Paper Group NANR 201
Mistake Bounds for Binary Matrix Completion. Building a learner corpus for Russian. Dependency Based Embeddings for Sentence Classification Tasks. Improving Sequence to Sequence Learning for Morphological Inflection Generation: The BIU-MIT Systems for the SIGMORPHON 2016 Shared Task for Morphological Reinflection. Proceedings of the 1st Workshop on …
Mistake Bounds for Binary Matrix Completion
| Title | Mistake Bounds for Binary Matrix Completion |
| Authors | Mark Herbster, Stephen Pasteris, Massimiliano Pontil |
| Abstract | We study the problem of completing a binary matrix in an online learning setting. On each trial we predict a matrix entry and then receive the true entry. We propose a Matrix Exponentiated Gradient algorithm [1] to solve this problem. We provide a mistake bound for the algorithm, which scales with the margin complexity [2, 3] of the underlying matrix. The bound suggests an interpretation where each row of the matrix is a prediction task over a finite set of objects, the columns. Using this we show that the algorithm makes a number of mistakes which is comparable up to a logarithmic factor to the number of mistakes made by the Kernel Perceptron with an optimal kernel in hindsight. We discuss applications of the algorithm to predicting as well as the best biclustering and to the problem of predicting the labeling of a graph without knowing the graph in advance. |
| Tasks | Matrix Completion |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6567-mistake-bounds-for-binary-matrix-completion |
| http://papers.nips.cc/paper/6567-mistake-bounds-for-binary-matrix-completion.pdf | |
| PWC | https://paperswithcode.com/paper/mistake-bounds-for-binary-matrix-completion |
| Repo | |
| Framework | |
Building a learner corpus for Russian
| Title | Building a learner corpus for Russian |
| Authors | Ekaterina Rakhilina, Anastasia Vyrenkova, Elmira Mustakimova, Alina Ladygina, Ivan Smirnov |
| Abstract | |
| Tasks | Language Acquisition, Language Identification |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-6509/ |
| https://www.aclweb.org/anthology/W16-6509 | |
| PWC | https://paperswithcode.com/paper/building-a-learner-corpus-for-russian |
| Repo | |
| Framework | |
Dependency Based Embeddings for Sentence Classification Tasks
| Title | Dependency Based Embeddings for Sentence Classification Tasks |
| Authors | Alex Komninos, ros, Man, Suresh har |
| Abstract | |
| Tasks | Chunking, Learning Word Embeddings, Named Entity Recognition, Relation Classification, Sentence Classification, Sentiment Analysis, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1175/ |
| https://www.aclweb.org/anthology/N16-1175 | |
| PWC | https://paperswithcode.com/paper/dependency-based-embeddings-for-sentence |
| Repo | |
| Framework | |
Improving Sequence to Sequence Learning for Morphological Inflection Generation: The BIU-MIT Systems for the SIGMORPHON 2016 Shared Task for Morphological Reinflection
| Title | Improving Sequence to Sequence Learning for Morphological Inflection Generation: The BIU-MIT Systems for the SIGMORPHON 2016 Shared Task for Morphological Reinflection |
| Authors | Roee Aharoni, Yoav Goldberg, Yonatan Belinkov |
| Abstract | |
| Tasks | Feature Engineering, Machine Translation, Morphological Inflection |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2007/ |
| https://www.aclweb.org/anthology/W16-2007 | |
| PWC | https://paperswithcode.com/paper/improving-sequence-to-sequence-learning-for |
| Repo | |
| Framework | |
Proceedings of the 1st Workshop on Representation Learning for NLP
| Title | Proceedings of the 1st Workshop on Representation Learning for NLP |
| Authors | |
| Abstract | |
| Tasks | Representation Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1600/ |
| https://www.aclweb.org/anthology/W16-1600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-1st-workshop-on |
| Repo | |
| Framework | |
Detecting Grammatical Errors in Machine Translation Output Using Dependency Parsing and Treebank Querying
| Title | Detecting Grammatical Errors in Machine Translation Output Using Dependency Parsing and Treebank Querying |
| Authors | Arda Tezcan, Veronique Hoste, Lieve Macken |
| Abstract | |
| Tasks | Dependency Parsing, Machine Translation |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/W16-3409/ |
| https://www.aclweb.org/anthology/W16-3409 | |
| PWC | https://paperswithcode.com/paper/detecting-grammatical-errors-in-machine |
| Repo | |
| Framework | |
Graphonological Levenshtein Edit Distance: Application for Automated Cognate Identification
| Title | Graphonological Levenshtein Edit Distance: Application for Automated Cognate Identification |
| Authors | Bogdan Babych |
| Abstract | |
| Tasks | Transliteration |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/W16-3402/ |
| https://www.aclweb.org/anthology/W16-3402 | |
| PWC | https://paperswithcode.com/paper/graphonological-levenshtein-edit-distance |
| Repo | |
| Framework | |
A Graphical Pronoun Analysis Tool for the PROTEST Pronoun Evaluation Test Suite
| Title | A Graphical Pronoun Analysis Tool for the PROTEST Pronoun Evaluation Test Suite |
| Authors | Christian Hardmeier, Liane Guillou |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/W16-3418/ |
| https://www.aclweb.org/anthology/W16-3418 | |
| PWC | https://paperswithcode.com/paper/a-graphical-pronoun-analysis-tool-for-the |
| Repo | |
| Framework | |
Automated scalable segmentation of neurons from multispectral images
| Title | Automated scalable segmentation of neurons from multispectral images |
| Authors | Uygar Sümbül, Douglas Roossien, Dawen Cai, Fei Chen, Nicholas Barry, John P. Cunningham, Edward Boyden, Liam Paninski |
| Abstract | Reconstruction of neuroanatomy is a fundamental problem in neuroscience. Stochastic expression of colors in individual cells is a promising tool, although its use in the nervous system has been limited due to various sources of variability in expression. Moreover, the intermingled anatomy of neuronal trees is challenging for existing segmentation algorithms. Here, we propose a method to automate the segmentation of neurons in such (potentially pseudo-colored) images. The method uses spatio-color relations between the voxels, generates supervoxels to reduce the problem size by four orders of magnitude before the final segmentation, and is parallelizable over the supervoxels. To quantify performance and gain insight, we generate simulated images, where the noise level and characteristics, the density of expression, and the number of fluorophore types are variable. We also present segmentations of real Brainbow images of the mouse hippocampus, which reveal many of the dendritic segments. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6549-automated-scalable-segmentation-of-neurons-from-multispectral-images |
| http://papers.nips.cc/paper/6549-automated-scalable-segmentation-of-neurons-from-multispectral-images.pdf | |
| PWC | https://paperswithcode.com/paper/automated-scalable-segmentation-of-neurons |
| Repo | |
| Framework | |
Relation- and Phrase-level Linking of FrameNet with Sar-graphs
| Title | Relation- and Phrase-level Linking of FrameNet with Sar-graphs |
| Authors | Aleks Gabryszak, ra, Sebastian Krause, Leonhard Hennig, Feiyu Xu, Hans Uszkoreit |
| Abstract | Recent research shows the importance of linking linguistic knowledge resources for the creation of large-scale linguistic data. We describe our approach for combining two English resources, FrameNet and sar-graphs, and illustrate the benefits of the linked data in a relation extraction setting. While FrameNet consists of schematic representations of situations, linked to lexemes and their valency patterns, sar-graphs are knowledge resources that connect semantic relations from factual knowledge graphs to the linguistic phrases used to express instances of these relations. We analyze the conceptual similarities and differences of both resources and propose to link sar-graphs and FrameNet on the levels of relations/frames as well as phrases. The former alignment involves a manual ontology mapping step, which allows us to extend sar-graphs with new phrase patterns from FrameNet. The phrase-level linking, on the other hand, is fully automatic. We investigate the quality of the automatically constructed links and identify two main classes of errors. |
| Tasks | Knowledge Graphs, Relation Extraction |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1383/ |
| https://www.aclweb.org/anthology/L16-1383 | |
| PWC | https://paperswithcode.com/paper/relation-and-phrase-level-linking-of-framenet |
| Repo | |
| Framework | |
Multi-step learning and underlying structure in statistical models
| Title | Multi-step learning and underlying structure in statistical models |
| Authors | Maia Fraser |
| Abstract | In multi-step learning, where a final learning task is accomplished via a sequence of intermediate learning tasks, the intuition is that successive steps or levels transform the initial data into representations more and more suited" to the final learning task. A related principle arises in transfer-learning where Baxter (2000) proposed a theoretical framework to study how learning multiple tasks transforms the inductive bias of a learner. The most widespread multi-step learning approach is semi-supervised learning with two steps: unsupervised, then supervised. Several authors (Castelli-Cover, 1996; Balcan-Blum, 2005; Niyogi, 2008; Ben-David et al, 2008; Urner et al, 2011) have analyzed SSL, with Balcan-Blum (2005) proposing a version of the PAC learning framework augmented by a compatibility function” to link concept class and unlabeled data distribution. We propose to analyze SSL and other multi-step learning approaches, much in the spirit of Baxter’s framework, by defining a learning problem generatively as a joint statistical model on $X \times Y$. This determines in a natural way the class of conditional distributions that are possible with each marginal, and amounts to an abstract form of compatibility function. It also allows to analyze both discrete and non-discrete settings. As tool for our analysis, we define a notion of $\gamma$-uniform shattering for statistical models. We use this to give conditions on the marginal and conditional models which imply an advantage for multi-step learning approaches. In particular, we recover a more general version of a result of Poggio et al (2012): under mild hypotheses a multi-step approach which learns features invariant under successive factors of a finite group of invariances has sample complexity requirements that are additive rather than multiplicative in the size of the subgroups. |
| Tasks | Transfer Learning |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6197-multi-step-learning-and-underlying-structure-in-statistical-models |
| http://papers.nips.cc/paper/6197-multi-step-learning-and-underlying-structure-in-statistical-models.pdf | |
| PWC | https://paperswithcode.com/paper/multi-step-learning-and-underlying-structure |
| Repo | |
| Framework | |
Proceedings of the 19th Annual Conference of the EAMT: Projects/Products
| Title | Proceedings of the 19th Annual Conference of the EAMT: Projects/Products |
| Authors | {European Association for Machine Translation} |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/W16-3424/ |
| https://www.aclweb.org/anthology/W16-3424 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-19th-annual-conference-of |
| Repo | |
| Framework | |
Comparing the Template-Based Approach to GF: the case of Afrikaans
| Title | Comparing the Template-Based Approach to GF: the case of Afrikaans |
| Authors | Lauren Sanby, Ion Todd, Maria C. Keet |
| Abstract | |
| Tasks | Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3510/ |
| https://www.aclweb.org/anthology/W16-3510 | |
| PWC | https://paperswithcode.com/paper/comparing-the-template-based-approach-to-gf |
| Repo | |
| Framework | |
A Repository of Frame Instance Lexicalizations for Generation
| Title | A Repository of Frame Instance Lexicalizations for Generation |
| Authors | Valerio Basile |
| Abstract | |
| Tasks | Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3502/ |
| https://www.aclweb.org/anthology/W16-3502 | |
| PWC | https://paperswithcode.com/paper/a-repository-of-frame-instance |
| Repo | |
| Framework | |
QCRI @ DSL 2016: Spoken Arabic Dialect Identification Using Textual Features
| Title | QCRI @ DSL 2016: Spoken Arabic Dialect Identification Using Textual Features |
| Authors | Mohamed Eldesouki, Fahim Dalvi, Hassan Sajjad, Kareem Darwish |
| Abstract | The paper describes the QCRI submissions to the task of automatic Arabic dialect classification into 5 Arabic variants, namely Egyptian, Gulf, Levantine, North-African, and Modern Standard Arabic (MSA). The training data is relatively small and is automatically generated from an ASR system. To avoid over-fitting on such small data, we carefully selected and designed the features to capture the morphological essence of the different dialects. We submitted four runs to the Arabic sub-task. For all runs, we used a combined feature vector of character bi-grams, tri-grams, 4-grams, and 5-grams. We tried several machine-learning algorithms, namely Logistic Regression, Naive Bayes, Neural Networks, and Support Vector Machines (SVM) with linear and string kernels. However, our submitted runs used SVM with a linear kernel. In the closed submission, we got the best accuracy of 0.5136 and the third best weighted F1 score, with a difference less than 0.002 from the highest score. |
| Tasks | Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4828/ |
| https://www.aclweb.org/anthology/W16-4828 | |
| PWC | https://paperswithcode.com/paper/qcri-dsl-2016-spoken-arabic-dialect |
| Repo | |
| Framework | |
