Related papers: LEATHER: A Framework for Learning to Generate Huma…
To efficiently select optimal dataset combinations for enhancing multi-task learning (MTL) performance in large language models, we proposed a novel framework that leverages a neural network to predict the best dataset combinations. The…
We present a comparison of word-based and character-based sequence-to-sequence models for data-to-text natural language generation, which generate natural language descriptions for structured inputs. On the datasets of two recent generation…
Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions and/or relying on contextual cues and common-sense…
Along with the development of systems for natural language understanding and generation, dialog systems have been widely adopted for language learning and practicing. Many current educational dialog systems perform chitchat, where the…
We seek to create agents that both act and communicate with other agents in pursuit of a goal. Towards this end, we extend LIGHT (Urbanek et al. 2019) -- a large-scale crowd-sourced fantasy text-game -- with a dataset of quests. These…
Previous research on multi-party dialogue generation has predominantly leveraged structural information inherent in dialogues to directly inform the generation process. However, the prevalence of colloquial expressions and incomplete…
This paper explores educational interactions involving humans and artificial intelligences not as sequences of prompts and responses, but as a social process of conversation and exploration. In this conception, learners continually converse…
Language carries thought and coordination among humans but rarely reaches further along the spectrum of diverse intelligence. Yet non-neural systems -- from gene regulatory networks and microbial consortia to fungi -- are increasingly…
We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums. Our agents operate in LIGHT (Urbanek et al. 2019) -- a large-scale crowd-sourced fantasy text adventure game wherein…
Recent trends in natural language processing using pretraining have shifted focus towards pretraining and fine-tuning approaches for text generation. Often the focus has been on task-agnostic approaches that generalize the language modeling…
Large Language Models (LLMs), when used for conditional text generation, often produce hallucinations, i.e., information that is unfaithful or not grounded in the input context. This issue arises in typical conditional text generation…
The development of chatbots requires collecting a large number of human-chatbot dialogues to reflect the breadth of users' sociodemographic backgrounds and conversational goals. However, the resource requirements to conduct the respective…
In our dynamic world where data arrives in a continuous stream, continual learning enables us to incrementally add new tasks/domains without the need to retrain from scratch. A major challenge in continual learning of language model is…
Digital learning platforms enable students to learn on a flexible and individual schedule as well as providing instant feedback mechanisms. The field of STEM education requires students to solve numerous training exercises to grasp…
Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…
Building a dialogue system that can communicate naturally with humans is a challenging yet interesting problem of agent-based computing. The rapid growth in this area is usually hindered by the long-standing problem of data scarcity as…
Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…
In this paper, a novel Generation-Evaluation framework is developed for multi-turn conversations with the objective of letting both participants know more about each other. For the sake of rational knowledge utilization and coherent…
Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently…
Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…