Paper Group NAWR 11
Matrix Norm Estimation from a Few Entries. Fine-grained domain classification of text using TERMIUM Plus. Joint UD Parsing of Norwegian Bokm\aal and Nynorsk. Semi-Automated Resolution of Inconsistency for a Harmonized Multiword Expression and Dependency Parse Annotation. UW-FinSent at SemEval-2017 Task 5: Sentiment Analysis on Financial News Headli …
Matrix Norm Estimation from a Few Entries
| Title | Matrix Norm Estimation from a Few Entries |
| Authors | Ashish Khetan, Sewoong Oh |
| Abstract | Singular values of a data in a matrix form provide insights on the structure of the data, the effective dimensionality, and the choice of hyper-parameters on higher-level data analysis tools. However, in many practical applications such as collaborative filtering and network analysis, we only get a partial observation. Under such scenarios, we consider the fundamental problem of recovering various spectral properties of the underlying matrix from a sampling of its entries. We propose a framework of first estimating the Schatten $k$-norms of a matrix for several values of $k$, and using these as surrogates for estimating spectral properties of interest, such as the spectrum itself or the rank. This paper focuses on the technical challenges in accurately estimating the Schatten norms from a sampling of a matrix. We introduce a novel unbiased estimator based on counting small structures in a graph and provide guarantees that match its empirical performances. Our theoretical analysis shows that Schatten norms can be recovered accurately from strictly smaller number of samples compared to what is needed to recover the underlying low-rank matrix. Numerical experiments suggest that we significantly improve upon a competing approach of using matrix completion methods. |
| Tasks | Matrix Completion |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7221-matrix-norm-estimation-from-a-few-entries |
| http://papers.nips.cc/paper/7221-matrix-norm-estimation-from-a-few-entries.pdf | |
| PWC | https://paperswithcode.com/paper/matrix-norm-estimation-from-a-few-entries |
| Repo | https://github.com/khetan2/Schatten_norm_estimation |
| Framework | none |
Fine-grained domain classification of text using TERMIUM Plus
| Title | Fine-grained domain classification of text using TERMIUM Plus |
| Authors | Gabriel Bernier-Colborne, Caroline Barri{`e}re, Pierre Andr{'e} M{'e}nard |
| Abstract | |
| Tasks | Text Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7005/ |
| https://www.aclweb.org/anthology/W17-7005 | |
| PWC | https://paperswithcode.com/paper/fine-grained-domain-classification-of-text |
| Repo | https://github.com/crim-ca/LOTKS_2017 |
| Framework | none |
Joint UD Parsing of Norwegian Bokm\aal and Nynorsk
| Title | Joint UD Parsing of Norwegian Bokm\aal and Nynorsk |
| Authors | Erik Velldal, Lilja {\O}vrelid, Petter Hohle |
| Abstract | |
| Tasks | Language Identification, Machine Translation |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0201/ |
| https://www.aclweb.org/anthology/W17-0201 | |
| PWC | https://paperswithcode.com/paper/joint-ud-parsing-of-norwegian-bokmal-and |
| Repo | https://github.com/erikve/bm-nn-parsing |
| Framework | none |
Semi-Automated Resolution of Inconsistency for a Harmonized Multiword Expression and Dependency Parse Annotation
| Title | Semi-Automated Resolution of Inconsistency for a Harmonized Multiword Expression and Dependency Parse Annotation |
| Authors | King Chan, Julian Brooke, Timothy Baldwin |
| Abstract | This paper presents a methodology for identifying and resolving various kinds of inconsistency in the context of merging dependency and multiword expression (MWE) annotations, to generate a dependency treebank with comprehensive MWE annotations. Candidates for correction are identified using a variety of heuristics, including an entirely novel one which identifies violations of MWE constituency in the dependency tree, and resolved by arbitration with minimal human intervention. Using this technique, we identified and corrected several hundred errors across both parse and MWE annotations, representing changes to a significant percentage (well over 10{%}) of the MWE instances in the joint corpus. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1726/ |
| https://www.aclweb.org/anthology/W17-1726 | |
| PWC | https://paperswithcode.com/paper/semi-automated-resolution-of-inconsistency |
| Repo | https://github.com/eltimster/HAMSTER |
| Framework | none |
UW-FinSent at SemEval-2017 Task 5: Sentiment Analysis on Financial News Headlines using Training Dataset Augmentation
| Title | UW-FinSent at SemEval-2017 Task 5: Sentiment Analysis on Financial News Headlines using Training Dataset Augmentation |
| Authors | Vineet John, Olga Vechtomova |
| Abstract | This paper discusses the approach taken by the UWaterloo team to arrive at a solution for the Fine-Grained Sentiment Analysis problem posed by Task 5 of SemEval 2017. The paper describes the document vectorization and sentiment score prediction techniques used, as well as the design and implementation decisions taken while building the system for this task. The system uses text vectorization models, such as N-gram, TF-IDF and paragraph embeddings, coupled with regression model variants to predict the sentiment scores. Amongst the methods examined, unigrams and bigrams coupled with simple linear regression obtained the best baseline accuracy. The paper also explores data augmentation methods to supplement the training dataset. This system was designed for Subtask 2 (News Statements and Headlines). |
| Tasks | Data Augmentation, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2149/ |
| https://www.aclweb.org/anthology/S17-2149 | |
| PWC | https://paperswithcode.com/paper/uw-finsent-at-semeval-2017-task-5-sentiment |
| Repo | https://github.com/v1n337/semeval2017-task5 |
| Framework | tf |
Textual Inference: getting logic from humans
| Title | Textual Inference: getting logic from humans |
| Authors | Aikaterini-Lida Kalouli, Livy Real, Valeria de Paiva |
| Abstract | |
| Tasks | Natural Language Inference |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6915/ |
| https://www.aclweb.org/anthology/W17-6915 | |
| PWC | https://paperswithcode.com/paper/textual-inference-getting-logic-from-humans |
| Repo | https://github.com/kkalouli/SICK-processing |
| Framework | none |
Structured Learning for Temporal Relation Extraction from Clinical Records
| Title | Structured Learning for Temporal Relation Extraction from Clinical Records |
| Authors | Artuur Leeuwenberg, Marie-Francine Moens |
| Abstract | We propose a scalable structured learning model that jointly predicts temporal relations between events and temporal expressions (TLINKS), and the relation between these events and the document creation time (DCTR). We employ a structured perceptron, together with integer linear programming constraints for document-level inference during training and prediction to exploit relational properties of temporality, together with global learning of the relations at the document level. Moreover, this study gives insights in the results of integrating constraints for temporal relation extraction when using structured learning and prediction. Our best system outperforms the state-of-the art on both the CONTAINS TLINK task, and the DCTR task. |
| Tasks | Relation Extraction, Temporal Information Extraction |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1108/ |
| https://www.aclweb.org/anthology/E17-1108 | |
| PWC | https://paperswithcode.com/paper/structured-learning-for-temporal-relation |
| Repo | https://github.com/tuur/SPTempRels |
| Framework | none |
Inherent fuzzy entropy for the improvement of EEG complexity evaluation
| Title | Inherent fuzzy entropy for the improvement of EEG complexity evaluation |
| Authors | Zehong Cao, Chin-Teng Lin |
| Abstract | In recent years, the concept of entropy has been widely used to measure the dynamic complexity of signals. Since the state of complexity of human beings is significantly affected by their health state, developing accurate complexity evaluation algorithms is a crucial and urgent area of study. This paper proposes using inherent fuzzy entropy (Inherent FuzzyEn) and its multiscale version, which employs empirical mode decomposition and fuzzy membership function (exponential function) to address the dynamic complexity in electroencephalogram (EEG) data. In the literature, the reliability of entropy-based complexity evaluations has been limited by superimposed trends in signals and a lack of multiple time scales. Our proposed method represents the first attempt to use the Inherent FuzzyEn algorithm to increase the reliability of complexity evaluation in realistic EEG applications. We recorded the EEG signals of several subjects under resting condition, and the EEG complexity was evaluated using approximate entropy, sample entropy, FuzzyEn, and Inherent FuzzyEn, respectively. The results indicate that Inherent FuzzyEn is superior to other competing models regardless of the use of fuzzy or nonfuzzy structures, and has the most stable complexity and smallest root mean square deviation. |
| Tasks | EEG |
| Published | 2017-02-13 |
| URL | https://ieeexplore.ieee.org/abstract/document/7851069 |
| https://ieeexplore.ieee.org/abstract/document/7851069 | |
| PWC | https://paperswithcode.com/paper/inherent-fuzzy-entropy-for-the-improvement-of |
| Repo | https://github.com/czh513/EEG-Inherent-Fuzzy-Entropy |
| Framework | none |
GRaSP: Grounded Representation and Source Perspective
| Title | GRaSP: Grounded Representation and Source Perspective |
| Authors | Antske Fokkens, Piek Vossen, Marco Rospocher, Rinke Hoekstra, Willem Robert van Hage |
| Abstract | When people or organizations provide information, they make choices regarding what information they include and how they present it. The combination of these two aspects (the content and stance provided by the source) represents a perspective. Investigating differences in perspective can provide various useful insights in the reliability of information, the way perspectives change over time, shared beliefs among groups of a similar social or political background and contrasts between other groups, etc. This paper introduces GRaSP, a generic framework for modeling perspectives and their sources. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7803/ |
| https://doi.org/10.26615/978-954-452-040-3_003 | |
| PWC | https://paperswithcode.com/paper/grasp-grounded-representation-and-source |
| Repo | https://github.com/cltl/GRaSP |
| Framework | none |
Identifying Cognate Sets Across Dictionaries of Related Languages
| Title | Identifying Cognate Sets Across Dictionaries of Related Languages |
| Authors | Adam St Arnaud, David Beck, Grzegorz Kondrak |
| Abstract | We present a system for identifying cognate sets across dictionaries of related languages. The likelihood of a cognate relationship is calculated on the basis of a rich set of features that capture both phonetic and semantic similarity, as well as the presence of regular sound correspondences. The similarity scores are used to cluster words from different languages that may originate from a common proto-word. When tested on the Algonquian language family, our system detects 63{%} of cognate sets while maintaining cluster purity of 70{%}. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1267/ |
| https://www.aclweb.org/anthology/D17-1267 | |
| PWC | https://paperswithcode.com/paper/identifying-cognate-sets-across-dictionaries |
| Repo | https://github.com/ajstarna/SemaPhoR |
| Framework | none |
MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting
| Title | MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting |
| Authors | Tomoyuki Kajiwara, Mamoru Komachi, Daichi Mochihashi |
| Abstract | We present a pointwise mutual information (PMI)-based approach to formalize paraphrasability and propose a variant of PMI, called MIPA, for the paraphrase acquisition. Our paraphrase acquisition method first acquires lexical paraphrase pairs by bilingual pivoting and then reranks them by PMI and distributional similarity. The complementary nature of information from bilingual corpora and from monolingual corpora makes the proposed method robust. Experimental results show that the proposed method substantially outperforms bilingual pivoting and distributional similarity themselves in terms of metrics such as MRR, MAP, coverage, and Spearman{'}s correlation. |
| Tasks | Learning Word Embeddings, Semantic Textual Similarity, Word Alignment, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1009/ |
| https://www.aclweb.org/anthology/I17-1009 | |
| PWC | https://paperswithcode.com/paper/mipa-mutual-information-based-paraphrase |
| Repo | https://github.com/tmu-nlp/pmi-ppdb |
| Framework | none |
Attentional Correlation Filter Network for Adaptive Visual Tracking
| Title | Attentional Correlation Filter Network for Adaptive Visual Tracking |
| Authors | Jongwon Choi, Hyung Jin Chang, Sangdoo Yun, Tobias Fischer, Yiannis Demiris, Jin Young Choi |
| Abstract | We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency. The subset of filters is adaptively selected by a deep attentional network according to the dynamic properties of the tracking target. Our contributions are manifold, and are summarised as follows: (i) Introducing the Attentional Correlation Filter Network which allows adaptive tracking of dynamic targets. (ii) Utilising an attentional network which shifts the attention to the best candidate modules, as well as predicting the estimated accuracy of currently inactive modules. (iii) Enlarging the variety of correlation filters which cover target drift, blurriness, occlusion, scale changes, and flexible aspect ratio. (iv) Validating the robustness and efficiency of the attentional mechanism for visual tracking through a number of experiments. Our method achieves similar performance to non real-time trackers, and state-of-the-art performance amongst real-time trackers. |
| Tasks | Visual Object Tracking, Visual Tracking |
| Published | 2017-07-21 |
| URL | https://sites.google.com/site/jwchoivision/home/acfn-1 |
| https://drive.google.com/open?id=0B0ZkG8zaRQoLUHdlTGNtUWFjd1E | |
| PWC | https://paperswithcode.com/paper/attentional-correlation-filter-network-for-1 |
| Repo | https://github.com/jongwon20000/ACFN |
| Framework | tf |
GraWiTas: a Grammar-based Wikipedia Talk Page Parser
| Title | GraWiTas: a Grammar-based Wikipedia Talk Page Parser |
| Authors | Benjamin Cabrera, Laura Steinert, Bj{"o}rn Ross |
| Abstract | Wikipedia offers researchers unique insights into the collaboration and communication patterns of a large self-regulating community of editors. The main medium of direct communication between editors of an article is the article{'}s talk page. However, a talk page file is unstructured and therefore difficult to analyse automatically. A few parsers exist that enable its transformation into a structured data format. However, they are rarely open source, support only a limited subset of the talk page syntax {–} resulting in the loss of content {–} and usually support only one export format. Together with this article we offer a very fast, lightweight, open source parser with support for various output formats. In a preliminary evaluation it achieved a high accuracy. The parser uses a grammar-based approach {–} offering a transparent implementation and easy extensibility. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3006/ |
| https://www.aclweb.org/anthology/E17-3006 | |
| PWC | https://paperswithcode.com/paper/grawitas-a-grammar-based-wikipedia-talk-page |
| Repo | https://github.com/ace7k3/grawitas |
| Framework | none |
Bounded-Depth High-Coverage Search Space for Noncrossing Parses
| Title | Bounded-Depth High-Coverage Search Space for Noncrossing Parses |
| Authors | Anssi Yli-Jyr{"a} |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4004/ |
| https://www.aclweb.org/anthology/W17-4004 | |
| PWC | https://paperswithcode.com/paper/bounded-depth-high-coverage-search-space-for |
| Repo | https://github.com/amikael/depconv |
| Framework | none |
Low-Dimensionality Calibration Through Local Anisotropic Scaling for Robust Hand Model Personalization
| Title | Low-Dimensionality Calibration Through Local Anisotropic Scaling for Robust Hand Model Personalization |
| Authors | Edoardo Remelli, Anastasia Tkach, Andrea Tagliasacchi, Mark Pauly |
| Abstract | We present a robust algorithm for personalizing a sphere-mesh tracking model to a user from a collection of depth measurements. Our core contribution is to demonstrate how simple geometric reasoning can be exploited to build a shape-space, and how its performance is comparable to shape-spaces constructed from datasets of carefully calibrated models. We achieve this goal by first re-parameterizing the geometry of the tracking template, and introducing a multi-stage calibration optimization. Our novel parameterization decouples the degrees of freedom for pose and shape, resulting in improved convergence properties. Our analytically differentiable multi-stage calibration pipeline optimizes for the model in the natural low-dimensional space of local anisotropic scalings, leading to an effective solution that can be easily embedded in other tracking/calibration algorithms. Compared to existing sphere-mesh calibration algorithms, quantitative experiments assess our algorithm possesses a larger convergence basin, and our personalized models allows to perform motion tracking with superior accuracy. Code and data are available at http://github.com/edoRemelli/hadjust |
| Tasks | Calibration |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Remelli_Low-Dimensionality_Calibration_Through_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Remelli_Low-Dimensionality_Calibration_Through_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/low-dimensionality-calibration-through-local |
| Repo | https://github.com/edoRemelli/hadjust |
| Framework | none |
