A method to boost automatic speech recognition by blending keyword lists with language models.
Iuliia Thorbecke, Juan Zuluaga-Gomez, Esaú Villatoro-Tello
― 4 min read
Computer Science - Computation and Language
RSSThis study focuses on enhancing entity recognition in old texts affected by OCR errors.
Emanuela Boros, Maud Ehrmann
― 6 min read
A study on vocal imitation techniques using technology to enhance communication.
Matthew Caren, Kartik Chandra, Joshua B. Tenenbaum
― 5 min read
A new framework enhances models' ability to handle time-related questions effectively.
Wanqi Yang, Yanda Li, Meng Fang
― 5 min read
Examining how robots can truly understand language through real-world experiences.
Sara Incao, Carlo Mazzola, Giulia Belgiovine
― 6 min read
Utilizing NLP to document and protect the endangered Hawrami dialect.
Aram Khaksar, Hossein Hassani
― 6 min read
Learn how to effectively train speech models with fewer labeled resources.
Iuliia Thorbecke, Juan Zuluaga-Gomez, Esaú Villatoro-Tello
― 7 min read
A new approach to assess AI benchmarks for cultural understanding.
Jonathan H. Rystrøm, Kenneth C. Enevoldsen
― 8 min read
CodeInsight offers a refined dataset for generating Python code with real examples.
Nathanaël Beau, Benoît Crabbé
― 7 min read
An analysis of gender terminology in speech technology and its societal implications.
Ariadna Sanchez, Alice Ross, Nina Markl
― 7 min read
Introducing CLIPFit, a method for efficient fine-tuning of Vision-Language Models.
Ming Li, Jike Zhong, Chenxin Li
― 6 min read
Examining the impact of AI-generated text on investor decisions.
Takehiro Takayanagi, Hiroya Takamura, Kiyoshi Izumi
― 5 min read
A study on omissions and distortions in natural language generation from RDF data.
Juliette Faille, Albert Gatt, Claire Gardent
― 5 min read
Learn how low-bit quantization improves the efficiency of large language models.
Ruihao Gong, Yifu Ding, Zining Wang
― 6 min read
A new method improves accuracy in answering questions from tables by merging two systems.
Siyue Zhang, Anh Tuan Luu, Chen Zhao
― 7 min read
SWE2 improves detection of hate speech on social media through advanced techniques.
Guanyi Mou, Pengyi Ye, Kyumin Lee
― 4 min read
This framework improves counterfactual statement detection using neural models and causal methods.
Thong Nguyen, Truc-My Nguyen
― 6 min read
The CCI model enhances story creation through character focus and image inspiration.
Kyeongman Park, Minbeom Kim, Kyomin Jung
― 7 min read
AI advancements are transforming the generation of essential medical documents.
Justin Xu, Zhihong Chen, Andrew Johnston
― 6 min read
This study examines how people express coping strategies through language in emotional situations.
Enrica Troiano, Sofie Labat, Marco Antonio Stranisci
― 5 min read
SciDFM offers advanced reasoning and understanding for scientific research.
Liangtai Sun, Danyu Luo, Da Ma
― 5 min read
New methods focus on analyzing source code for better defect prediction.
Hung Viet Pham, Tung Thanh Nguyen
― 7 min read
MultiClimate dataset reveals public stances on climate change through videos.
Jiawen Wang, Longfei Zuo, Siyao Peng
― 6 min read
An overview of various methods for merging models to enhance machine learning performance.
Derek Tam, Yash Kant, Brian Lester
― 8 min read
A new method for generating engaging distractors in educational assessments.
Devrim Cavusoglu, Secil Sen, Ulas Sert
― 5 min read
A study on how models follow instructions during complex dialogues.
Elliot L. Epstein, Kaisheng Yao, Jing Li
― 6 min read
Introducing LowREm, a tool for enhancing word embeddings in underrepresented languages.
Daniil Gurgurov, Rishu Kumar, Simon Ostermann
― 5 min read
Assessing the impact of LLMs on healthcare documentation and safety.
Emma Croxford, Yanjun Gao, Nicholas Pellegrino
― 7 min read
MultiMed project enhances automatic speech recognition for better healthcare communication.
Khai Le-Duc, Phuc Phan, Tan-Hanh Pham
― 5 min read
A study on improving retrieval methods for diverse opinions on complex questions.
Hung-Ting Chen, Eunsol Choi
― 7 min read
This article discusses new strategies for training speech translation systems effectively.
Belen Alastruey, Gerard I. Gállego, Marta R. Costa-jussà
― 6 min read
EMOVA enhances human-computer interaction through emotional expression.
Kai Chen, Yunhao Gou, Runhui Huang
― 5 min read
Exploring how LLMs struggle with complex coding challenges.
Yotam Wolf, Binyamin Rothberg, Dorin Shteyman
― 8 min read
This study assesses LLM performance in answering questions and predicting material properties.
Hongchen Wang, Kangming Li, Scott Ramsay
― 5 min read
This article explores intransitivity and its impact on decision-making in various fields.
Jiuding Duan, Jiyi Li, Yukino Baba
― 5 min read
Evaluating LLM performance across long texts in five languages.
Ameeta Agrawal, Andy Dang, Sina Bagheri Nezhad
― 6 min read
BEATS enhances LLMs' ability to solve math problems clearly and accurately.
Linzhuang Sun, Hao Liang, Jingxuan Wei
― 5 min read
Analyzing how gender-fair language influences language models in text classification tasks.
Andreas Waldis, Joel Birrer, Anne Lauscher
― 6 min read
PEDRO improves efficiency in fine-tuning large language models with adjustable vectors.
Tianfang Xie, Tianjing Li, Wei Zhu
― 5 min read
A new dataset to improve language models focused on business-related text.
Siyan Wang, Bradford Levy
― 5 min read