Related papers: Low-Resource Response Generation with Template Pri…

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using…

Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have…

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning…

Accurate knowledge selection is critical in knowledge-grounded dialogue systems. Towards a closer look at it, we offer a novel perspective to organize existing literature, i.e., knowledge selection coupled with, after, and before…

When provided with sufficient explanatory context, smaller Language Models have been shown to exhibit strong reasoning ability on challenging short-answer question-answering tasks where the questions are unseen in training. We evaluate two…

Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning,…

There has been a growing interest in statistical inference from data satisfying the so-called manifold hypothesis, assuming data points in the high-dimensional ambient space to lie in close vicinity of a submanifold of much lower dimension.…

Temporal gates play a significant role in modern recurrent-based neural encoders, enabling fine-grained control over recursive compositional operations over time. In recurrent models such as the long short-term memory (LSTM), temporal gates…

Large scale Pre-trained Language Models have proven to be very powerful approach in various Natural language tasks. OpenAI's GPT-2 \cite{radford2019language} is notable for its capability to generate fluent, well formulated, grammatically…

Patterns are fundamental to human cognition, enabling the recognition of structure and regularity across diverse domains. In this work, we focus on structural repeats, patterns that arise from the repetition of hierarchical relations within…

Modern generative pre-trained language models excel at open-ended text generation, yet continue to underperform on structure-related tasks such as NER, relation extraction, and semantic role labeling, especially when compared to…

Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…

We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a…

Data-to-text generation has recently attracted substantial interests due to its wide applications. Existing methods have shown impressive performance on an array of tasks. However, they rely on a significant amount of labeled data for each…

We study multi-turn response generation for open-domain dialogues. The existing state-of-the-art addresses the problem with deep neural architectures. While these models improved response quality, their complexity also hinders the…

Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generation process.…

Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the lack…

This paper explores the task of translating natural language queries into regular expressions which embody their meaning. In contrast to prior work, the proposed neural model does not utilize domain-specific crafting, learning to translate…

Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting responses. Attempts to boost informativeness alone come at the…

Named entity recognition (NER) models generally perform poorly when large training datasets are unavailable for low-resource domains. Recently, pre-training a large-scale language model has become a promising direction for coping with the…