Related papers: Leveraging Few-Shot Data Augmentation and Waterfal…

Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields…

End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus. However, one of the fatal drawbacks in such approaches is that they are unable to generate…

This study presents a novel generative modeling approach to rainfall-runoff modeling, focusing on the synthesis of realistic daily catchment runoff time series in response to catchment-averaged climate forcing. Unlike traditional…

Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation…

Automatic question generation aims at the generation of questions from a context, with the corresponding answers being sub-spans of the given passage. Whereas, most of the methods mostly rely on heuristic rules to generate questions, more…

The traditional data annotation process is often labor-intensive, time-consuming, and susceptible to human bias, which complicates the management of increasingly complex datasets. This study explores the potential of large language models…

Large language models (LLMs) can be used as accessible and intelligent chatbots by constructing natural language queries and directly inputting the prompt into the large language model. However, different prompt' constructions often lead to…

Conversational query rewriting aims to reformulate a concise conversational query to a fully specified, context-independent query that can be effectively handled by existing information retrieval systems. This paper presents a few-shot…

Data augmentation has been shown to effectively improve the performance of multimodal machine learning models. This paper introduces a generative model for data augmentation by leveraging the correlations among multiple modalities.…

Existing work on generating hints in Intelligent Tutoring Systems (ITS) focuses mostly on manual and non-personalized feedback. In this work, we explore automatically generated questions as personalized feedback in an ITS. Our personalized…

While recent neural text-to-speech (TTS) systems perform remarkably well, they typically require a substantial amount of recordings from the target speaker reading in the desired speaking style. In this work, we present a novel 3-step…

We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a…

Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few…

Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-of-domain detection, require extensive and flexible datasets for experiments and evaluation. As…

Augmenting large language models (LLMs) with user-specific knowledge is crucial for real-world applications, such as personal AI assistants. However, LLMs inherently lack mechanisms for prompt-driven knowledge capture. This paper…

Using a sequence-to-sequence framework, many neural conversation models for chit-chat succeed in naturalness of the response. Nevertheless, the neural conversation models tend to give generic responses which are not specific to given…

The training of task-oriented dialogue systems is often confronted with the lack of annotated data. In contrast to previous work which augments training data through expensive crowd-sourcing efforts, we propose four different automatic…

Task-oriented dialogue systems use four connected modules, namely, Natural Language Understanding (NLU), a Dialogue State Tracking (DST), Dialogue Policy (DP) and Natural Language Generation (NLG). A research challenge is to learn each…

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…

Human educators possess an intrinsic ability to anticipate and seek educational explanations from students, which drives them to pose thought-provoking questions when students cannot articulate these explanations independently. We aim to…