본문 바로가기
반응형

자연어처리572

[2023-11-22] 오늘의 자연어처리 Deepparse : An Extendable, and Fine-Tunable State-Of-The-Art Library for Parsing Multinational Street Addresses Abstract:Segmenting an address into meaningful components, also known as address parsing, is an essential step in many applications from record linkage to geocoding and package delivery. Consequently, a lot of work has been dedicated to develop accurate address parsing techniques, with.. 2023. 11. 22.
[2023-11-21] 오늘의 자연어처리 The Impact of Familiarity on Naming Variation: A Study on Object Naming in Mandarin Chinese Abstract:Different speakers often produce different names for the same object or entity (e.g., "woman" vs. "tourist" for a female tourist). The reasons behind variation in naming are not well understood. We create a Language and Vision dataset for Mandarin Chinese that provides an average of 20 names for .. 2023. 11. 21.
[2023-11-20] 오늘의 자연어처리 Performance Trade-offs of Watermarking Large Language Models Abstract:Amidst growing concerns of large language models (LLMs) being misused for generating misinformation or completing homework assignments, watermarking has emerged as an effective solution for distinguishing human-written and LLM-generated text. A prominent watermarking strategy is to embed a signal into generated text by upsampl.. 2023. 11. 20.
[2023-11-19] 오늘의 자연어처리 ML-Bench: Large Language Models Leverage Open-source Libraries for Machine Learning Tasks Abstract:Large language models have shown promising performance in code generation benchmarks. However, a considerable divide exists between these benchmark achievements and their practical applicability, primarily attributed to real-world programming's reliance on pre-existing libraries. Instead of evaluat.. 2023. 11. 19.
반응형