Paper Group NANR 21
A Legal Perspective on Training Models for Natural Language Processing. Moving TIGER beyond Sentence-Level. Low-resource Post Processing of Noisy OCR Output for Historical Corpus Digitisation. Universal Dependencies for Ainu. Bridging the LAPPS Grid and CLARIN. Paraphrastic Variance between European and Brazilian Portuguese. Tilde MT Platform for D …
A Legal Perspective on Training Models for Natural Language Processing
| Title | A Legal Perspective on Training Models for Natural Language Processing |
| Authors | Richard Eckart de Castilho, Giulia Dore, Thomas Margoni, Penny Labropoulou, Iryna Gurevych |
| Abstract | |
| Tasks | Named Entity Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1202/ |
| https://www.aclweb.org/anthology/L18-1202 | |
| PWC | https://paperswithcode.com/paper/a-legal-perspective-on-training-models-for |
| Repo | |
| Framework | |
Moving TIGER beyond Sentence-Level
| Title | Moving TIGER beyond Sentence-Level |
| Authors | Agnieszka Falenska, Kerstin Eckart, Jonas Kuhn |
| Abstract | |
| Tasks | Boundary Detection, Dependency Parsing, Lemmatization, Morphological Analysis, Morphological Tagging, Part-Of-Speech Tagging, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1348/ |
| https://www.aclweb.org/anthology/L18-1348 | |
| PWC | https://paperswithcode.com/paper/moving-tiger-beyond-sentence-level |
| Repo | |
| Framework | |
Low-resource Post Processing of Noisy OCR Output for Historical Corpus Digitisation
| Title | Low-resource Post Processing of Noisy OCR Output for Historical Corpus Digitisation |
| Authors | Caitlin Richter, Matthew Wickes, Deniz Beser, Mitch Marcus |
| Abstract | |
| Tasks | Optical Character Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1369/ |
| https://www.aclweb.org/anthology/L18-1369 | |
| PWC | https://paperswithcode.com/paper/low-resource-post-processing-of-noisy-ocr |
| Repo | |
| Framework | |
Universal Dependencies for Ainu
| Title | Universal Dependencies for Ainu |
| Authors | Hajime Senuma, Akiko Aizawa |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1373/ |
| https://www.aclweb.org/anthology/L18-1373 | |
| PWC | https://paperswithcode.com/paper/universal-dependencies-for-ainu |
| Repo | |
| Framework | |
Bridging the LAPPS Grid and CLARIN
| Title | Bridging the LAPPS Grid and CLARIN |
| Authors | Erhard Hinrichs, Nancy Ide, James Pustejovsky, Jan Haji{\v{c}}, Marie Hinrichs, Mohammad Fazleh Elahi, Keith Suderman, Marc Verhagen, Kyeongmin Rim, Pavel Stra{\v{n}}{'a}k, Jozef Mi{\v{s}}utka |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1206/ |
| https://www.aclweb.org/anthology/L18-1206 | |
| PWC | https://paperswithcode.com/paper/bridging-the-lapps-grid-and-clarin |
| Repo | |
| Framework | |
Paraphrastic Variance between European and Brazilian Portuguese
| Title | Paraphrastic Variance between European and Brazilian Portuguese |
| Authors | Anabela Barreiro, Cristina Mota |
| Abstract | This paper presents a methodology to extract a paraphrase database for the European and Brazilian varieties of Portuguese, and discusses a set of paraphrastic categories of multiwords and phrasal units, such as the compounds {}toda a gente{''} versus {}todo o mundo{''} {}everybody{'} or the gerundive constructions [estar a + V-Inf] versus [ficar + V-Ger] (e.g., {``}estive a observar{''} {``}fiquei observando{''} {}I was observing{'}), which are extremely relevant to high quality paraphrasing. The variants were manually aligned in the e-PACT corpus, using the CLUE-Aligner tool. The methodology, inspired in the Logos Model, focuses on a semantico-syntactic analysis of each paraphrastic unit and constitutes a subset of the Gold-CLUE-Paraphrases. The construction of a larger dataset of paraphrastic contrasts among the distinct varieties of the Portuguese language is indispensable for variety adaptation, i.e., for dealing with the cultural, linguistic and stylistic differences between them, making it possible to convert texts (semi-)automatically from one variety into another, a key function in paraphrasing systems. This topic represents an interesting new line of research with valuable applications in language learning, language generation, question-answering, summarization, and machine translation, among others. The paraphrastic units are the first resource of its kind for Portuguese to become available to the scientific community for research purposes. |
| Tasks | Machine Translation, Question Answering, Text Generation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3912/ |
| https://www.aclweb.org/anthology/W18-3912 | |
| PWC | https://paperswithcode.com/paper/paraphrastic-variance-between-european-and |
| Repo | |
| Framework | |
Tilde MT Platform for Developing Client Specific MT Solutions
| Title | Tilde MT Platform for Developing Client Specific MT Solutions |
| Authors | M{=a}rcis Pinnis, Andrejs Vasi{\c{l}}jevs, Rihards Kalni{\c{n}}{\v{s}}, Roberts Rozis, Raivis Skadi{\c{n}}{\v{s}}, Valters {\v{S}}ics |
| Abstract | |
| Tasks | Common Sense Reasoning, Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1214/ |
| https://www.aclweb.org/anthology/L18-1214 | |
| PWC | https://paperswithcode.com/paper/tilde-mt-platform-for-developing-client |
| Repo | |
| Framework | |
APPLICATION OF DEEP CONVOLUTIONAL NEURAL NETWORK TO PREVENT ATM FRAUD BY FACIAL DISGUISE IDENTIFICATION
| Title | APPLICATION OF DEEP CONVOLUTIONAL NEURAL NETWORK TO PREVENT ATM FRAUD BY FACIAL DISGUISE IDENTIFICATION |
| Authors | Suraj Nandkishor Kothawade, Sumit Baburao Tamgale |
| Abstract | The paper proposes and demonstrates a Deep Convolutional Neural Network (DCNN) architecture to identify users with disguised face attempting a fraudulent ATM transaction. The recent introduction of Disguised Face Identification (DFI) framework proves the applicability of deep neural networks for this very problem. All the ATMs nowadays incorporate a hidden camera in them and capture the footage of their users. However, it is impossible for the police to track down the impersonators with disguised faces from the ATM footage. The proposed deep convolutional neural network is trained to identify, in real time, whether the user in the captured image is trying to cloak his identity or not. The output of the DCNN is then reported to the ATM to take appropriate steps and prevent the swindler from completing the transaction. The network is trained using a dataset of images captured in similar situations as of an ATM. The comparatively low background clutter in the images enables the network to demonstrate high accuracy in feature extraction and classification for all the different disguises. |
| Tasks | Face Identification |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SyhcXjy0Z |
| https://openreview.net/pdf?id=SyhcXjy0Z | |
| PWC | https://paperswithcode.com/paper/application-of-deep-convolutional-neural |
| Repo | |
| Framework | |
Implicit Probabilistic Integrators for ODEs
| Title | Implicit Probabilistic Integrators for ODEs |
| Authors | Onur Teymur, Han Cheng Lie, Tim Sullivan, Ben Calderhead |
| Abstract | We introduce a family of implicit probabilistic integrators for initial value problems (IVPs), taking as a starting point the multistep Adams–Moulton method. The implicit construction allows for dynamic feedback from the forthcoming time-step, in contrast to previous probabilistic integrators, all of which are based on explicit methods. We begin with a concise survey of the rapidly-expanding field of probabilistic ODE solvers. We then introduce our method, which builds on and adapts the work of Conrad et al. (2016) and Teymur et al. (2016), and provide a rigorous proof of its well-definedness and convergence. We discuss the problem of the calibration of such integrators and suggest one approach. We give an illustrative example highlighting the effect of the use of probabilistic integrators—including our new method—in the setting of parameter inference within an inverse problem. |
| Tasks | Calibration |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7955-implicit-probabilistic-integrators-for-odes |
| http://papers.nips.cc/paper/7955-implicit-probabilistic-integrators-for-odes.pdf | |
| PWC | https://paperswithcode.com/paper/implicit-probabilistic-integrators-for-odes |
| Repo | |
| Framework | |
Compact Representation of Uncertainty in Clustering
| Title | Compact Representation of Uncertainty in Clustering |
| Authors | Craig Greenberg, Nicholas Monath, Ari Kobren, Patrick Flaherty, Andrew Mcgregor, Andrew Mccallum |
| Abstract | For many classic structured prediction problems, probability distributions over the dependent variables can be efficiently computed using widely-known algorithms and data structures (such as forward-backward, and its corresponding trellis for exact probability distributions in Markov models). However, we know of no previous work studying efficient representations of exact distributions over clusterings. This paper presents definitions and proofs for a dynamic-programming inference procedure that computes the partition function, the marginal probability of a cluster, and the MAP clustering—all exactly. Rather than the Nth Bell number, these exact solutions take time and space proportional to the substantially smaller powerset of N. Indeed, we improve upon the time complexity of the algorithm introduced by Kohonen and Corander (2016) for this problem by a factor of N. While still large, this previously unknown result is intellectually interesting in its own right, makes feasible exact inference for important real-world small data applications (such as medicine), and provides a natural stepping stone towards sparse-trellis approximations that enable further scalability (which we also explore). In experiments, we demonstrate the superiority of our approach over approximate methods in analyzing real-world gene expression data used in cancer treatment. |
| Tasks | Structured Prediction |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8081-compact-representation-of-uncertainty-in-clustering |
| http://papers.nips.cc/paper/8081-compact-representation-of-uncertainty-in-clustering.pdf | |
| PWC | https://paperswithcode.com/paper/compact-representation-of-uncertainty-in |
| Repo | |
| Framework | |
The Abkhaz National Corpus
| Title | The Abkhaz National Corpus |
| Authors | Paul Meurer |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1390/ |
| https://www.aclweb.org/anthology/L18-1390 | |
| PWC | https://paperswithcode.com/paper/the-abkhaz-national-corpus |
| Repo | |
| Framework | |
Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds
| Title | Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds |
| Authors | Raghav Somani, Chirag Gupta, Prateek Jain, Praneeth Netrapalli |
| Abstract | This paper studies the problem of sparse regression where the goal is to learn a sparse vector that best optimizes a given objective function. Under the assumption that the objective function satisfies restricted strong convexity (RSC), we analyze orthogonal matching pursuit (OMP), a greedy algorithm that is used heavily in applications, and obtain support recovery result as well as a tight generalization error bound for OMP. Furthermore, we obtain lower bounds for OMP, showing that both our results on support recovery and generalization error are tight up to logarithmic factors. To the best of our knowledge, these support recovery and generalization bounds are the first such matching upper and lower bounds (up to logarithmic factors) for {\em any} sparse regression algorithm under the RSC assumption. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8279-support-recovery-for-orthogonal-matching-pursuit-upper-and-lower-bounds |
| http://papers.nips.cc/paper/8279-support-recovery-for-orthogonal-matching-pursuit-upper-and-lower-bounds.pdf | |
| PWC | https://paperswithcode.com/paper/support-recovery-for-orthogonal-matching |
| Repo | |
| Framework | |
Word Embedding and WordNet Based Metaphor Identification and Interpretation
| Title | Word Embedding and WordNet Based Metaphor Identification and Interpretation |
| Authors | Rui Mao, Chenghua Lin, Frank Guerin |
| Abstract | Metaphoric expressions are widespread in natural language, posing a significant challenge for various natural language processing tasks such as Machine Translation. Current word embedding based metaphor identification models cannot identify the exact metaphorical words within a sentence. In this paper, we propose an unsupervised learning method that identifies and interprets metaphors at word-level without any preprocessing, outperforming strong baselines in the metaphor identification task. Our model extends to interpret the identified metaphors, paraphrasing them into their literal counterparts, so that they can be better translated by machines. We evaluated this with two popular translation systems for English to Chinese, showing that our model improved the systems significantly. |
| Tasks | Decision Making, Machine Translation, Sentiment Analysis, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1113/ |
| https://www.aclweb.org/anthology/P18-1113 | |
| PWC | https://paperswithcode.com/paper/word-embedding-and-wordnet-based-metaphor |
| Repo | |
| Framework | |
The Morpho-syntactic Annotation of Animacy for a Dependency Parser
| Title | The Morpho-syntactic Annotation of Animacy for a Dependency Parser |
| Authors | Mohammed Attia, Vitaly Nikolaev, Ali Elkahky |
| Abstract | |
| Tasks | Dependency Parsing, Text Generation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1414/ |
| https://www.aclweb.org/anthology/L18-1414 | |
| PWC | https://paperswithcode.com/paper/the-morpho-syntactic-annotation-of-animacy |
| Repo | |
| Framework | |
Simple random search of static linear policies is competitive for reinforcement learning
| Title | Simple random search of static linear policies is competitive for reinforcement learning |
| Authors | Horia Mania, Aurelia Guy, Benjamin Recht |
| Abstract | Model-free reinforcement learning aims to offer off-the-shelf solutions for controlling dynamical systems without requiring models of the system dynamics. We introduce a model-free random search algorithm for training static, linear policies for continuous control problems. Common evaluation methodology shows that our method matches state-of-the-art sample efficiency on the benchmark MuJoCo locomotion tasks. Nonetheless, more rigorous evaluation reveals that the assessment of performance on these benchmarks is optimistic. We evaluate the performance of our method over hundreds of random seeds and many different hyperparameter configurations for each benchmark task. This extensive evaluation is possible because of the small computational footprint of our method. Our simulations highlight a high variability in performance in these benchmark tasks, indicating that commonly used estimations of sample efficiency do not adequately evaluate the performance of RL algorithms. Our results stress the need for new baselines, benchmarks and evaluation methodology for RL algorithms. |
| Tasks | Continuous Control |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7451-simple-random-search-of-static-linear-policies-is-competitive-for-reinforcement-learning |
| http://papers.nips.cc/paper/7451-simple-random-search-of-static-linear-policies-is-competitive-for-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/simple-random-search-of-static-linear |
| Repo | |
| Framework | |
