Related papers: Adversarial Learning for Neural Dialogue Generatio…

Generating adversarial examples for natural language is hard, as natural language consists of discrete symbols, and examples are often of variable lengths. In this paper, we propose a geometry-inspired attack for generating natural language…

We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled…

While deep learning in the form of recurrent neural networks (RNNs) has caused a significant improvement in neural language modeling, the fact that they are extremely prone to overfitting is still a mainly unresolved issue. In this paper we…

Adversarial training, a method for learning robust deep neural networks, constructs adversarial examples during training. However, recent methods for generating NLP adversarial examples involve combinatorial search and expensive sentence…

Deep generative models are rapidly becoming a common tool for researchers and developers. However, as exhaustively shown for the family of discriminative models, the test-time inference of deep neural networks cannot be fully controlled and…

Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs against certain criteria (e.g.,…

Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training…

Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate human behavior remains a significant challenge. An effective simulator must expose the failure…

Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…

Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle this problem, we…

Dialog policies, which determine a system's action based on the current state at each dialog turn, are crucial to the success of the dialog. In recent years, reinforcement learning (RL) has emerged as a promising option for dialog policy…

Many natural language related applications involve text generation, created by humans or machines. While in many of those applications machines support humans, yet in few others, (e.g. adversarial machine learning, social bots and trolls)…

A common training technique for language models is teacher forcing (TF). TF attempts to match human language exactly, even though identical meanings can be expressed in different ways. This motivates use of sequence-level objectives for…

To predict what someone will say is to model how they think. We study this through next-turn dialogue prediction: given a conversation, predict the next utterance produced by a person. We compare learning approaches along two dimensions:…

Adversarial examples are some special input that can perturb the output of a deep neural network, in order to make produce intentional errors in the learning algorithms in the production environment. Most of the present methods for…

The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in…

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…

Recent progress on neural approaches for language processing has triggered a resurgence of interest on building intelligent open-domain chatbots. However, even the state-of-the-art neural chatbots cannot produce satisfying responses for…

Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs, for which effective test cases are a critical bottleneck. Existing test generation methods, whether based on prompting or supervised…

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…