Zobrazeno 1 - 10
of 173
pro vyhledávání: '"Riloff, Ellen"'
In-context learning (ICL) has proven to be an effective strategy for improving the performance of large language models (LLMs) with no additional training. However, the exact mechanism behind these performance improvements remains unclear. This study
Externí odkaz:
http://arxiv.org/abs/2408.11546
Autor:
Jiang, Tianyu, Vinogradova, Sonia, Stringham, Nathan, Earl, E. Louise, Hollander, Allan D., Huber, Patrick R., Riloff, Ellen, Schillo, R. Sandra, Ubbiali, Giorgio A., Lange, Matthew
Our research explores the use of natural language processing (NLP) methods to automatically classify entities for the purpose of knowledge graph population and integration with food system ontologies. We have created NLP models that can automatically
Externí odkaz:
http://arxiv.org/abs/2309.10880
Autor:
Oraby, Shereen, Harrison, Vrindavan, Reed, Lena, Hernandez, Ernesto, Riloff, Ellen, Walker, Marilyn
The use of irony and sarcasm in social media allows us to study them at scale for the first time. However, their diversity has made it difficult to construct a high-quality corpus of sarcasm in dialogue. Here, we describe the process of creating a la
Externí odkaz:
http://arxiv.org/abs/1709.05404
Effective models of social dialog must understand a broad range of rhetorical and figurative devices. Rhetorical questions (RQs) are a type of figurative language whose aim is to achieve a pragmatic goal, such as structuring an argument, being persua
Externí odkaz:
http://arxiv.org/abs/1709.05305
We investigate the characteristics of factual and emotional argumentation styles observed in online debates. Using an annotated set of "factual" and "feeling" debate forum posts, we extract patterns that are highly correlated with factual and emotion
Externí odkaz:
http://arxiv.org/abs/1709.05295
Autor:
Breck, Eric, Light, Marc, Mann, Gideon S., Riloff, Ellen, Anand, Brianne Brown Pranav, Rooth, Mats, Thelen, Michael
In this paper we analyze two question answering tasks : the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we an
Externí odkaz:
http://arxiv.org/abs/cs/0107006
Autor:
Riloff, Ellen, Shepherd, Jessica
Semantic knowledge can be a great asset to natural language processing systems, but it is usually hand-coded for each application. Although some semantic information is available in general-purpose knowledge bases such as WordNet and Cyc, many applic
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9706013
Publikováno v:
Computational Intelligence. Aug2013, Vol. 29 Issue 3, p466-488. 23p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2016 IEEE/ACM International Conference on Advances in Social Networks Analysis & Mining (ASONAM); 2016, p711-718, 8p