Related papers: Pneg: Prompt-based Negative Response Generation fo…

Moving from limited-domain natural language generation (NLG) to open domain is difficult because the number of semantic input combinations grows exponentially with the number of domains. Therefore, it is important to leverage existing…

It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differentiable. The existing training strategies either suffer…

Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversity often fail to capture the semantic diversity of generated…

Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this systems-fathoming how and when neural-based systems fail in such cases is critical…

Automatic question generation according to an answer within the given passage is useful for many applications, such as question answering system, dialogue system, etc. Current neural-based methods mostly take two steps which extract several…

Response generation is one of the critical components in task-oriented dialog systems. Existing studies have shown that large pre-trained language models can be adapted to this task. The typical paradigm of adapting such extremely large…

Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, search, and dialogue. In this…

Matching model is essential for Image-Text Retrieval framework. Existing research usually train the model with a triplet loss and explore various strategy to retrieve hard negative sentences in the dataset. We argue that current…

In comparison to the interpretation of classification models, the explanation of sequence generation models is also an important problem, however it has seen little attention. In this work, we study model-agnostic explanations of a…

Despite recent progress, state-of-the-art question answering models remain vulnerable to a variety of adversarial attacks. While dynamic adversarial data collection, in which a human annotator tries to write examples that fool a…

Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the…

Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey…

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets (GAN) that…

In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algorithms, IAT…

In this paper, we focus on the task of generating a pun sentence given a pair of word senses. A major challenge for pun generation is the lack of large-scale pun corpus to guide the supervised learning. To remedy this, we propose an…

The Visual Dialogue task requires an agent to engage in a conversation about an image with a human. It represents an extension of the Visual Question Answering task in that the agent needs to answer a question about an image, but it needs…

Automated evaluation of open domain natural language generation (NLG) models remains a challenge and widely used metrics such as BLEU and Perplexity can be misleading in some cases. In our paper, we propose to evaluate natural language…

Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a classifier at hand. An attacker introduces specially crafted adversarial samples to a deployed classifier, which are being…

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…

In recent years, the generation of conversation content based on deep neural networks has attracted many researchers. However, traditional neural language models tend to generate general replies, lacking logical and emotional factors. This…