Related papers: A BERT-based Distractor Generation Scheme with Mul…

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…

Large language models (LLMs) have shown remarkable success across a wide range of natural language generation tasks, where proper prompt designs make great impacts. While existing prompting methods are normally restricted to providing…

Multiple choice questions (MCQs) are a popular method for evaluating students' knowledge due to their efficiency in administration and grading. Crafting high-quality math MCQs is a labor-intensive process that requires educators to…

Generative Adversarial Networks (GANs) produce impressive results on unconditional image generation when powered with large-scale image datasets. Yet generated images are still easy to spot especially on datasets with high variance (e.g.…

Generative Adversarial Networks (GANs) can successfully approximate a probability distribution and produce realistic samples. However, open questions such as sufficient convergence conditions and mode collapse still persist. In this paper,…

The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data. However, when different metrics are used for comparing the methods…

Machine learning approaches now achieve impressive generation capabilities in numerous domains such as image, audio or video. However, most training \& evaluation frameworks revolve around the idea of strictly modelling the original data…

Generating diverse sequences is important in many NLP applications such as question generation or summarization that exhibit semantically one-to-many relationships between source and the target sequences. We present a method to explicitly…

Training generative adversarial networks is unstable in high-dimensions as the true data distribution tends to be concentrated in a small fraction of the ambient space. The discriminator is then quickly able to classify nearly all generated…

Question Generation (QG), the task of automatically generating questions from a source input, has seen significant progress in recent years. Difficulty-controllable QG (DCQG) enables control over the difficulty level of generated questions…

Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…

Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to successfully complete conversations. Recent state-of-the-art DST implementations rely on schemata of diverse services to improve model robustness and handle…

In this study, we implement a novel BERT architecture for multitask fine-tuning on three downstream tasks: sentiment classification, paraphrase detection, and semantic textual similarity prediction. Our model, Multitask BERT, incorporates…

Neural generative models have become popular and achieved promising performance on short-text conversation tasks. They are generally trained to build a 1-to-1 mapping from the input post to its output response. However, a given post is…

Question generation (QG) attempts to solve the inverse of question answering (QA) problem by generating a natural language question given a document and an answer. While sequence to sequence neural models surpass rule-based systems for QG,…

While participants in a multi-party multi-turn conversation simultaneously engage in multiple conversation topics, existing response selection methods are developed mainly focusing on a two-party single-conversation scenario. Hence, the…

Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents. Such a model is useful in generating clarifying options. However, a naive model trained only using the targeted…

NLP-powered automatic question generation (QG) techniques carry great pedagogical potential of saving educators' time and benefiting student learning. Yet, QG systems have not been widely adopted in classrooms to date. In this work, we aim…

Generative deep learning systems offer powerful tools for artefact generation, given their ability to model distributions of data and generate high-fidelity results. In the context of computational creativity, however, a major shortcoming…

Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…