Paper Group NANR 100
From FOAF to English: Linguistic Contribution to Web Semantics. Targeting EEG/LFP Synchrony with Neural Nets. Non-Markovian Globally Consistent Multi-Object Tracking. INGEOTEC at SemEval 2017 Task 4: A B4MSA Ensemble based on Genetic Programming for Twitter Sentiment Analysis. TSA-INF at SemEval-2017 Task 4: An Ensemble of Deep Learning Architectur …
From FOAF to English: Linguistic Contribution to Web Semantics
| Title | From FOAF to English: Linguistic Contribution to Web Semantics |
| Authors | Max Silberztein |
| Abstract | |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3801/ |
| https://www.aclweb.org/anthology/W17-3801 | |
| PWC | https://paperswithcode.com/paper/from-foaf-to-english-linguistic-contribution |
| Repo | |
| Framework | |
Targeting EEG/LFP Synchrony with Neural Nets
| Title | Targeting EEG/LFP Synchrony with Neural Nets |
| Authors | Yitong Li, Michael Murias, Samantha Major, Geraldine Dawson, Kafui Dzirasa, Lawrence Carin, David E. Carlson |
| Abstract | We consider the analysis of Electroencephalography (EEG) and Local Field Potential (LFP) datasets, which are “big” in terms of the size of recorded data but rarely have sufficient labels required to train complex models (e.g., conventional deep learning methods). Furthermore, in many scientific applications, the goal is to be able to understand the underlying features related to the classification, which prohibits the blind application of deep networks. This motivates the development of a new model based on {\em parameterized} convolutional filters guided by previous neuroscience research; the filters learn relevant frequency bands while targeting synchrony, which are frequency-specific power and phase correlations between electrodes. This results in a highly expressive convolutional neural network with only a few hundred parameters, applicable to smaller datasets. The proposed approach is demonstrated to yield competitive (often state-of-the-art) predictive performance during our empirical tests while yielding interpretable features. Furthermore, a Gaussian process adapter is developed to combine analysis over distinct electrode layouts, allowing the joint processing of multiple datasets to address overfitting and improve generalizability. Finally, it is demonstrated that the proposed framework effectively tracks neural dynamics on children in a clinical trial on Autism Spectrum Disorder. |
| Tasks | EEG |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7048-targeting-eeglfp-synchrony-with-neural-nets |
| http://papers.nips.cc/paper/7048-targeting-eeglfp-synchrony-with-neural-nets.pdf | |
| PWC | https://paperswithcode.com/paper/targeting-eeglfp-synchrony-with-neural-nets |
| Repo | |
| Framework | |
Non-Markovian Globally Consistent Multi-Object Tracking
| Title | Non-Markovian Globally Consistent Multi-Object Tracking |
| Authors | Andrii Maksai, Xinchao Wang, Francois Fleuret, Pascal Fua |
| Abstract | Many state-of-the-art approaches to multi-object tracking rely on detecting them in each frame independently, grouping detections into short but reliable trajectory segments, and then further grouping them into full trajectories. This grouping typically relies on imposing local smoothness constraints but almost never on enforcing more global ones on the trajectories. In this paper, we propose a non-Markovian approach to imposing global consistency by using behavioral patterns to guide the tracking algorithm. When used in conjunction with state-of-the-art tracking algorithms, this further increases their already good performance on multiple challenging datasets. We show significant improvements both in supervised settings where ground truth is available and behavioral patterns can be learned from it, and in completely unsupervised settings. |
| Tasks | Multi-Object Tracking, Object Tracking |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Maksai_Non-Markovian_Globally_Consistent_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Maksai_Non-Markovian_Globally_Consistent_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/non-markovian-globally-consistent-multi |
| Repo | |
| Framework | |
INGEOTEC at SemEval 2017 Task 4: A B4MSA Ensemble based on Genetic Programming for Twitter Sentiment Analysis
| Title | INGEOTEC at SemEval 2017 Task 4: A B4MSA Ensemble based on Genetic Programming for Twitter Sentiment Analysis |
| Authors | Mir, Sabino a-Jim{'e}nez, Mario Graff, Eric Sadit Tellez, Daniela Moctezuma |
| Abstract | This paper describes the system used in SemEval-2017 Task 4 (Subtask A): Message Polarity Classification for both English and Arabic languages. Our proposed system is an ensemble of two layers, the first one uses our generic framework for multilingual polarity classification (B4MSA) and the second layer combines all the decision function values predicted by B4MSA systems using a non-linear function evolved using a Genetic Programming system, EvoDAG. With this approach, the best performances reached by our system were macro-recall 0.68 (English) and 0.477 (Arabic) which set us in sixth and fourth positions in the results table, respectively. |
| Tasks | Combinatorial Optimization, Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2130/ |
| https://www.aclweb.org/anthology/S17-2130 | |
| PWC | https://paperswithcode.com/paper/ingeotec-at-semeval-2017-task-4-a-b4msa |
| Repo | |
| Framework | |
TSA-INF at SemEval-2017 Task 4: An Ensemble of Deep Learning Architectures Including Lexicon Features for Twitter Sentiment Analysis
| Title | TSA-INF at SemEval-2017 Task 4: An Ensemble of Deep Learning Architectures Including Lexicon Features for Twitter Sentiment Analysis |
| Authors | Amit Ajit Deshmane, Jasper Friedrichs |
| Abstract | This paper describes the submission of team TSA-INF to SemEval-2017 Task 4 Subtask A. The submitted system is an ensemble of three varying deep learning architectures for sentiment analysis. The core of the architecture is a convolutional neural network that performs well on text classification as is. The second subsystem is a gated recurrent neural network implementation. Additionally, the third system integrates opinion lexicons directly into a convolution neural network architecture. The resulting ensemble of the three architectures achieved a top ten ranking with a macro-averaged recall of 64.3{%}. Additional results comparing variations of the submitted system are not conclusive enough to determine a best architecture, but serve as a benchmark for further implementations. |
| Tasks | Sentiment Analysis, Text Classification, Twitter Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2135/ |
| https://www.aclweb.org/anthology/S17-2135 | |
| PWC | https://paperswithcode.com/paper/tsa-inf-at-semeval-2017-task-4-an-ensemble-of |
| Repo | |
| Framework | |
Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares
| Title | Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares |
| Authors | Junqi Tang, Mohammad Golbabaee, Mike E. Davies |
| Abstract | We propose a randomized first order optimization algorithm Gradient Projection Iterative Sketch (GPIS) and an accelerated variant for efficiently solving large scale constrained Least Squares (LS). We provide the first theoretical convergence analysis for both algorithms. An efficient implementation using a tailored line-search scheme is also proposed. We demonstrate our methods’ computational efficiency compared to the classical accelerated gradient method, and the variance-reduced stochastic gradient methods through numerical experiments in various large synthetic/real data sets. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=578 |
| http://proceedings.mlr.press/v70/tang17a/tang17a.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-projection-iterative-sketch-for |
| Repo | |
| Framework | |
Online Prediction with Selfish Experts
| Title | Online Prediction with Selfish Experts |
| Authors | Tim Roughgarden, Okke Schrijvers |
| Abstract | We consider the problem of binary prediction with expert advice in settings where experts have agency and seek to maximize their credibility. This paper makes three main contributions. First, it defines a model to reason formally about settings with selfish experts, and demonstrates that ``incentive compatible’’ (IC) algorithms are closely related to the design of proper scoring rules. Second, we design IC algorithms with good performance guarantees for the absolute loss function. Third, we give a formal separation between the power of online prediction with selfish experts and online prediction with honest experts by proving lower bounds for both IC and non-IC algorithms. In particular, with selfish experts and the absolute loss function, there is no (randomized) algorithm for online prediction—IC or otherwise—with asymptotically vanishing regret. | |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6729-online-prediction-with-selfish-experts |
| http://papers.nips.cc/paper/6729-online-prediction-with-selfish-experts.pdf | |
| PWC | https://paperswithcode.com/paper/online-prediction-with-selfish-experts |
| Repo | |
| Framework | |
Learning to Generate Market Comments from Stock Prices
| Title | Learning to Generate Market Comments from Stock Prices |
| Authors | Soichiro Murakami, Akihiko Watanabe, Akira Miyazawa, Keiichi Goshima, Toshihiko Yanase, Hiroya Takamura, Yusuke Miyao |
| Abstract | This paper presents a novel encoder-decoder model for automatically generating market comments from stock prices. The model first encodes both short- and long-term series of stock prices so that it can mention short- and long-term changes in stock prices. In the decoding phase, our model can also generate a numerical value by selecting an appropriate arithmetic operation such as subtraction or rounding, and applying it to the input stock prices. Empirical experiments show that our best model generates market comments at the fluency and the informativeness approaching human-generated reference texts. |
| Tasks | Text Generation, Time Series |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1126/ |
| https://www.aclweb.org/anthology/P17-1126 | |
| PWC | https://paperswithcode.com/paper/learning-to-generate-market-comments-from |
| Repo | |
| Framework | |
Feature-Rich Networks for Knowledge Base Completion
| Title | Feature-Rich Networks for Knowledge Base Completion |
| Authors | Alex Komninos, ros, Man, Suresh har |
| Abstract | We propose jointly modelling Knowledge Bases and aligned text with Feature-Rich Networks. Our models perform Knowledge Base Completion by learning to represent and compose diverse feature types from partially aligned and noisy resources. We perform experiments on Freebase utilizing additional entity type information and syntactic textual relations. Our evaluation suggests that the proposed models can better incorporate side information than previously proposed combinations of bilinear models with convolutional neural networks, showing large improvements when scoring the plausibility of unobserved facts with associated textual mentions. |
| Tasks | Entity Linking, Knowledge Base Completion, Named Entity Recognition, Question Answering, Relation Extraction |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2051/ |
| https://www.aclweb.org/anthology/P17-2051 | |
| PWC | https://paperswithcode.com/paper/feature-rich-networks-for-knowledge-base |
| Repo | |
| Framework | |
Attention-based Dialog Embedding for Dialog Breakdown Detection
| Title | Attention-based Dialog Embedding for Dialog Breakdown Detection |
| Authors | Chanyoung Park, Kyungduk Kim, Songkuk Kim |
| Abstract | Dialog Breakdown Detection Challenge 3 of Dialog System Technology Challenge 6 |
| Tasks | |
| Published | 2017-12-10 |
| URL | http://workshop.colips.org/dstc6/papers.html |
| http://workshop.colips.org/dstc6/papers/track3_paper14_park.pdf | |
| PWC | https://paperswithcode.com/paper/attention-based-dialog-embedding-for-dialog |
| Repo | |
| Framework | |
Joint Dimensionality Reduction and Metric Learning: A Geometric Take
| Title | Joint Dimensionality Reduction and Metric Learning: A Geometric Take |
| Authors | Mehrtash Harandi, Mathieu Salzmann, Richard Hartley |
| Abstract | To be tractable and robust to data noise, existing metric learning algorithms commonly rely on PCA as a pre-processing step. How can we know, however, that PCA, or any other specific dimensionality reduction technique, is the method of choice for the problem at hand? The answer is simple: We cannot! To address this issue, in this paper, we develop a Riemannian framework to jointly learn a mapping performing dimensionality reduction and a metric in the induced space. Our experiments evidence that, while we directly work on high-dimensional features, our approach yields competitive runtimes with and higher accuracy than state-of-the-art metric learning algorithms. |
| Tasks | Dimensionality Reduction, Metric Learning |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=561 |
| http://proceedings.mlr.press/v70/harandi17a/harandi17a.pdf | |
| PWC | https://paperswithcode.com/paper/joint-dimensionality-reduction-and-metric |
| Repo | |
| Framework | |
Automatically Tagging Constructions of Causation and Their Slot-Fillers
| Title | Automatically Tagging Constructions of Causation and Their Slot-Fillers |
| Authors | Jesse Dunietz, Lori Levin, Jaime Carbonell |
| Abstract | This paper explores extending shallow semantic parsing beyond lexical-unit triggers, using causal relations as a test case. Semantic parsing becomes difficult in the face of the wide variety of linguistic realizations that causation can take on. We therefore base our approach on the concept of constructions from the linguistic paradigm known as Construction Grammar (CxG). In CxG, a construction is a form/function pairing that can rely on arbitrary linguistic and semantic features. Rather than codifying all aspects of each construction{'}s form, as some attempts to employ CxG in NLP have done, we propose methods that offload that problem to machine learning. We describe two supervised approaches for tagging causal constructions and their arguments. Both approaches combine automatically induced pattern-matching rules with statistical classifiers that learn the subtler parameters of the constructions. Our results show that these approaches are promising: they significantly outperform na{"\i}ve baselines for both construction recognition and cause and effect head matches. |
| Tasks | Semantic Parsing |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/Q17-1009/ |
| https://www.aclweb.org/anthology/Q17-1009 | |
| PWC | https://paperswithcode.com/paper/automatically-tagging-constructions-of |
| Repo | |
| Framework | |
ACTSA: Annotated Corpus for Telugu Sentiment Analysis
| Title | ACTSA: Annotated Corpus for Telugu Sentiment Analysis |
| Authors | S Mukku, eep Sricharan, Radhika Mamidi |
| Abstract | Sentiment analysis deals with the task of determining the polarity of a document or sentence and has received a lot of attention in recent years for the English language. With the rapid growth of social media these days, a lot of data is available in regional languages besides English. Telugu is one such regional language with abundant data available in social media, but it{'}s hard to find a labelled data of sentences for Telugu Sentiment Analysis. In this paper, we describe an effort to build a gold-standard annotated corpus of Telugu sentences to support Telugu Sentiment Analysis. The corpus, named ACTSA (Annotated Corpus for Telugu Sentiment Analysis) has a collection of Telugu sentences taken from different sources which were then pre-processed and manually annotated by native Telugu speakers using our annotation guidelines. In total, we have annotated 5457 sentences, which makes our corpus the largest resource currently available. The corpus and the annotation guidelines are made publicly available. |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5408/ |
| https://www.aclweb.org/anthology/W17-5408 | |
| PWC | https://paperswithcode.com/paper/actsa-annotated-corpus-for-telugu-sentiment |
| Repo | |
| Framework | |
An Algebra for Feature Extraction
| Title | An Algebra for Feature Extraction |
| Authors | Vivek Srikumar |
| Abstract | Though feature extraction is a necessary first step in statistical NLP, it is often seen as a mere preprocessing step. Yet, it can dominate computation time, both during training, and especially at deployment. In this paper, we formalize feature extraction from an algebraic perspective. Our formalization allows us to define a message passing algorithm that can restructure feature templates to be more computationally efficient. We show via experiments on text chunking and relation extraction that this restructuring does indeed speed up feature extraction in practice by reducing redundant computation. |
| Tasks | Chunking, Relation Extraction |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1173/ |
| https://www.aclweb.org/anthology/P17-1173 | |
| PWC | https://paperswithcode.com/paper/an-algebra-for-feature-extraction |
| Repo | |
| Framework | |
nQuery - A Natural Language Statement to SQL Query Generator
| Title | nQuery - A Natural Language Statement to SQL Query Generator |
| Authors | N Sukthankar, an, Sanket Maharnawar, Pranay Deshmukh, Yashodhara Haribhakta, Vibhavari Kamble |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3004/ |
| https://www.aclweb.org/anthology/P17-3004 | |
| PWC | https://paperswithcode.com/paper/nquery-a-natural-language-statement-to-sql |
| Repo | |
| Framework | |
