News Reporter: A Multi-lingual LLM Framework for Broadcast T.V News

2024-10-10 · Tarun Jain, Yufei Gao, Sridhar Vanga, Karan Singla

Large Language Models (LLMs) have fast become an essential tools to many conversational chatbots due to their ability to provide coherent answers for varied queries. Datasets used to train these LLMs are often a mix of generic and synthetic samples, thus lacking the verification needed to provide correct and verifiable answers for T.V. News. We collect and share a large collection of QA pairs extracted from transcripts of news recordings from various news-channels across the United States. Resultant QA pairs are then used to fine-tune an off-the-shelf LLM model. Our model surpasses base models of similar size on several open LLM benchmarks. We further integrate and propose a RAG method to improve contextualization of our answers and also point it to a verifiable news recording.

📄 PDF Abstract BibTeX arXiv:2410.07520

Code (0)

등록된 구현이 없습니다.

Tasks

RAG

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

WordPiece 설명 없음

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Weight Decay 설명 없음

Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

MultiVENT: Multilingual Videos of Events with Aligned Natural Text

2023-07-06 · Kate Sanders, David Etter, Reno Kriz, Benjamin Van Durme

Everyday news coverage has shifted from traditional broadcasts towards a wide range of presentation formats such as first-hand, unedited video footage. Datasets that reflect the diverse array of multimodal, multilingual …

Information Retrieval Retrieval Video Retrieval

MultiVENT: Multilingual Videos of Events and Aligned Natural Text

2023-09-26 · NeurIPS 2023 11

Xiaomingbot: A Multilingual Robot News Reporter

2020-07-12 · ACL 2020 6 · Runxin Xu, Jun Cao, Mingxuan Wang, Jiaze Chen 외

This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four integral capabilities: news generation, news translation, news reading and avatar animation. …

Articles News Generation Translation Voice Cloning

The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring

2018-07-01 · ACL 2018 7 · Ulrich Germann, Ren{\=a}rs Liepins, Guntis Barzdins, Didzis Gosko 외

The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes. The Platform o…

Clustering Document Summarization Multi-Document Summarization Translation

New bilingual speech databases for audio diarization

2014-05-01 · LREC 2014 5 · David Tavarez, Eva Navas, Daniel Erro, Ibon Saratxaga 외

This paper describes the process of collecting and recording two new bilingual speech databases in Spanish and Basque. They are designed primarily for speaker diarization in two different application domains: broadcast n…

speaker-diarization Speaker Diarization Speaker Recognition