Sciweavers

ACL
2015
8 years 15 days ago
On Using Very Large Target Vocabulary for Neural Machine Translation
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches su...
Sébastien Jean, KyungHyun Cho, Roland Memis...
ACL
2015
8 years 15 days ago
Neural CRF Parsing
This paper describes a parsing model that combines the exact dynamic programming of CRF parsing with the rich nonlinear featurization of neural net approaches. Our model is struct...
Greg Durrett, Dan Klein
ACL
2015
8 years 15 days ago
Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning
Zero-shot methods in language, vision and other domains rely on a cross-space mapping function that projects vectors from the relevant feature space (e.g., visualfeature-based ima...
Angeliki Lazaridou, Georgiana Dinu, Marco Baroni
ACL
2015
8 years 15 days ago
Sparse, Contextually Informed Models for Irony Detection: Exploiting User Communities, Entities and Sentiment
Automatically detecting verbal irony (roughly, sarcasm) in online content is important for many practical applications (e.g., sentiment detection), but it is difficult. Previous ...
Byron C. Wallace, Do Kook Choe, Eugene Charniak
ACL
2015
8 years 15 days ago
Addressing the Rare Word Problem in Neural Machine Translation
Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. A significant weakness i...
Thang Luong, Ilya Sutskever, Quoc V. Le, Oriol Vin...
ACL
2015
8 years 15 days ago
Multi-domain Dialog State Tracking using Recurrent Neural Networks
Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, welldefined domain in mind. This paper shows that dialog data dr...
Nikola Mrksic, Diarmuid Ó Séaghdha, ...
ACL
2015
8 years 15 days ago
Cross-lingual Transfer of Named Entity Recognizers without Parallel Corpora
We propose an approach to cross-lingual named entity recognition model transfer without the use of parallel corpora. In addition to global de-lexicalized features, we introduce mu...
Ayah Zirikly
ACL
2015
8 years 15 days ago
Dependency-based Convolutional Neural Networks for Sentence Embedding
In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequen...
Mingbo Ma, Liang Huang, Bowen Zhou, Bing Xiang
ACL
2015
8 years 15 days ago
Tracking unbounded Topic Streams
Tracking topics on social media streams is non-trivial as the number of topics mentioned grows without bound. This complexity is compounded when we want to track such topics again...
Dominik Wurzer, Victor Lavrenko, Miles Osborne