Paper Group NANR 38
International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 2, December 2017-Special Issue on Selected Papers from ROCLING XXIX. Proceedings of the 10th International Conference on Natural Language Generation. The Semantic Proto-Role Linking Model. Mapping distinct timescales of functional interactions among …
International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 2, December 2017-Special Issue on Selected Papers from ROCLING XXIX
| Title | International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 2, December 2017-Special Issue on Selected Papers from ROCLING XXIX |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/O17-3000/ |
| https://www.aclweb.org/anthology/O17-3000 | |
| PWC | https://paperswithcode.com/paper/international-journal-of-computational-9 |
| Repo | |
| Framework | |
Proceedings of the 10th International Conference on Natural Language Generation
| Title | Proceedings of the 10th International Conference on Natural Language Generation |
| Authors | |
| Abstract | |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3500/ |
| https://www.aclweb.org/anthology/W17-3500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-10th-international-4 |
| Repo | |
| Framework | |
The Semantic Proto-Role Linking Model
| Title | The Semantic Proto-Role Linking Model |
| Authors | Aaron Steven White, Kyle Rawlins, Benjamin Van Durme |
| Abstract | We propose the semantic proto-role linking model, which jointly induces both predicate-specific semantic roles and predicate-general semantic proto-roles based on semantic proto-role property likelihood judgments. We use this model to empirically evaluate Dowty{'}s thematic proto-role linking theory. |
| Tasks | Semantic Role Labeling |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2015/ |
| https://www.aclweb.org/anthology/E17-2015 | |
| PWC | https://paperswithcode.com/paper/the-semantic-proto-role-linking-model |
| Repo | |
| Framework | |
Mapping distinct timescales of functional interactions among brain networks
| Title | Mapping distinct timescales of functional interactions among brain networks |
| Authors | Mali Sundaresan, Arshed Nabeel, Devarajan Sridharan |
| Abstract | Brain processes occur at various timescales, ranging from milliseconds (neurons) to minutes and hours (behavior). Characterizing functional coupling among brain regions at these diverse timescales is key to understanding how the brain produces behavior. Here, we apply instantaneous and lag-based measures of conditional linear dependence, based on Granger-Geweke causality (GC), to infer network connections at distinct timescales from functional magnetic resonance imaging (fMRI) data. Due to the slow sampling rate of fMRI, it is widely held that GC produces spurious and unreliable estimates of functional connectivity when applied to fMRI data. We challenge this claim with simulations and a novel machine learning approach. First, we show, with simulated fMRI data, that instantaneous and lag-based GC identify distinct timescales and complementary patterns of functional connectivity. Next, we analyze fMRI scans from 500 subjects and show that a linear classifier trained on either instantaneous or lag-based GC connectivity reliably distinguishes task versus rest brain states, with ~80-85% cross-validation accuracy. Importantly, instantaneous and lag-based GC exploit markedly different spatial and temporal patterns of connectivity to achieve robust classification. Our approach enables identifying functionally connected networks that operate at distinct timescales in the brain. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6999-mapping-distinct-timescales-of-functional-interactions-among-brain-networks |
| http://papers.nips.cc/paper/6999-mapping-distinct-timescales-of-functional-interactions-among-brain-networks.pdf | |
| PWC | https://paperswithcode.com/paper/mapping-distinct-timescales-of-functional |
| Repo | |
| Framework | |
Automatic Categorization of Tagalog Documents Using Support Vector Machines
| Title | Automatic Categorization of Tagalog Documents Using Support Vector Machines |
| Authors | April Dae Bation, Aileen Joan Vicente, Erlyn Manguilimotan |
| Abstract | |
| Tasks | Document Classification, Feature Selection, Lemmatization, Text Categorization |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1046/ |
| https://www.aclweb.org/anthology/Y17-1046 | |
| PWC | https://paperswithcode.com/paper/automatic-categorization-of-tagalog-documents |
| Repo | |
| Framework | |
Max-Margin Invariant Features from Transformed Unlabelled Data
| Title | Max-Margin Invariant Features from Transformed Unlabelled Data |
| Authors | Dipan Pal, Ashwin Kannan, Gautam Arakalgud, Marios Savvides |
| Abstract | The study of representations invariant to common transformations of the data is important to learning. Most techniques have focused on local approximate invariance implemented within expensive optimization frameworks lacking explicit theoretical guarantees. In this paper, we study kernels that are invariant to a unitary group while having theoretical guarantees in addressing the important practical issue of unavailability of transformed versions of labelled data. A problem we call the Unlabeled Transformation Problem which is a special form of semi-supervised learning and one-shot learning. We present a theoretically motivated alternate approach to the invariant kernel SVM based on which we propose Max-Margin Invariant Features (MMIF) to solve this problem. As an illustration, we design an framework for face recognition and demonstrate the efficacy of our approach on a large scale semi-synthetic dataset with 153,000 images and a new challenging protocol on Labelled Faces in the Wild (LFW) while out-performing strong baselines. |
| Tasks | Face Recognition, One-Shot Learning |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6742-max-margin-invariant-features-from-transformed-unlabelled-data |
| http://papers.nips.cc/paper/6742-max-margin-invariant-features-from-transformed-unlabelled-data.pdf | |
| PWC | https://paperswithcode.com/paper/max-margin-invariant-features-from-1 |
| Repo | |
| Framework | |
Concept Equalization to Guide Correct Training of Neural Machine Translation
| Title | Concept Equalization to Guide Correct Training of Neural Machine Translation |
| Authors | Kangil Kim, Jong-Hun Shin, Seung-Hoon Na, SangKeun Jung |
| Abstract | Neural machine translation decoders are usually conditional language models to sequentially generate words for target sentences. This approach is limited to find the best word composition and requires help of explicit methods as beam search. To help learning correct compositional mechanisms in NMTs, we propose concept equalization using direct mapping distributed representations of source and target sentences. In a translation experiment from English to French, the concept equalization significantly improved translation quality by 3.00 BLEU points compared to a state-of-the-art NMT model. |
| Tasks | Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2051/ |
| https://www.aclweb.org/anthology/I17-2051 | |
| PWC | https://paperswithcode.com/paper/concept-equalization-to-guide-correct |
| Repo | |
| Framework | |
Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture
| Title | Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture |
| Authors | Mingmin Zhao, Shichao Yue, Dina Katabi, Tommi S. Jaakkola, Matt T. Bianchi |
| Abstract | We focus on predicting sleep stages from radio measurements without any attached sensors on subjects. We introduce a new predictive model that combines convolutional and recurrent neural networks to extract sleep-specific subject-invariant features from RF signals and capture the temporal progression of sleep. A key innovation underlying our approach is a modified adversarial training regime that discards extraneous information specific to individuals or measurement conditions, while retaining all information relevant to the predictive task. We analyze our game theoretic setup and empirically demonstrate that our model achieves significant improvements over state-of-the-art solutions. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=889 |
| http://proceedings.mlr.press/v70/zhao17d/zhao17d.pdf | |
| PWC | https://paperswithcode.com/paper/learning-sleep-stages-from-radio-signals-a |
| Repo | |
| Framework | |
Proceedings of the Student Research Workshop Associated with RANLP 2017
| Title | Proceedings of the Student Research Workshop Associated with RANLP 2017 |
| Authors | Venelin, Irina, Pepa, Yasen Kiprov, Ivelina Nikolova |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/papers/R17-2000/r17-2000 |
| https://www.aclweb.org/anthology/R17-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-student-research-workshop-1 |
| Repo | |
| Framework | |
Findings of the 2017 Conference on Machine Translation (WMT17)
| Title | Findings of the 2017 Conference on Machine Translation (WMT17) |
| Authors | Ond{\v{r}}ej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Shujian Huang, Matthias Huck, Philipp Koehn, Qun Liu, Varvara Logacheva, Christof Monz, Matteo Negri, Matt Post, Raphael Rubino, Lucia Specia, Marco Turchi |
| Abstract | |
| Tasks | Automatic Post-Editing, Machine Translation, Multimodal Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4717/ |
| https://www.aclweb.org/anthology/W17-4717 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-2017-conference-on-machine |
| Repo | |
| Framework | |
Xception: Deep Learning With Depthwise Separable Convolutions
| Title | Xception: Deep Learning With Depthwise Separable Convolutions |
| Authors | Francois Chollet |
| Abstract | We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution can be understood as an Inception module with a maximally large number of towers. This observation leads us to propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions. We show that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset (which Inception V3 was designed for), and significantly outperforms Inception V3 on a larger image classification dataset comprising 350 million images and 17,000 classes. Since the Xception architecture has the same number of parameters as Inception V3, the performance gains are not due to increased capacity but rather to a more efficient use of model parameters. |
| Tasks | Image Classification |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Chollet_Xception_Deep_Learning_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Chollet_Xception_Deep_Learning_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/xception-deep-learning-with-depthwise-1 |
| Repo | |
| Framework | |
Spoken Term Discovery for Language Documentation using Translations
| Title | Spoken Term Discovery for Language Documentation using Translations |
| Authors | Antonios Anastasopoulos, Sameer Bansal, David Chiang, Sharon Goldwater, Adam Lopez |
| Abstract | Vast amounts of speech data collected for language documentation and research remain untranscribed and unsearchable, but often a small amount of speech may have text translations available. We present a method for partially labeling additional speech with translations in this scenario. We modify an unsupervised speech-to-translation alignment model and obtain prototype speech segments that match the translation words, which are in turn used to discover terms in the unlabelled data. We evaluate our method on a Spanish-English speech translation corpus and on two corpora of endangered languages, Arapaho and Ainu, demonstrating its appropriateness and applicability in an actual very-low-resource scenario. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4607/ |
| https://www.aclweb.org/anthology/W17-4607 | |
| PWC | https://paperswithcode.com/paper/spoken-term-discovery-for-language |
| Repo | |
| Framework | |
On the stylistic evolution from communism to democracy: Solomon Marcus study case
| Title | On the stylistic evolution from communism to democracy: Solomon Marcus study case |
| Authors | Anca Dinu, Liviu P. Dinu, Bogdan Dumitru |
| Abstract | In this article we propose a stylistic analysis of Solomon Marcus{'} non-scientific published texts, gathered in six volumes, aiming to uncover some of his quantitative and qualitative fingerprints. Moreover, we compare and cluster two distinct periods of time in his writing style: 22 years of communist regime (1967-1989) and 27 years of democracy (1990-2016). The distributional analysis of Marcus{'} text reveals that the passing from the communist regime period to democracy is sharply marked by two complementary changes in Marcus{'} writing: in the pre-democracy period, the communist norms of writing style demanded on the one hand long phrases, long words and clich{'e}s, and on the other hand, a short list of preferred {``}official{''} topics; in democracy tendency was towards shorten phrases and words while approaching a broader area of topics. | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1028/ |
| https://doi.org/10.26615/978-954-452-049-6_028 | |
| PWC | https://paperswithcode.com/paper/on-the-stylistic-evolution-from-communism-to |
| Repo | |
| Framework | |
Investigating the Documentation of Electronic Cigarette Use in the Veteran Affairs Electronic Health Record: A Pilot Study
| Title | Investigating the Documentation of Electronic Cigarette Use in the Veteran Affairs Electronic Health Record: A Pilot Study |
| Authors | Danielle Mowery, Brett South, Olga Patterson, Shu-Hong Zhu, Mike Conway |
| Abstract | In this paper, we present pilot work on characterising the documentation of electronic cigarettes (e-cigarettes) in the United States Veterans Administration Electronic Health Record. The Veterans Health Administration is the largest health care system in the United States with 1,233 health care facilities nationwide, serving 8.9 million veterans per year. We identified a random sample of 2000 Veterans Administration patients, coded as current tobacco users, from 2008 to 2014. Using simple keyword matching techniques combined with qualitative analysis, we investigated the prevalence and distribution of e-cigarette terms in these clinical notes, discovering that for current smokers, 11.9{%} of patient records contain an e-cigarette related term. |
| Tasks | Epidemiology |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2335/ |
| https://www.aclweb.org/anthology/W17-2335 | |
| PWC | https://paperswithcode.com/paper/investigating-the-documentation-of-electronic |
| Repo | |
| Framework | |
Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems
| Title | Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems |
| Authors | Ingmar Kanitscheider, Ila Fiete |
| Abstract | Self-localization during navigation with noisy sensors in an ambiguous world is computationally challenging, yet animals and humans excel at it. In robotics, {\em Simultaneous Location and Mapping} (SLAM) algorithms solve this problem through joint sequential probabilistic inference of their own coordinates and those of external spatial landmarks. We generate the first neural solution to the SLAM problem by training recurrent LSTM networks to perform a set of hard 2D navigation tasks that require generalization to completely novel trajectories and environments. Our goal is to make sense of how the diverse phenomenology in the brain’s spatial navigation circuits is related to their function. We show that the hidden unit representations exhibit several key properties of hippocampal place cells, including stable tuning curves that remap between environments. Our result is also a proof of concept for end-to-end-learning of a SLAM algorithm using recurrent networks, and a demonstration of why this approach may have some advantages for robotic SLAM. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7039-training-recurrent-networks-to-generate-hypotheses-about-how-the-brain-solves-hard-navigation-problems |
| http://papers.nips.cc/paper/7039-training-recurrent-networks-to-generate-hypotheses-about-how-the-brain-solves-hard-navigation-problems.pdf | |
| PWC | https://paperswithcode.com/paper/training-recurrent-networks-to-generate |
| Repo | |
| Framework | |
