Related papers: DAL: Dual Adversarial Learning for Dialogue Genera…
This paper presents a new adversarial learning method for generative conversational agents (GCA) besides a new model of GCA. Similar to previous works on adversarial learning for dialogue generation, our method assumes the GCA as a…
The generative adversarial networks (GANs) have facilitated the development of speech enhancement recently. Nevertheless, the performance advantage is still limited when compared with state-of-the-art models. In this paper, we propose a…
Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems with opposite objectives: NLU tackles the transformation from natural language to…
Having engaging and informative conversations with users is the utmost goal for open-domain conversational systems. Recent advances in transformer-based language models and their applications to dialogue systems have succeeded to generate…
Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a…
In unsupervised data generation tasks, besides the generation of a sample based on previous observations, one would often like to give hints to the model in order to bias the generation towards desirable metrics. We propose a method that…
Generative adversarial learning is a popular new approach to training generative models which has been proven successful for other related problems as well. The general idea is to maintain an oracle $D$ that discriminates between the…
Generative adversarial networks (GAN) have been effective for learning generative models for real-world data. However, existing GANs (GAN and its variants) tend to suffer from training problems such as instability and mode collapse. In this…
Generative adversarial nets (GANs) are a promising technique for modeling a distribution from samples. It is however well known that GAN training suffers from instability due to the nature of its maximin formulation. In this paper, we…
Traditional CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs). Existing adversarial attack methods often rely…
Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes. Modeling…
We aim to overcome the lack of diversity in responses of current dialogue systems and to develop a dialogue system that is engaging as a conversational partner. We propose a generator-evaluator model that evaluates multiple responses…
As a revolutionary generative paradigm of deep learning, generative adversarial networks (GANs) have been widely applied in various fields to synthesize realistic data. However, it is challenging for conventional GANs to synthesize raw…
Human conversation is a complex mechanism with subtle nuances. It is hence an ambitious goal to develop artificial intelligence agents that can participate fluently in a conversation. While we are still far from achieving this goal, recent…
Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge. As Generative Adversarial Networks (GANs) are able to…
Dynamic adversarial question generation, where humans write examples to stump a model, aims to create examples that are realistic and informative. However, the advent of large language models (LLMs) has been a double-edged sword for human…
Advanced biological intelligence learns efficiently from an information-rich stream of stimulus information, even when feedback on behaviour quality is sparse or absent. Such learning exploits implicit assumptions about task domains. We…
In the past decades, intensive efforts have been put to design various loss functions and metric forms for metric learning problem. These improvements have shown promising results when the test data is similar to the training data. However,…
Besides the well-known classification task, these days neural networks are frequently being applied to generate or transform data, such as images and audio signals. In such tasks, the conventional loss functions like the mean squared error…
Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However,…