Zobrazeno 1 - 10
of 759
pro vyhledávání: '"Tran, Quan"'
Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated directly int
Externí odkaz:
http://arxiv.org/abs/2408.07465
Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models
Autor:
Nguyen, Minh, Dernoncourt, Franck, Yoon, Seunghyun, Deilamsalehy, Hanieh, Tan, Hao, Rossi, Ryan, Tran, Quan Hung, Bui, Trung, Nguyen, Thien Huu
We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of text-based spea
Externí odkaz:
http://arxiv.org/abs/2407.12094
Foundational models (FMs), pretrained on extensive datasets using self-supervised techniques, are capable of learning generalized patterns from large amounts of data. This reduces the need for extensive labeled datasets for each new task, saving both
Externí odkaz:
http://arxiv.org/abs/2406.09837
Autor:
Le, Hung, Tran, Quan, Nguyen, Dung, Do, Kien, Mittal, Saloni, Ogueji, Kelechi, Venkatesh, Svetha
How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingly while ensuring that updates do not deviate too far from a reference
Externí odkaz:
http://arxiv.org/abs/2405.16388
Autor:
Kim, Hyunjae, Yoon, Seunghyun, Bui, Trung, Zhao, Handong, Tran, Quan, Dernoncourt, Franck, Kang, Jaewoo
Contrastive language-image pre-training (CLIP) models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval, where the model is required to effectively process natural language input to produce a
Externí odkaz:
http://arxiv.org/abs/2402.15120
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we introduce a novel approach called class-aware optimal transport (OT), which measures the OT distance between
Externí odkaz:
http://arxiv.org/abs/2401.15952
Autor:
Xing, Linzi, Tran, Quan, Caba, Fabian, Dernoncourt, Franck, Yoon, Seunghyun, Wang, Zhaowen, Bui, Trung, Carenini, Giuseppe
Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal, relying solely on a single modality is arguably insufficient. On the
Externí odkaz:
http://arxiv.org/abs/2312.00220
Autor:
Deng, Zhongfen, Yoon, Seunghyun, Bui, Trung, Dernoncourt, Franck, Tran, Quan Hung, Liu, Shuaiqi, Zhao, Wenting, Zhang, Tao, Wang, Yibo, Yu, Philip S.
Aspect-based meeting transcript summarization aims to produce multiple summaries, each focusing on one aspect of content in a meeting transcript. It is challenging as sentences related to different aspects can mingle together, and those relevant to a
Externí odkaz:
http://arxiv.org/abs/2311.04292
Data-Free Knowledge Distillation (DFKD) has made significant recent strides by transferring knowledge from a teacher neural network to a student neural network without accessing the original data. Nonetheless, existing approaches encounter a signific
Externí odkaz:
http://arxiv.org/abs/2310.00258
Autor:
Lai, Viet Dac, Salinas, Abel, Tan, Hao, Bui, Trung, Tran, Quan, Yoon, Seunghyun, Deilamsalehy, Hanieh, Dernoncourt, Franck, Nguyen, Thien Huu
Punctuation restoration is an important task in automatic speech recognition (ASR) which aim to restore the syntactic structure of generated ASR texts to improve readability. While punctuated texts are abundant from written documents, the discrepancy
Externí odkaz:
http://arxiv.org/abs/2307.12949