Paper Group NANR 153
Dep_search: Efficient Search Tool for Large Dependency Parsebanks. LMU Munich’s Neural Machine Translation Systems for News Articles and Health Information Texts. A Birth-Death Process for Feature Allocation. NTNU-2 at SemEval-2017 Task 10: Identifying Synonym and Hyponym Relations among Keyphrases in Scientific Documents. Radiometric Calibration …
Dep_search: Efficient Search Tool for Large Dependency Parsebanks
| Title | Dep_search: Efficient Search Tool for Large Dependency Parsebanks |
| Authors | Juhani Luotolahti, Jenna Kanerva, Filip Ginter |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0233/ |
| https://www.aclweb.org/anthology/W17-0233 | |
| PWC | https://paperswithcode.com/paper/dep_search-efficient-search-tool-for-large |
| Repo | |
| Framework | |
LMU Munich’s Neural Machine Translation Systems for News Articles and Health Information Texts
| Title | LMU Munich’s Neural Machine Translation Systems for News Articles and Health Information Texts |
| Authors | Matthias Huck, Fabienne Braune, Alex Fraser, er |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4730/ |
| https://www.aclweb.org/anthology/W17-4730 | |
| PWC | https://paperswithcode.com/paper/lmu-munichs-neural-machine-translation |
| Repo | |
| Framework | |
A Birth-Death Process for Feature Allocation
| Title | A Birth-Death Process for Feature Allocation |
| Authors | Konstantina Palla, David Knowles, Zoubin Ghahramani |
| Abstract | We propose a Bayesian nonparametric prior over feature allocations for sequential data, the birth-death feature allocation process (BDFP). The BDFP models the evolution of the feature allocation of a set of N objects across a covariate (e.g.~time) by creating and deleting features. A BDFP is exchangeable, projective, stationary and reversible, and its equilibrium distribution is given by the Indian buffet process (IBP). We show that the Beta process on an extended space is the de Finetti mixing distribution underlying the BDFP. Finally, we present the finite approximation of the BDFP, the Beta Event Process (BEP), that permits simplified inference. The utility of the BDFP as a prior is demonstrated on real world dynamic genomics and social network data. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=692 |
| http://proceedings.mlr.press/v70/palla17a/palla17a.pdf | |
| PWC | https://paperswithcode.com/paper/a-birth-death-process-for-feature-allocation |
| Repo | |
| Framework | |
NTNU-2 at SemEval-2017 Task 10: Identifying Synonym and Hyponym Relations among Keyphrases in Scientific Documents
| Title | NTNU-2 at SemEval-2017 Task 10: Identifying Synonym and Hyponym Relations among Keyphrases in Scientific Documents |
| Authors | Biswanath Barik, Erwin Marsi |
| Abstract | This paper presents our relation extraction system for subtask C of SemEval-2017 Task 10: ScienceIE. Assuming that the keyphrases are already annotated in the input data, our work explores a wide range of linguistic features, applies various feature selection techniques, optimizes the hyper parameters and class weights and experiments with different problem formulations (single classification model vs individual classifiers for each keyphrase type, single-step classifier vs pipeline classifier for hyponym relations). Performance of five popular classification algorithms are evaluated for each problem formulation along with feature selection. The best setting achieved an F1 score of 71.0{%} for synonym and 30.0{%} for hyponym relation on the test data. |
| Tasks | Feature Selection, Knowledge Base Completion, Relation Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2168/ |
| https://www.aclweb.org/anthology/S17-2168 | |
| PWC | https://paperswithcode.com/paper/ntnu-2-at-semeval-2017-task-10-identifying |
| Repo | |
| Framework | |
Radiometric Calibration for Internet Photo Collections
| Title | Radiometric Calibration for Internet Photo Collections |
| Authors | Zhipeng Mo, Boxin Shi, Sai-Kit Yeung, Yasuyuki Matsushita |
| Abstract | Radiometrically calibrating the images from Internet photo collections brings photometric analysis from lab data to big image data in the wild, but conventional calibration methods cannot be directly applied to such image data. This paper presents a method to jointly perform radiometric calibration for a set of images in an Internet photo collection. By incorporating the consistency of scene reflectance for corresponding pixels in multiple images, the proposed method estimates radiometric response functions of all the images using a rank minimization framework. Our calibration aligns all response functions in an image set up to the same exponential ambiguity in a robust manner. Quantitative results using both synthetic and real data show the effectiveness of the proposed method. |
| Tasks | Calibration |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Mo_Radiometric_Calibration_for_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Mo_Radiometric_Calibration_for_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/radiometric-calibration-for-internet-photo |
| Repo | |
| Framework | |
Universal Dependencies for Swedish Sign Language
| Title | Universal Dependencies for Swedish Sign Language |
| Authors | Robert {"O}stling, Carl B{"o}rstell, Moa G{"a}rdenfors, Mats Wir{'e}n |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0243/ |
| https://www.aclweb.org/anthology/W17-0243 | |
| PWC | https://paperswithcode.com/paper/universal-dependencies-for-swedish-sign |
| Repo | |
| Framework | |
Nonsymbolic Text Representation
| Title | Nonsymbolic Text Representation |
| Authors | Hinrich Sch{"u}tze |
| Abstract | We introduce the first generic text representation model that is completely nonsymbolic, i.e., it does not require the availability of a segmentation or tokenization method that attempts to identify words or other symbolic units in text. This applies to training the parameters of the model on a training corpus as well as to applying it when computing the representation of a new text. We show that our model performs better than prior work on an information extraction and a text denoising task. |
| Tasks | Denoising, Entity Typing, Representation Learning, Tokenization, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1074/ |
| https://www.aclweb.org/anthology/E17-1074 | |
| PWC | https://paperswithcode.com/paper/nonsymbolic-text-representation-1 |
| Repo | |
| Framework | |
DEMO: Giellatekno Open-source click-in-text dictionaries for bringing closely related languages into contact.
| Title | DEMO: Giellatekno Open-source click-in-text dictionaries for bringing closely related languages into contact. |
| Authors | Jack Rueter |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-0602/ |
| https://www.aclweb.org/anthology/W17-0602 | |
| PWC | https://paperswithcode.com/paper/demo-giellatekno-open-source-click-in-text |
| Repo | |
| Framework | |
Parsing with Dynamic Continuized CCG
| Title | Parsing with Dynamic Continuized CCG |
| Authors | Michael White, Simon Charlow, Jordan Needle, Dylan Bumford |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6208/ |
| https://www.aclweb.org/anthology/W17-6208 | |
| PWC | https://paperswithcode.com/paper/parsing-with-dynamic-continuized-ccg |
| Repo | |
| Framework | |
Parsing Minimalist Languages with Interpreted Regular Tree Grammars
| Title | Parsing Minimalist Languages with Interpreted Regular Tree Grammars |
| Authors | Meaghan Fowlie, Alex Koller, er |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6202/ |
| https://www.aclweb.org/anthology/W17-6202 | |
| PWC | https://paperswithcode.com/paper/parsing-minimalist-languages-with-interpreted |
| Repo | |
| Framework | |
Lexical Acquisition through Implicit Confirmations over Multiple Dialogues
| Title | Lexical Acquisition through Implicit Confirmations over Multiple Dialogues |
| Authors | Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano, Kazunori Komatani |
| Abstract | We address the problem of acquiring the ontological categories of unknown terms through implicit confirmation in dialogues. We develop an approach that makes implicit confirmation requests with an unknown term{'}s predicted category. Our approach does not degrade user experience with repetitive explicit confirmations, but the system has difficulty determining if information in the confirmation request can be correctly acquired. To overcome this challenge, we propose a method for determining whether or not the predicted category is correct, which is included in an implicit confirmation request. Our method exploits multiple user responses to implicit confirmation requests containing the same ontological category. Experimental results revealed that the proposed method exhibited a higher precision rate for determining the correctly predicted categories than when only single user responses were considered. |
| Tasks | Chatbot, Task-Oriented Dialogue Systems |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5507/ |
| https://www.aclweb.org/anthology/W17-5507 | |
| PWC | https://paperswithcode.com/paper/lexical-acquisition-through-implicit |
| Repo | |
| Framework | |
Geometry of Neural Network Loss Surfaces via Random Matrix Theory
| Title | Geometry of Neural Network Loss Surfaces via Random Matrix Theory |
| Authors | Jeffrey Pennington, Yasaman Bahri |
| Abstract | Understanding the geometry of neural network loss surfaces is important for the development of improved optimization algorithms and for building a theoretical understanding of why deep learning works. In this paper, we study the geometry in terms of the distribution of eigenvalues of the Hessian matrix at critical points of varying energy. We introduce an analytical framework and a set of tools from random matrix theory that allow us to compute an approximation of this distribution under a set of simplifying assumptions. The shape of the spectrum depends strongly on the energy and another key parameter, $\phi$, which measures the ratio of parameters to data points. Our analysis predicts and numerical simulations support that for critical points of small index, the number of negative eigenvalues scales like the 3/2 power of the energy. We leave as an open problem an explanation for our observation that, in the context of a certain memorization task, the energy of minimizers is well-approximated by the function $1/2(1-\phi)^2$. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=655 |
| http://proceedings.mlr.press/v70/pennington17a/pennington17a.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-of-neural-network-loss-surfaces-via |
| Repo | |
| Framework | |
Telling Apart Tweets Associated with Controversial versus Non-Controversial Topics
| Title | Telling Apart Tweets Associated with Controversial versus Non-Controversial Topics |
| Authors | Aseel Addawood, Rezvaneh Rezapour, Omid Abdar, Jana Diesner |
| Abstract | In this paper, we evaluate the predictability of tweets associated with controversial versus non-controversial topics. As a first step, we crowd-sourced the scoring of a predefined set of topics on a Likert scale from non-controversial to controversial. Our feature set entails and goes beyond sentiment features, e.g., by leveraging empathic language and other features that have been previously used but are new for this particular study. We find focusing on the structural characteristics of tweets to be beneficial for this task. Using a combination of emphatic, language-specific, and Twitter-specific features for supervised learning resulted in 87{%} accuracy (F1) for cross-validation of the training set and 63.4{%} accuracy when using the test set. Our analysis shows that features specific to Twitter or social media, in general, are more prevalent in tweets on controversial topics than in non-controversial ones. To test the premise of the paper, we conducted two additional sets of experiments, which led to mixed results. This finding will inform our future investigations into the relationship between language use on social media and the perceived controversiality of topics. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2905/ |
| https://www.aclweb.org/anthology/W17-2905 | |
| PWC | https://paperswithcode.com/paper/telling-apart-tweets-associated-with |
| Repo | |
| Framework | |
DPSCREEN: Dynamic Personalized Screening
| Title | DPSCREEN: Dynamic Personalized Screening |
| Authors | Kartik Ahuja, William Zame, Mihaela Van Der Schaar |
| Abstract | Screening is important for the diagnosis and treatment of a wide variety of diseases. A good screening policy should be personalized to the disease, to the features of the patient and to the dynamic history of the patient (including the history of screening). The growth of electronic health records data has led to the development of many models to predict the onset and progression of different diseases. However, there has been limited work to address the personalized screening for these different diseases. In this work, we develop the first framework to construct screening policies for a large class of disease models. The disease is modeled as a finite state stochastic process with an absorbing disease state. The patient observes an external information process (for instance, self-examinations, discovering comorbidities, etc.) which can trigger the patient to arrive at the clinician earlier than scheduled screenings. The clinician carries out the tests; based on the test results and the external information it schedules the next arrival. Computing the exactly optimal screening policy that balances the delay in the detection against the frequency of screenings is computationally intractable; this paper provides a computationally tractable construction of an approximately optimal policy. As an illustration, we make use of a large breast cancer data set. The constructed policy screens patients more or less often according to their initial risk – it is personalized to the features of the patient – and according to the results of previous screens – it is personalized to the history of the patient. In comparison with existing clinical policies, the constructed policy leads to large reductions (28-68 %) in the number of screens performed while achieving the same expected delays in disease detection. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6731-dpscreen-dynamic-personalized-screening |
| http://papers.nips.cc/paper/6731-dpscreen-dynamic-personalized-screening.pdf | |
| PWC | https://paperswithcode.com/paper/dpscreen-dynamic-personalized-screening |
| Repo | |
| Framework | |
A Semismooth Newton Method for Fast, Generic Convex Programming
| Title | A Semismooth Newton Method for Fast, Generic Convex Programming |
| Authors | Alnur Ali, Eric Wong, J. Zico Kolter |
| Abstract | We introduce Newton-ADMM, a method for fast conic optimization. The basic idea is to view the residuals of consecutive iterates generated by the alternating direction method of multipliers (ADMM) as a set of fixed point equations, and then use a nonsmooth Newton method to find a solution; we apply the basic idea to the Splitting Cone Solver (SCS), a state-of-the-art method for solving generic conic optimization problems. We demonstrate theoretically, by extending the theory of semismooth operators, that Newton-ADMM converges rapidly (i.e., quadratically) to a solution; empirically, Newton-ADMM is significantly faster than SCS on a number of problems. The method also has essentially no tuning parameters, generates certificates of primal or dual infeasibility, when appropriate, and can be specialized to solve specific convex problems. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=512 |
| http://proceedings.mlr.press/v70/ali17a/ali17a.pdf | |
| PWC | https://paperswithcode.com/paper/a-semismooth-newton-method-for-fast-generic |
| Repo | |
| Framework | |
