Zobrazeno 1 - 10
of 79
pro vyhledávání: '"Vitor R. Carvalho"'
Autor:
Sparsh Gupta, Vitor R. Carvalho
Publikováno v:
SIGIR
The task of ranking question-answer pairs in response to an input query, aka FAQ (Frequently Asked Question) Retrieval, has traditionally been focused mostly on extracting relevance signals between query and questions based on extensive manual featur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f12d6de92d5816c5d1bb2165b2af45c4
https://doi.org/10.1145/3331184.3331294
https://doi.org/10.1145/3331184.3331294
Autor:
Sparsh Gupta, Vitor R. Carvalho
Publikováno v:
RepL4NLP@ACL
Adversarial training is a process in Machine Learning that explicitly trains models on adversarial inputs (inputs designed to deceive or trick the learning process) in order to make it more robust or accurate. In this paper we investigate how represe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::795a22a19b636fe50a0cb3b23bd384f4
https://doi.org/10.18653/v1/w19-4325
https://doi.org/10.18653/v1/w19-4325
Publikováno v:
ACL (1)
Adversarial domain adaptation has been recently proposed as an effective technique for textual matching tasks, such as question deduplication. Here we investigate the use of gradient reversal on adversarial domain adaptation to explicitly learn both
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e9b8825a1c03ba358299640b34e4c7a
https://doi.org/10.18653/v1/p19-1556
https://doi.org/10.18653/v1/p19-1556
Publikováno v:
NAACL-HLT
We introduce a new task called Multimodal Named Entity Recognition (MNER) for noisy user-generated data such as tweets or Snapchat captions, which comprise short text with accompanying images. These social media posts often come in inconsistent or in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e256a24a54927f4f69244f7e08331301
http://arxiv.org/abs/1802.07862
http://arxiv.org/abs/1802.07862
Publikováno v:
ACL (1)
Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram. This combination of image and text in a single message allows for more creative and expressive forms of com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a18b6451869b116974e99144738cf5a9
https://doi.org/10.18653/v1/p18-1185
https://doi.org/10.18653/v1/p18-1185
Publikováno v:
ACL (1)
We introduce the new Multimodal Named Entity Disambiguation (MNED) task for multimodal social media posts such as Snapchat or Instagram captions, which are composed of short captions with accompanying images. Social media posts bring significant chal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f6b8fe1e0a8bbc9e3fbb6fb28f5540e
https://doi.org/10.18653/v1/p18-1186
https://doi.org/10.18653/v1/p18-1186
Publikováno v:
IJCAI
Modeling dialog systems is currently one of the most active problems in Natural Language Processing. Recent advancement in Deep Learning has sparked an interest in the use of neural networks in modeling language, particularly for personalized convers
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c999a88f38a902e38618f460565e8b24
https://doi.org/10.24963/ijcai.2017/521
https://doi.org/10.24963/ijcai.2017/521
Publikováno v:
WSDM
The advent of crowdsourcing is revolutionizing data annotation, evaluation, and other traditionally manual-labor intensive processes by dramatically reducing the time, cost, and effort involved. This in turn is driving a disruptive shift in search an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb6b7e759c6371efb76c2f1bc99726b5
https://doi.org/10.1145/1988852.1988856
https://doi.org/10.1145/1988852.1988856
Autor:
Vitor R. Carvalho
Everyday more than half of American adult internet users read or write email messages at least once. The prevalence of email has significantly impacted the working world, functioning as a great asset on many levels, yet at times, a costly liability.
Publikováno v:
Proceedings of the 21st International Conference on World Wide Web.
The International Workshop Email 2012 on Messaging and Web of Data: Private meets Public (and vice-versa) was held on April 16th 2012 at 21st World Wide Web Conference (WWW 2012) in Lyon, France. The Email 2012 workshop brought together researchers a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46c2a6bb1006ae7694e88173ecae1ee7
https://doi.org/10.1145/3259170
https://doi.org/10.1145/3259170