Related papers: A Simple and Efficient Multi-Task Learning Approac…

Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills. This however often leads to low sample efficiency, requiring a large amount of interaction…

Task-oriented dialogues often require agents to enact complex, multi-step procedures in order to meet user requests. While large language models have found success automating these dialogues in constrained environments, their widespread…

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…

Generating stylized responses is essential to build intelligent and engaging dialogue systems. However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, especially when the…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Real-world text classification tasks often require many labeled training examples that are expensive to obtain. Recent advancements in machine teaching, specifically the data programming paradigm, facilitate the creation of training data…

Multi-task learning of deformable object manipulation is a challenging problem in robot manipulation. Most previous works address this problem in a goal-conditioned way and adapt goal images to specify different tasks, which limits the…

Large-scale visual language models are widely used as pre-trained models and then adapted for various downstream tasks. While humans are known to efficiently learn new tasks from a few examples, deep learning models struggle with adaptation…

For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on…

Reinforcement learning requires interaction with an environment, which is expensive for robots. This constraint necessitates approaches that work with limited environmental interaction by maximizing the reuse of previous experiences. We…

Response generation for task-oriented dialogues involves two basic components: dialogue planning and surface realization. These two components, however, have a discrepancy in their objectives, i.e., task completion and language quality. To…

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…

Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a…

We compare different models for low resource multi-task sequence tagging that leverage dependencies between label sequences for different tasks. Our analysis is aimed at datasets where each example has labels for multiple tasks. Current…

Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these…

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for…

We present a knowledge-grounded dialog system developed for the ninth Dialog System Technology Challenge (DSTC9) Track 1 - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access. We leverage transfer…

This paper studies multi-task training of retrieval-augmented generation models for knowledge-intensive tasks. We propose to clean the training set by utilizing a distinct property of knowledge-intensive generation: The connection of…

In open-domain dialogue response generation, a dialogue context can be continued with diverse responses, and the dialogue models should capture such one-to-many relations. In this work, we first analyze the training objective of dialogue…

Self-rationalizing models that also generate a free-text explanation for their predicted labels are an important tool to build trustworthy AI applications. Since generating explanations for annotated labels is a laborious and costly pro…