[HTML][HTML] Crafting a museum guide using ChatGPT4

G Trichopoulos, M Konstantakis, G Caridakis… - Big Data and Cognitive …, 2023‏ - mdpi.com
This paper introduces a groundbreaking approach to enriching the museum experience
using ChatGPT4, a state-of-the-art language model by OpenAI. By develo** a museum …

Advancing naturalistic affective science with deep learning

C Lin, LS Bulls, LJ Tepfer, AD Vyas, MA Thornton - Affective Science, 2023‏ - Springer
People express their own emotions and perceive others' emotions via a variety of channels,
including facial movements, body gestures, vocal prosody, and language. Studying these …

Spoken‐to‐written text conversion for enhancement of Korean–English readability and machine translation

HJ Choi, M Choi, S Kim, Y Lim, M Lee, S Yun… - ETRI …, 2024‏ - Wiley Online Library
The Korean language has written (formal) and spoken (phonetic) forms that differ in their
application, which can lead to confusion, especially when dealing with numbers and …

K-nct: Korean neural grammatical error correction gold-standard test set using novel error type classification criteria

S Koo, C Park, J Seo, S Lee, H Moon, J Lee… - IEEE Access, 2022‏ - ieeexplore.ieee.org
Recently, active research has been conducted on Korean grammatical error correction on
machine translation (MT) and automatic noise generation. However, there is no gold …

Uncovering the risks and drawbacks associated with the use of synthetic data for grammatical error correction

S Koo, C Park, S Lee, J Seo, S Eo, H Moon… - IEEE Access, 2023‏ - ieeexplore.ieee.org
In a Data-Centric AI paradigm, the model performance is enhanced without altering the
model architecture, as evidenced by real-world and benchmark dataset demonstrations …

KEBAP: Korean Error Explainable Benchmark Dataset for ASR and Post-processing

S Koo, C Park, J Kim, J Seo, S Eo… - Proceedings of the …, 2023‏ - aclanthology.org
Abstract Automatic Speech Recognition (ASR) systems are instrumental across various
applications, with their performance being critically tied to user satisfaction. Conventional …

AI for patents: A novel yet effective and efficient framework for patent analysis

J Son, H Moon, J Lee, S Lee, C Park, W Jung… - IEEE Access, 2022‏ - ieeexplore.ieee.org
Patents provide inventors exclusive rights to their inventions by protecting their intellectual
property rights. However, analyzing patent documents generally requires knowledge of …

Back transcription as a method for evaluating robustness of natural language understanding models to speech recognition errors

M Kubis, P Skórzewski, M Sowański… - arxiv preprint arxiv …, 2023‏ - arxiv.org
In a spoken dialogue system, an NLU model is preceded by a speech recognition system
that can deteriorate the performance of natural language understanding. This paper …

UAV path planning in multi-task environments with risks through natural language understanding

C Wang, Z Zhong, X **ang, Y Zhu, L Wu, D Yin, J Li - Drones, 2023‏ - mdpi.com
Path planning using handcrafted waypoints is inefficient for a multi-task UAV operating in
dynamic environments with potential risks such as bad weather, obstacles, or forbidden …

Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing

C Park, J Seo, S Lee, J Son, H Moon, S Eo… - Findings of the …, 2024‏ - aclanthology.org
The recent advancements in the realm of Automatic Speech Recognition (ASR) post-
processing have been primarily driven by sequence-to-sequence paradigms. Despite their …