Zobrazeno 1 - 10
of 398
pro vyhledávání: '"HOVY, EDUARD"'
Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning
Packing, initially utilized in the pre-training phase, is an optimization technique designed to maximize hardware resource efficiency by combining different training sequences to fit the model's maximum input length. Although it has demonstrated effe
Externí odkaz:
http://arxiv.org/abs/2410.08081
Autor:
Mahmudi, Aso, Herce, Borja, Amestica, Demian Inostroza, Scherbakov, Andreas, Hovy, Eduard, Vylomova, Ekaterina
Linguistic fieldwork is an important component in language documentation and preservation. However, it is a long, exhaustive, and time-consuming process. This paper presents a novel model that guides a linguist during the fieldwork and accounts for t
Externí odkaz:
http://arxiv.org/abs/2409.14628
Autor:
Sachan, Mrinmaya, Dubey, Avinava, Hovy, Eduard H., Mitchell, Tom M., Roth, Dan, Xing, Eric P.
Publikováno v:
Computational Linguistics, Vol 45, Iss 4, Pp 627-665 (2020)
To ensure readability, text is often written and presented with due formatting. These text formatting devices help the writer to effectively convey the narrative. At the same time, these help the readers pick up the structure of the discourse and com
Externí odkaz:
https://doaj.org/article/dc8f38f4640e4e158191ebcbb5855a15
Autor:
Liu, Zhiwei, Yang, Kailai, Xie, Qianqian, de Kock, Christine, Ananiadou, Sophia, Hovy, Eduard
Misinformation is prevalent in various fields such as education, politics, health, etc., causing significant harm to society. However, current methods for cross-domain misinformation detection rely on time and resources consuming fine-tuning and comp
Externí odkaz:
http://arxiv.org/abs/2406.11093
Autor:
Choe, Sang Keun, Ahn, Hwijeen, Bae, Juhan, Zhao, Kewen, Kang, Minsoo, Chung, Youngseog, Pratapa, Adithya, Neiswanger, Willie, Strubell, Emma, Mitamura, Teruko, Schneider, Jeff, Hovy, Eduard, Grosse, Roger, Xing, Eric
Large language models (LLMs) are trained on a vast amount of human-written data, but data providers often remain uncredited. In response to this issue, data valuation (or data attribution), which quantifies the contribution or value of each data to t
Externí odkaz:
http://arxiv.org/abs/2405.13954
Modern natural language generation systems with Large Language Models (LLMs) exhibit the capability to generate a plausible summary of multiple documents; however, it is uncertain if they truly possess the capability of information consolidation to g
Externí odkaz:
http://arxiv.org/abs/2402.18005
Autor:
Wang, Shuhe, Cao, Beiming, Zhang, Shengyu, Li, Xiaoya, Li, Jiwei, Wu, Fei, Wang, Guoyin, Hovy, Eduard
Due to the lack of a large collection of high-quality labeled sentence pairs with textual similarity scores, existing approaches for Semantic Textual Similarity (STS) mostly rely on unsupervised techniques or training signals that are only partially
Externí odkaz:
http://arxiv.org/abs/2312.05603
Autor:
Li, Sha, Han, Chi, Yu, Pengfei, Edwards, Carl, Li, Manling, Wang, Xingyao, Fung, Yi R., Yu, Charles, Tetreault, Joel R., Hovy, Eduard H., Ji, Heng
The recent explosion of performance of large language models (LLMs) has changed the field of Natural Language Processing (NLP) more abruptly and seismically than any other shift in the field's 80-year history. This has resulted in concerns that the f
Externí odkaz:
http://arxiv.org/abs/2310.20633
Autor:
Augenstein, Isabelle, Baldwin, Timothy, Cha, Meeyoung, Chakraborty, Tanmoy, Ciampaglia, Giovanni Luca, Corney, David, DiResta, Renee, Ferrara, Emilio, Hale, Scott, Halevy, Alon, Hovy, Eduard, Ji, Heng, Menczer, Filippo, Miguez, Ruben, Nakov, Preslav, Scheufele, Dietram, Sharma, Shivam, Zagni, Giovanni
The emergence of tools based on Large Language Models (LLMs), such as OpenAI's ChatGPT, Microsoft's Bing Chat, and Google's Bard, has garnered immense public attention. These incredibly useful, natural-sounding tools mark significant advances in natu
Externí odkaz:
http://arxiv.org/abs/2310.05189
In this work we propose a pragmatic method that reduces the annotation cost for structured label spaces using active learning. Our approach leverages partial annotation, which reduces labeling costs for structured outputs by selecting only the most i
Externí odkaz:
http://arxiv.org/abs/2305.12634