Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Marujo, Luís"'
Autor:
Poddar, Lahari, Neves, Leonardo, Brendel, William, Marujo, Luis, Tulyakov, Sergey, Karuturi, Pradeep
Tracking user reported bugs requires considerable engineering effort in going through many repetitive reports and assigning them to the correct teams. This paper proposes a neural architecture that can jointly (1) detect if two bug reports are duplic
Externí odkaz:
http://arxiv.org/abs/1903.12431
The frequent use of Emojis on social media platforms has created a new form of multimodal social interaction. Developing methods for the study and representation of emoji semantics helps to improve future multimodal communication systems. In this pap
Externí odkaz:
http://arxiv.org/abs/1805.00731
Autor:
Ling, Wang, Luís, Tiago, Marujo, Luís, Astudillo, Ramón Fernandez, Amir, Silvio, Dyer, Chris, Black, Alan W., Trancoso, Isabel
We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs. Relative to traditional word representation models that have independent vectors for each word type, our model requires only a si
Externí odkaz:
http://arxiv.org/abs/1508.02096
Autor:
Marujo, Luís, Portêlo, José, Ling, Wang, de Matos, David Martins, Neto, João P., Gershman, Anatole, Carbonell, Jaime, Trancoso, Isabel, Raj, Bhiksha
State-of-the-art extractive multi-document summarization systems are usually designed without any concern about privacy issues, meaning that all documents are open to third parties. In this paper we propose a privacy-preserving approach to multi-docu
Externí odkaz:
http://arxiv.org/abs/1508.01420
Autor:
Marujo, Luís, Ribeiro, Ricardo, de Matos, David Martins, Neto, João P., Gershman, Anatole, Carbonell, Jaime
The increasing amount of online content motivated the development of multi-document summarization methods. In this work, we explore straightforward approaches to extend single-document summarization methods to multi-document summarization. The propos
Externí odkaz:
http://arxiv.org/abs/1507.02907
Autor:
Aparício, Marta, Figueiredo, Paulo, Raposo, Francisco, de Matos, David Martins, Ribeiro, Ricardo, Marujo, Luís
Publikováno v:
Pattern Recognition Letters, Volume 73, 1 April 2016, Pages 7-12
We assess the performance of generic text summarization algorithms applied to films and documentaries, using the well-known behavior of summarization of news articles as reference. We use three datasets: (i) news articles, (ii) film scripts and subti
Externí odkaz:
http://arxiv.org/abs/1506.01273
Autor:
Marujo, Luis, Portêlo, José, de Matos, David Martins, Neto, João P., Gershman, Anatole, Carbonell, Jaime, Trancoso, Isabel, Raj, Bhiksha
State-of-the-art important passage retrieval methods obtain very good results, but do not take into account privacy issues. In this paper, we present a privacy preserving method that relies on creating secure representations of documents. Our approac
Externí odkaz:
http://arxiv.org/abs/1407.5416
Event classification at sentence level is an important Information Extraction task with applications in several NLP, IR, and personalization systems. Multi-label binary relevance (BR) are the state-of-art methods. In this work, we explored new multi-
Externí odkaz:
http://arxiv.org/abs/1403.6023
In this work, we propose two stochastic architectural models (CMC and CMC-M) with two layers of classifiers applicable to datasets with one and multiple skewed classes. This distinction becomes important when the datasets have a large number of class
Externí odkaz:
http://arxiv.org/abs/1312.6597
Fast and effective automated indexing is critical for search and personalized services. Key phrases that consist of one or more words and represent the main concepts of the document are often used for the purpose of indexing. In this paper, we invest
Externí odkaz:
http://arxiv.org/abs/1306.4886