Zobrazeno 1 - 10
of 127
pro vyhledávání: '"Choi Jinho D"'
The challenge of defining a slot schema to represent the state of a task-oriented dialogue system is addressed by Slot Schema Induction (SSI), which aims to automatically induce slots from unlabeled dialogue data. Whereas previous approaches induce s
Externí odkaz:
http://arxiv.org/abs/2408.01638
ESM+: Modern Insights into Perspective on Text-to-SQL Evaluation in the Age of Large Language Models
The task of Text-to-SQL enables anyone to retrieve information from SQL databases using natural language. Despite several challenges, recent models have made remarkable advancements in this task using large language models (LLMs). Interestingly, we f
Externí odkaz:
http://arxiv.org/abs/2407.07313
Autor:
Finch, Sarah E., Choi, Jinho D.
Open-domain dialogue systems need to grasp social commonsense to understand and respond effectively to human users. Commonsense-augmented dialogue models have been proposed that aim to infer commonsense knowledge from dialogue contexts in order to im
Externí odkaz:
http://arxiv.org/abs/2406.09138
Autor:
Finch, James D., Choi, Jinho D.
We demonstrate substantial performance gains in zero-shot dialogue state tracking (DST) by enhancing training data diversity through synthetic data generation. Existing DST datasets are severely limited in the number of application domains and slot t
Externí odkaz:
http://arxiv.org/abs/2405.12468
Autor:
Tu, Sichang, Powers, Abigail, Merrill, Natalie, Fani, Negar, Carter, Sierra, Doogan, Stephen, Choi, Jinho D.
The shortage of clinical workforce presents significant challenges in mental healthcare, limiting access to formal diagnostics and services. We aim to tackle this shortage by integrating a customized large language model (LLM) into the workflow, thus
Externí odkaz:
http://arxiv.org/abs/2405.11178
Bias is a disproportionate prejudice in favor of one side against another. Due to the success of transformer-based Masked Language Models (MLMs) and their impact on many NLP tasks, a systematic evaluation of bias in these models is needed more than e
Externí odkaz:
http://arxiv.org/abs/2404.06621
Factual inconsistencies pose a significant hurdle for the faithful summarization by generative models. While a major direction to enhance inconsistency detection is to derive stronger Natural Language Inference (NLI) models, we propose an orthogonal
Externí odkaz:
http://arxiv.org/abs/2402.12821
Autor:
Finch, Sarah E., Choi, Jinho D.
Mastering commonsense understanding and reasoning is a pivotal skill essential for conducting engaging conversations. While there have been several attempts to create datasets that facilitate commonsense inferences in dialogue contexts, existing data
Externí odkaz:
http://arxiv.org/abs/2401.15471
Autor:
Shin, Jaemin, Yoon, Hyungjun, Lee, Seungjoo, Park, Sungjoon, Liu, Yunxin, Choi, Jinho D., Lee, Sung-Ju
Psychiatrists diagnose mental disorders via the linguistic use of patients. Still, due to data privacy, existing passive mental health monitoring systems use alternative features such as activity, app usage, and location via mobile devices. We propos
Externí odkaz:
http://arxiv.org/abs/2310.16538
Human evaluation has been widely accepted as the standard for evaluating chat-oriented dialogue systems. However, there is a significant variation in previous work regarding who gets recruited as evaluators. Evaluator groups such as domain experts, u
Externí odkaz:
http://arxiv.org/abs/2309.07998