Temporal Cascade Model for Analyzing Spread in Evolving Networks

Autor: Aparajita Haldar, Shuang Wang, Gunduz Vehbi Demirci, Joe Oakley, Hakan Ferhatosmanoglu

Publikováno v: ACM Transactions on Spatial Algorithms and Systems. 9:1-30

Current approaches for modeling propagation in networks (e.g., of diseases, computer viruses, rumors) cannot adequately capture temporal properties such as order/duration of evolving connections or dynamic likelihoods of propagation along connections

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::de8959f8a2a1d0e620ee31b10b63256e
https://doi.org/10.1145/3579996

Variational recurrent sequence-to-sequence retrieval for stepwise illustration

Autor: Aparajita Haldar, Tanaya Guha, Yulan He, George Vogiatzis, Vishwash Batra, Hakan Ferhatosmanoglu

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030454388
ECIR (1)

We address and formalise the task of sequence-to-sequence (seq2seq) cross-modal retrieval. Given a sequence of text passages as query, the goal is to retrieve a sequence of images that best describes and aligns with the query. This new task extends t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89cda1545b8cf55017529ac676908b6d
http://wrap.warwick.ac.uk/136120/1/WRAP-variational-recurrent-sequence-to-sequence-retrieval-stepwise-illustration-Batra-2020.pdf

Characterizing the Impact of Geometric Properties of Word Embeddings on Task Performance

Autor: Eric Fosler-Lussier, Brendan Whitaker, Hakan Ferhatosmanoglu, Aparajita Haldar, Denis Newman-Griffis

Publikováno v: Whitaker, B, Newman-Griffis, D, Haldar, A, Ferhatosmanoglu, H & Fosler-Lussier, E 2019, Characterizing the Impact of Geometric Properties of Word Embeddings on Task Performance . in Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP . Minneapolis, USA, pp. 8-17, The Third Workshop on Evaluating Vector Space Representations for NLP, Minneapolis, United States, 6/06/19 . https://doi.org/10.18653/v1/W19-2002
Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP

Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of embedding featu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a50d8f510f6f13a88c6ab6a85ccec73
https://www.pure.ed.ac.uk/ws/files/353258464/Characterising_the_impact_WHITAKER_DOA29032019_VOR_CC_BY.pdf

Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation

Autor: Aparajita Haldar, Benjamin Van Durme, Ellie Pavlick, Rachel Rudinger, Adam Poliak, Aaron Steven White, J. Edward Hu

Publikováno v: BlackboxNLP@EMNLP
Web of Science
Scopus-Elsevier

We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation captures distinct types of reasoning. The collection results from recasting 13 existing dataset

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::84afa229152012df63411f78392da6fa