Zobrazeno 1 - 10
of 391
pro vyhledávání: '"Skiena, Steven"'
Autor:
Draganov, Ondřej, Skiena, Steven
Word embeddings represent language vocabularies as clouds of $d$-dimensional points. We investigate how information is conveyed by the general shape of these clouds, outside of representing the semantic meaning of each token. Specifically, we use the
Externí odkaz:
http://arxiv.org/abs/2404.00500
Autor:
Yin, Yunting, Skiena, Steven
Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We present an exploratory study of the degree o
Externí odkaz:
http://arxiv.org/abs/2311.06362
Novels are often adapted into feature films, but the differences between the two media usually require dropping sections of the source text from the movie script. Here we study this screen adaptation process by constructing narrative alignments using
Externí odkaz:
http://arxiv.org/abs/2311.04020
Autor:
Pial, Tanzir, Skiena, Steven
Algorithmic sequence alignment identifies similar segments shared between pairs of documents, and is fundamental to many NLP tasks. But it is difficult to recognize similarities between distant versions of narratives such as translations and retellin
Externí odkaz:
http://arxiv.org/abs/2311.03627
Books have historically been the primary mechanism through which narratives are transmitted. We have developed a collection of resources for the large-scale analysis of novels, including: (1) an open source end-to-end NLP analysis pipeline for the an
Externí odkaz:
http://arxiv.org/abs/2311.03614
Recent advances in text-to-speech have made it possible to generate natural-sounding audio from text. However, audiobook narrations involve dramatic vocalizations and intonations by the reader, with greater reliance on emotions, dialogues, and descri
Externí odkaz:
http://arxiv.org/abs/2310.06930
Personalized PageRank Vectors are widely used as fundamental graph-learning tools for detecting anomalous spammers, learning graph embeddings, and training graph neural networks. The well-known local FwdPush algorithm approximates PPVs and has a subl
Externí odkaz:
http://arxiv.org/abs/2306.02102
Autor:
Zhou, Baojian, Skiena, Steven
The Area Under the ROC Curve (AUC) is an important model metric for evaluating binary classifiers, and many algorithms have been proposed to optimize AUC approximately. It raises the question of whether the generally insignificant gains observed by p
Externí odkaz:
http://arxiv.org/abs/2306.01528