Memory-Augmented Generative Adversarial Transformers
Conversational AI systems that rely on Large Language Models, like Transformers, have difficulty interweaving external data (like facts) with the language they generate. Vanilla Transformer architectures are not designed for answering factual questions with high accuracy. This paper investigates a possible route for addressing this problem. We propose to extend the standard Transformer architecture with an additional memory bank holding extra information (such as facts drawn from a knowledge base), and an extra attention layer for addressing this memory. We add this augmented memory to a Generative Adversarial Network-inspired Transformer architecture. This setup allows for implementing arbitrary felicity conditions on the generated language of the Transformer. We first demonstrate how this machinery can be deployed for handling factual questions in goal-oriented dialogues. Secondly, we demonstrate that our approach can be useful for applications like {\it style adaptation} as well: the adaptation of utterances according to certain stylistic (external) constraints, like social properties of human interlocutors in dialogues.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Memory Augmented Generative Adversarial Networks for Anomaly Detection
In this paper, we present a memory-augmented algorithm for anomaly detection. Classical anomaly detection algorithms focus on learning to model and generate normal data, but typically guarantees for detecting anomalous d…
Anomaly DetectionTask Specific Visual Saliency Prediction with Memory Augmented Conditional Generative Adversarial Networks
Visual saliency patterns are the result of a variety of factors aside from the image being parsed, however existing approaches have ignored these. To address this limitation, we propose a novel saliency estimation model …
Saliency PredictionToward generalizable learning of all (linear) first-order methods via memory augmented Transformers
We show that memory-augmented Transformers can implement the entire class of linear first-order methods (LFOMs), a class that contains gradient descent (GD) and more advanced methods such as conjugate gradient descent (C…
AllMixture-of-ExpertsTest-time AdaptationSpotFast Networks with Memory Augmented Lateral Transformers for Lipreading
This paper presents a novel deep learning architecture for word-level lipreading. Previous works suggest a potential for incorporating a pretrained deep 3D Convolutional Neural Networks as a front-end feature extractor. …
Action RecognitionLipreadingMemory Augmented Deep Generative models for Forecasting the Next Shot Location in Tennis
This paper presents a novel framework for predicting shot location and type in tennis. Inspired by recent neuroscience discoveries we incorporate neural memory modules to model the episodic and semantic memory components…
Generative Adversarial Network