structured tokenization.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If neural networks process long decoder sequences, then complete output sequences are generated, but computational cost increases

Engineering Contradiction:
Improveoutput qualityVSAvoidcomputational efficiency
Core Design Contradiction:
Measurement precisionVSPower

Solution Approach 1:

The patent applies segmentation by dividing long decoder sequences into shorter variable-length tokens. Instead of processing entire long sequences as single units, the network processes segmented tokens that can be dynamically adjusted in length, reducing the computational burden while maintaining the ability to generate complete output sequences.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies dynamics by making token lengths adaptive rather than fixed. The network learns to adjust token lengths dynamically based on the input sequence and translation requirements, allowing shorter tokens for complex regions and longer tokens for simpler regions, thereby optimizing computational efficiency while maintaining output quality.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If neural networks use variable token lengths, then accuracy improves, but training complexity increases

Engineering Contradiction:
Improvetranslation accuracyVSAvoidtraining complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies segmentation by introducing a structured tokenization system that divides output sequences into variable-length tokens with defined boundaries and representations. This structured approach to segmentation provides a framework that manages training complexity while enabling the network to learn optimal variable-length token representations for improved translation accuracy.

Inventive Principle:
Principle #1Segmentation

4Productivity

If neural networks generate sequences quickly, then productivity improves, but accuracy may decrease

Engineering Contradiction:
Improvegeneration speedVSAvoidoutput accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies dynamics by making the tokenization strategy adaptive and context-dependent. The network learns to dynamically adjust token lengths and boundaries based on the specific translation requirements, allowing it to generate sequences quickly for simple cases while maintaining high accuracy for complex cases by using more granular token representations when needed.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS11182566B2Processing text sequences using neural networks
Publication Date: 2021.11.23 GOOGLE LLC
  • US11182566B2 patent drawing
  • US11182566B2 patent drawing
  • US11182566B2 patent drawing

AI summary

A computer-implemented method for training a neural network that is configured to generate a score distribution over a set of multiple output positions. The neural network is configured to process a network input to generate a respective score distribution for each of a plurality of output positions including a respective score for each token in a predetermined set of tokens that includes n-grams of multiple different sizes. Example methods described herein provide trained neural networks which produce results with improved accuracy compared to the state of the art, e.g. translations that are more accurate compared to the state of the art, or more accurate speech recognition compared to the state of the art.