Paper Group NAWR 11
Measuring Semantic Similarity of Words Using Concept Networks. CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing. MMFeat: A Toolkit for Extracting Multi-Modal Features. Dealing with Out-Of-Vocabulary Problem in Sentence Alignment Using Word Similarity. GAP Safe Screening Rules for Sparse-Group Lasso. Binary Pattern Dictionary Learnin …
Measuring Semantic Similarity of Words Using Concept Networks
| Title | Measuring Semantic Similarity of Words Using Concept Networks |
| Authors | G{'a}bor Recski, Eszter Ikl{'o}di, Katalin Pajkossy, Andr{'a}s Kornai |
| Abstract | |
| Tasks | Representation Learning, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1622/ |
| https://www.aclweb.org/anthology/W16-1622 | |
| PWC | https://paperswithcode.com/paper/measuring-semantic-similarity-of-words-using |
| Repo | https://github.com/recski/wordsim |
| Framework | none |
CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing
| Title | CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing |
| Authors | Nianwen Xue, Hwee Tou Ng, Sameer Pradhan, Attapol Rutherford, Bonnie Webber, Chuan Wang, Hongmin Wang |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-2001/ |
| https://www.aclweb.org/anthology/K16-2001 | |
| PWC | https://paperswithcode.com/paper/conll-2016-shared-task-on-multilingual |
| Repo | https://github.com/attapol/conll16st |
| Framework | none |
MMFeat: A Toolkit for Extracting Multi-Modal Features
| Title | MMFeat: A Toolkit for Extracting Multi-Modal Features |
| Authors | Douwe Kiela |
| Abstract | |
| Tasks | Semantic Textual Similarity |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4010/ |
| https://www.aclweb.org/anthology/P16-4010 | |
| PWC | https://paperswithcode.com/paper/mmfeat-a-toolkit-for-extracting-multi-modal |
| Repo | https://github.com/douwekiela/mmfeat |
| Framework | none |
Dealing with Out-Of-Vocabulary Problem in Sentence Alignment Using Word Similarity
| Title | Dealing with Out-Of-Vocabulary Problem in Sentence Alignment Using Word Similarity |
| Authors | Hai-Long Trieu, Le-Minh Nguyen, Phuong-Thai Nguyen |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-2024/ |
| https://www.aclweb.org/anthology/Y16-2024 | |
| PWC | https://paperswithcode.com/paper/dealing-with-out-of-vocabulary-problem-in |
| Repo | https://github.com/nguyenlab/SentAlign-Similarity |
| Framework | none |
GAP Safe Screening Rules for Sparse-Group Lasso
| Title | GAP Safe Screening Rules for Sparse-Group Lasso |
| Authors | Eugene Ndiaye, Olivier Fercoq, Alexandre Gramfort, Joseph Salmon |
| Abstract | For statistical learning in high dimension, sparse regularizations have proven useful to boost both computational and statistical efficiency. In some contexts, it is natural to handle more refined structures than pure sparsity, such as for instance group sparsity. Sparse-Group Lasso has recently been introduced in the context of linear regression to enforce sparsity both at the feature and at the group level. We propose the first (provably) safe screening rules for Sparse-Group Lasso, i.e., rules that allow to discard early in the solver features/groups that are inactive at optimal solution. Thanks to efficient dual gap computations relying on the geometric properties of $\epsilon$-norm, safe screening rules for Sparse-Group Lasso lead to significant gains in term of computing time for our coordinate descent implementation. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6405-gap-safe-screening-rules-for-sparse-group-lasso |
| http://papers.nips.cc/paper/6405-gap-safe-screening-rules-for-sparse-group-lasso.pdf | |
| PWC | https://paperswithcode.com/paper/gap-safe-screening-rules-for-sparse-group-1 |
| Repo | https://github.com/EugeneNdiaye/GAPSAFE_SGL |
| Framework | none |
Binary Pattern Dictionary Learning for Gene Expression Representation in Drosophila Imaginal Discs.
| Title | Binary Pattern Dictionary Learning for Gene Expression Representation in Drosophila Imaginal Discs. |
| Authors | Jiří Borovec, Jan Kybic |
| Abstract | We present an image processing pipeline which accepts a large number of images, containing spatial expression information for thousands of genes in Drosophila imaginal discs. We assume that the gene activations are binary and can be expressed as a union of a small set of non-overlapping spatial patterns, yielding a compact representation of the spatial activation of each gene. This lends itself well to further automatic analysis, with the hope of discovering new biological relationships. Traditionally, the images were labeled manually, which was very time consuming. The key part of our work is a binary pattern dictionary learning algorithm, that takes a set of binary images and determines a set of patterns, which can be used to represent the input images with a small error. We also describe the preprocessing phase, where input images are segmented to recover the activation images and spatially aligned to a common reference. We compare binary pattern dictionary learning to existing alternative methods on synthetic data and also show results of the algorithm on real microscopy images of the Drosophila imaginal discs. |
| Tasks | Dictionary Learning |
| Published | 2016-11-23 |
| URL | https://link.springer.com/chapter/10.1007%2F978-3-319-54427-4_40 |
| https://link.springer.com/chapter/10.1007%2F978-3-319-54427-4_40 | |
| PWC | https://paperswithcode.com/paper/binary-pattern-dictionary-learning-for-gene |
| Repo | https://github.com/Borda/pyBPDL |
| Framework | none |
Improved Deep Metric Learning with Multi-class N-pair Loss Objective
| Title | Improved Deep Metric Learning with Multi-class N-pair Loss Objective |
| Authors | Kihyuk Sohn |
| Abstract | Deep metric learning has gained much popularity in recent years, following the success of deep learning. However, existing frameworks of deep metric learning based on contrastive loss and triplet loss often suffer from slow convergence, partially because they employ only one negative example while not interacting with the other negative classes in each update. In this paper, we propose to address this problem with a new metric learning objective called multi-class N-pair loss. The proposed objective function firstly generalizes triplet loss by allowing joint comparison among more than one negative examples – more specifically, N-1 negative examples – and secondly reduces the computational burden of evaluating deep embedding vectors via an efficient batch construction strategy using only N pairs of examples, instead of (N+1)×N. We demonstrate the superiority of our proposed loss to the triplet loss as well as other competing loss functions for a variety of tasks on several visual recognition benchmark, including fine-grained object recognition and verification, image clustering and retrieval, and face verification and identification. |
| Tasks | Face Verification, Image Clustering, Metric Learning, Object Recognition |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6200-improved-deep-metric-learning-with-multi-class-n-pair-loss-objective |
| http://papers.nips.cc/paper/6200-improved-deep-metric-learning-with-multi-class-n-pair-loss-objective.pdf | |
| PWC | https://paperswithcode.com/paper/improved-deep-metric-learning-with-multi |
| Repo | https://github.com/Confusezius/Deep-Metric-Learning-Baselines |
| Framework | pytorch |
Automatic Analysis of Flaws in Pre-Trained NLP Models
| Title | Automatic Analysis of Flaws in Pre-Trained NLP Models |
| Authors | Richard Eckart de Castilho |
| Abstract | Most tools for natural language processing today are based on machine learning and come with pre-trained models. In addition, third-parties provide pre-trained models for popular NLP tools. The predictive power and accuracy of these tools depends on the quality of these models. Downstream researchers often base their results on pre-trained models instead of training their own. Consequently, pre-trained models are an essential resource to our community. However, to be best of our knowledge, no systematic study of pre-trained models has been conducted so far. This paper reports on the analysis of 274 pre-models for six NLP tools and four potential causes of problems: encoding, tokenization, normalization and change over time. The analysis is implemented in the open source tool Model Investigator. Our work 1) allows model consumers to better assess whether a model is suitable for their task, 2) enables tool and model creators to sanity-check their models before distributing them, and 3) enables improvements in tool interoperability by performing automatic adjustments of normalization or other pre-processing based on the models used. |
| Tasks | Tokenization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5203/ |
| https://www.aclweb.org/anthology/W16-5203 | |
| PWC | https://paperswithcode.com/paper/automatic-analysis-of-flaws-in-pre-trained |
| Repo | https://github.com/UKPLab/coling2016-modelinspector |
| Framework | none |
Scalable Hyperparameter Optimization with Products of Gaussian Process Experts
| Title | Scalable Hyperparameter Optimization with Products of Gaussian Process Experts |
| Authors | Nicolas Schilling, Martin Wistuba, Lars Schmidt-Thieme |
| Abstract | In machine learning, hyperparameter optimization is a challenging but necessary task that is usually approached in a computationally expensive manner such as grid-search. Out of this reason, surrogate based black-box optimization techniques such as sequential model-based optimization have been proposed which allow for a faster hyperparameter optimization. Recent research proposes to also integrate hyperparameter performances on past data sets to allow for a faster and more efficient hyperparameter optimization. In this paper, we use products of Gaussian process experts as surrogate models for hyperparameter optimization. Naturally, Gaussian processes are a decent choice as they offer good prediction accuracy as well as estimations about their uncertainty. Additionally, their hyperparameters can be tuned very effectively. However, in the light of large meta data sets, learning a single Gaussian process is not feasible as it involves inversion of a large kernel matrix. This directly limits their usefulness for hyperparameter optimization if large scale hyperparameter performances on past data sets are given. By using products of Gaussian process experts the scalability issues can be circumvented, however, this usually comes with the price of having less predictive accuracy. In our experiments, we show empirically that products of experts nevertheless perform very well compared to a variety of published surrogate models. Thus, we propose a surrogate model that performs as well as the current state of the art, is scalable to large scale meta knowledge, does not include hyperparameters itself and finally is even very easy to parallelize. |
| Tasks | Gaussian Processes, Hyperparameter Optimization |
| Published | 2016-09-04 |
| URL | https://link.springer.com/chapter/10.1007/978-3-319-46128-1_3 |
| https://www.ismll.uni-hildesheim.de/pub/pdfs/schilling-ecml2016.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-hyperparameter-optimization-with |
| Repo | https://github.com/nicoschilling/ECML2016 |
| Framework | none |
Real-time News Story Detection and Tracking with Hashtags
| Title | Real-time News Story Detection and Tracking with Hashtags |
| Authors | Gevorg Poghosyan, Georgiana Ifrim |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-5703/ |
| https://www.aclweb.org/anthology/W16-5703 | |
| PWC | https://paperswithcode.com/paper/real-time-news-story-detection-and-tracking |
| Repo | https://github.com/gevra/may2016-stories |
| Framework | none |
Kyoto University Participation to WAT 2016
| Title | Kyoto University Participation to WAT 2016 |
| Authors | Fabien Cromieres, Chenhui Chu, Toshiaki Nakazawa, Sadao Kurohashi |
| Abstract | We describe here our approaches and results on the WAT 2016 shared translation tasks. We tried to use both an example-based machine translation (MT) system and a neural MT system. We report very good translation results, especially when using neural MT for Chinese-to-Japanese translation. |
| Tasks | Machine Translation, Spelling Correction |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4616/ |
| https://www.aclweb.org/anthology/W16-4616 | |
| PWC | https://paperswithcode.com/paper/kyoto-university-participation-to-wat-2016 |
| Repo | https://github.com/fabiencro/knmt |
| Framework | none |
LFRT, A MATLAB Toolbox for Load Forecast & Assesment of Additional Capacity for an Electrical Power System
| Title | LFRT, A MATLAB Toolbox for Load Forecast & Assesment of Additional Capacity for an Electrical Power System |
| Authors | Hazoor Ahmad, Muhammad Tariq, Awais Qarni, Intisar Ali Sajjad |
| Abstract | A developing country like Pakistan with sizable pressure on their limited financial resources can ill afford either of these two situations about energy forecast: 1) Too optimistic 2) Too conservative. Unlike all other field of research, load forecasting and reliability fields were lagging such a tool that can provide a juncture of all the function of load forecast and reliability on a single platform. Before the evolution of LOLP assessments of additional capacity of a power generating system was a big problem with different inaccurate solutions. This paper presents LFRT, a MATLAB Toolbox that contains set of routines to calculate the Load Forecast for medium term and long term, Capacity outage rates, capacity outage probability, and LOLP and LOLE, in case of unit’s availability-unavailability, load forecast uncertainty and addition or removal of units. Along with several other examples, LFRT is employed to solve for the assessment of additional capacity of hypothetical model of Tarbela hydro power plant after the installation of Tarbela-IV Extension Project. |
| Tasks | Load Forecasting |
| Published | 2016-04-12 |
| URL | https://www.academia.edu/32227321/LFRT_A_MATLAB_Toolbox_for_Load_Forecast_and_Assesment_of_Additional_Capacity_for_an_Electrical_Power_System |
| https://www.academia.edu/32227321/LFRT_A_MATLAB_Toolbox_for_Load_Forecast_and_Assesment_of_Additional_Capacity_for_an_Electrical_Power_System | |
| PWC | https://paperswithcode.com/paper/lfrt-a-matlab-toolbox-for-load-forecast |
| Repo | https://github.com/hazooree/lfrt |
| Framework | none |
Discourse Sense Classification from Scratch using Focused RNNs
| Title | Discourse Sense Classification from Scratch using Focused RNNs |
| Authors | Gregor Weiss, Marko Bajec |
| Abstract | |
| Tasks | Chunking |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-2006/ |
| https://www.aclweb.org/anthology/K16-2006 | |
| PWC | https://paperswithcode.com/paper/discourse-sense-classification-from-scratch |
| Repo | https://github.com/gw0/conll16st-v34-focused-rnns |
| Framework | none |
Exploration of register-dependent lexical semantics using word embeddings
| Title | Exploration of register-dependent lexical semantics using word embeddings |
| Authors | Andrey Kutuzov, Elizaveta Kuzmenko, Anna Marakasova |
| Abstract | We present an approach to detect differences in lexical semantics across English language registers, using word embedding models from distributional semantics paradigm. Models trained on register-specific subcorpora of the BNC corpus are employed to compare lists of nearest associates for particular words and draw conclusions about their semantic shifts depending on register in which they are used. The models are evaluated on the task of register classification with the help of the deep inverse regression approach. Additionally, we present a demo web service featuring most of the described models and allowing to explore word meanings in different English registers and to detect register affiliation for arbitrary texts. The code for the service can be easily adapted to any set of underlying models. |
| Tasks | Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4005/ |
| https://www.aclweb.org/anthology/W16-4005 | |
| PWC | https://paperswithcode.com/paper/exploration-of-register-dependent-lexical |
| Repo | https://github.com/ElizavetaKuzmenko/dsm_genres |
| Framework | none |
Learning to Answer Biomedical Questions: OAQA at BioASQ 4B
| Title | Learning to Answer Biomedical Questions: OAQA at BioASQ 4B |
| Authors | Zi Yang, Yue Zhou, Eric Nyberg |
| Abstract | |
| Tasks | Question Answering |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-3104/ |
| https://www.aclweb.org/anthology/W16-3104 | |
| PWC | https://paperswithcode.com/paper/learning-to-answer-biomedical-questions-oaqa |
| Repo | https://github.com/oaqa/bioasq |
| Framework | none |
