Paper Group NANR 217
A Multi-step Inertial Forward-Backward Splitting Method for Non-convex Optimization. Graphical Time Warping for Joint Alignment of Multiple Curves. OPT: Oslo–Potsdam–Teesside. Pipelining Rules, Rankers, and Classifier Ensembles for Shallow Discourse Parsing. Acquiring Opposition Relations among Italian Verb Senses using Crowdsourcing. TGermaCorp …
A Multi-step Inertial Forward-Backward Splitting Method for Non-convex Optimization
| Title | A Multi-step Inertial Forward-Backward Splitting Method for Non-convex Optimization |
| Authors | Jingwei Liang, Jalal Fadili, Gabriel Peyré |
| Abstract | In this paper, we propose a multi-step inertial Forward–Backward splitting algorithm for minimizing the sum of two non-necessarily convex functions, one of which is proper lower semi-continuous while the other is differentiable with a Lipschitz continuous gradient. We first prove global convergence of the scheme with the help of the Kurdyka–Łojasiewicz property. Then, when the non-smooth part is also partly smooth relative to a smooth submanifold, we establish finite identification of the latter and provide sharp local linear convergence analysis. The proposed method is illustrated on a few problems arising from statistics and machine learning. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6285-a-multi-step-inertial-forward-backward-splitting-method-for-non-convex-optimization |
| http://papers.nips.cc/paper/6285-a-multi-step-inertial-forward-backward-splitting-method-for-non-convex-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-step-inertial-forward-backward |
| Repo | |
| Framework | |
Graphical Time Warping for Joint Alignment of Multiple Curves
| Title | Graphical Time Warping for Joint Alignment of Multiple Curves |
| Authors | Yizhi Wang, David J. Miller, Kira Poskanzer, Yue Wang, Lin Tian, Guoqiang Yu |
| Abstract | Dynamic time warping (DTW) is a fundamental technique in time series analysis for comparing one curve to another using a flexible time-warping function. However, it was designed to compare a single pair of curves. In many applications, such as in metabolomics and image series analysis, alignment is simultaneously needed for multiple pairs. Because the underlying warping functions are often related, independent application of DTW to each pair is a sub-optimal solution. Yet, it is largely unknown how to efficiently conduct a joint alignment with all warping functions simultaneously considered, since any given warping function is constrained by the others and dynamic programming cannot be applied. In this paper, we show that the joint alignment problem can be transformed into a network flow problem and thus can be exactly and efficiently solved by the max flow algorithm, with a guarantee of global optimality. We name the proposed approach graphical time warping (GTW), emphasizing the graphical nature of the solution and that the dependency structure of the warping functions can be represented by a graph. Modifications of DTW, such as windowing and weighting, are readily derivable within GTW. We also discuss optimal tuning of parameters and hyperparameters in GTW. We illustrate the power of GTW using both synthetic data and a real case study of an astrocyte calcium movie. |
| Tasks | Time Series, Time Series Analysis |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6269-graphical-time-warping-for-joint-alignment-of-multiple-curves |
| http://papers.nips.cc/paper/6269-graphical-time-warping-for-joint-alignment-of-multiple-curves.pdf | |
| PWC | https://paperswithcode.com/paper/graphical-time-warping-for-joint-alignment-of |
| Repo | |
| Framework | |
OPT: Oslo–Potsdam–Teesside. Pipelining Rules, Rankers, and Classifier Ensembles for Shallow Discourse Parsing
| Title | OPT: Oslo–Potsdam–Teesside. Pipelining Rules, Rankers, and Classifier Ensembles for Shallow Discourse Parsing |
| Authors | Stephan Oepen, Jonathon Read, Tatjana Scheffler, Uladzimir Sidarenka, Manfred Stede, Erik Velldal, Lilja {\O}vrelid |
| Abstract | |
| Tasks | Machine Translation, Sentiment Analysis, Text Summarization |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-2002/ |
| https://www.aclweb.org/anthology/K16-2002 | |
| PWC | https://paperswithcode.com/paper/opt-osloapotsdamateesside-pipelining-rules |
| Repo | |
| Framework | |
Acquiring Opposition Relations among Italian Verb Senses using Crowdsourcing
| Title | Acquiring Opposition Relations among Italian Verb Senses using Crowdsourcing |
| Authors | Anna Feltracco, Simone Magnolini, Elisabetta Jezek, Bernardo Magnini |
| Abstract | We describe an experiment for the acquisition of opposition relations among Italian verb senses, based on a crowdsourcing methodology. The goal of the experiment is to discuss whether the types of opposition we distinguish (i.e. complementarity, antonymy, converseness and reversiveness) are actually perceived by the crowd. In particular, we collect data for Italian by using the crowdsourcing platform CrowdFlower. We ask annotators to judge the type of opposition existing among pairs of sentences -previously judged as opposite- that differ only for a verb: the verb in the first sentence is opposite of the verb in second sentence. Data corroborate the hypothesis that some opposition relations exclude each other, while others interact, being recognized as compatible by the contributors. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1339/ |
| https://www.aclweb.org/anthology/L16-1339 | |
| PWC | https://paperswithcode.com/paper/acquiring-opposition-relations-among-italian |
| Repo | |
| Framework | |
TGermaCorp – A (Digital) Humanities Resource for (Computational) Linguistics
| Title | TGermaCorp – A (Digital) Humanities Resource for (Computational) Linguistics |
| Authors | Andy Luecking, Armin Hoenen, Alex Mehler, er |
| Abstract | TGermaCorp is a German text corpus whose primary sources are collected from German literature texts which date from the sixteenth century to the present. The corpus is intended to represent its target language (German) in syntactic, lexical, stylistic and chronological diversity. For this purpose, it is hand-annotated on several linguistic layers, including POS, lemma, named entities, multiword expressions, clauses, sentences and paragraphs. In order to introduce TGermaCorp in comparison to more homogeneous corpora of contemporary everyday language, quantitative assessments of syntactic and lexical diversity are provided. In this respect, TGermaCorp contributes to establishing characterising features for resource descriptions, which is needed for keeping track of a meaningful comparison of the ever-growing number of natural language resources. The assessments confirm the special role of proper names, whose propagation in text may influence lexical and syntactic diversity measures in rather trivial ways. TGermaCorp will be made available via hucompute.org. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1677/ |
| https://www.aclweb.org/anthology/L16-1677 | |
| PWC | https://paperswithcode.com/paper/tgermacorp-a-digital-humanities-resource-for |
| Repo | |
| Framework | |
Anita: An Intelligent Text Adaptation Tool
| Title | Anita: An Intelligent Text Adaptation Tool |
| Authors | Gustavo Paetzold, Lucia Specia |
| Abstract | We introduce Anita: a flexible and intelligent Text Adaptation tool for web content that provides Text Simplification and Text Enhancement modules. Anita{'}s simplification module features a state-of-the-art system that adapts texts according to the needs of individual users, and its enhancement module allows the user to search for a word{'}s definitions, synonyms, translations, and visual cues through related images. These utilities are brought together in an easy-to-use interface of a freely available web browser extension. |
| Tasks | Lexical Simplification, Text Simplification |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2017/ |
| https://www.aclweb.org/anthology/C16-2017 | |
| PWC | https://paperswithcode.com/paper/anita-an-intelligent-text-adaptation-tool |
| Repo | |
| Framework | |
Assessing the Feasibility of an Automated Suggestion System for Communicating Critical Findings from Chest Radiology Reports to Referring Physicians
| Title | Assessing the Feasibility of an Automated Suggestion System for Communicating Critical Findings from Chest Radiology Reports to Referring Physicians |
| Authors | Brian E. Chapman, Danielle L. Mowery, Evan Narasimhan, Neel Patel, Wendy Chapman, Marta Heilbrun |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2924/ |
| https://www.aclweb.org/anthology/W16-2924 | |
| PWC | https://paperswithcode.com/paper/assessing-the-feasibility-of-an-automated |
| Repo | |
| Framework | |
Using Synthetically Collected Scripts for Story Generation
| Title | Using Synthetically Collected Scripts for Story Generation |
| Authors | Takashi Ogata, Tatsuya Arai, Jumpei Ono |
| Abstract | A script is a type of knowledge representation in artificial intelligence (AI). This paper presents two methods for synthetically using collected scripts for story generation. The first method recursively generates long sequences of events and the second creates script networks. Although related studies generally use one or more scripts for story generation, this research synthetically uses many scripts to flexibly generate a diverse narrative. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2053/ |
| https://www.aclweb.org/anthology/C16-2053 | |
| PWC | https://paperswithcode.com/paper/using-synthetically-collected-scripts-for |
| Repo | |
| Framework | |
Enabling text readability awareness during the micro planning phase of NLG applications
| Title | Enabling text readability awareness during the micro planning phase of NLG applications |
| Authors | Priscilla Moraes, Kathleen Mccoy, S Carberry, ra |
| Abstract | |
| Tasks | Language Modelling, Text Generation, Text Simplification |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-6621/ |
| https://www.aclweb.org/anthology/W16-6621 | |
| PWC | https://paperswithcode.com/paper/enabling-text-readability-awareness-during |
| Repo | |
| Framework | |
SURGE: Surface Regularized Geometry Estimation from a Single Image
| Title | SURGE: Surface Regularized Geometry Estimation from a Single Image |
| Authors | Peng Wang, Xiaohui Shen, Bryan Russell, Scott Cohen, Brian Price, Alan L. Yuille |
| Abstract | This paper introduces an approach to regularize 2.5D surface normal and depth predictions at each pixel given a single input image. The approach infers and reasons about the underlying 3D planar surfaces depicted in the image to snap predicted normals and depths to inferred planar surfaces, all while maintaining fine detail within objects. Our approach comprises two components: (i) a fourstream convolutional neural network (CNN) where depths, surface normals, and likelihoods of planar region and planar boundary are predicted at each pixel, followed by (ii) a dense conditional random field (DCRF) that integrates the four predictions such that the normals and depths are compatible with each other and regularized by the planar region and planar boundary information. The DCRF is formulated such that gradients can be passed to the surface normal and depth CNNs via backpropagation. In addition, we propose new planar wise metrics to evaluate geometry consistency within planar surfaces, which are more tightly related to dependent 3D editing applications. We show that our regularization yields a 30% relative improvement in planar consistency on the NYU v2 dataset. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6502-surge-surface-regularized-geometry-estimation-from-a-single-image |
| http://papers.nips.cc/paper/6502-surge-surface-regularized-geometry-estimation-from-a-single-image.pdf | |
| PWC | https://paperswithcode.com/paper/surge-surface-regularized-geometry-estimation |
| Repo | |
| Framework | |
pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection
| Title | pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection |
| Authors | Wan Wei, Xiao Zhang, Xuqin Liu, Wei Chen, Tengjiao Wang |
| Abstract | |
| Tasks | Sentence Classification, Stance Detection |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1062/ |
| https://www.aclweb.org/anthology/S16-1062 | |
| PWC | https://paperswithcode.com/paper/pkudblab-at-semeval-2016-task-6-a-specific |
| Repo | |
| Framework | |
Corpus Annotation within the French FrameNet: a Domain-by-domain Methodology
| Title | Corpus Annotation within the French FrameNet: a Domain-by-domain Methodology |
| Authors | Marianne Djemaa, C, Marie ito, Philippe Muller, Laure Vieu |
| Abstract | This paper reports on the development of a French FrameNet, within the ASFALDA project. While the first phase of the project focused on the development of a French set of frames and corresponding lexicon (Candito et al., 2014), this paper concentrates on the subsequent corpus annotation phase, which focused on four notional domains (commercial transactions, cognitive stances, causality and verbal communication). Given full coverage is not reachable for a relatively {``}new{''} FrameNet project, we advocate that focusing on specific notional domains allowed us to obtain full lexical coverage for the frames of these domains, while partially reflecting word sense ambiguities. Furthermore, as frames and roles were annotated on two French Treebanks (the French Treebank (Abeill{'e} and Barrier, 2004) and the Sequoia Treebank (Candito and Seddah, 2012), we were able to extract a syntactico-semantic lexicon from the annotated frames. In the resource{'}s current status, there are 98 frames, 662 frame evoking words, 872 senses, and about 13000 annotated frames, with their semantic roles assigned to portions of text. The French FrameNet is freely available at alpage.inria.fr/asfalda. | |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1601/ |
| https://www.aclweb.org/anthology/L16-1601 | |
| PWC | https://paperswithcode.com/paper/corpus-annotation-within-the-french-framenet |
| Repo | |
| Framework | |
Grapheme-to-Phoneme Models for (Almost) Any Language
| Title | Grapheme-to-Phoneme Models for (Almost) Any Language |
| Authors | Aliya Deri, Kevin Knight |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1038/ |
| https://www.aclweb.org/anthology/P16-1038 | |
| PWC | https://paperswithcode.com/paper/grapheme-to-phoneme-models-for-almost-any |
| Repo | |
| Framework | |
Evaluating Translation Quality and CLIR Performance of Query Sessions
| Title | Evaluating Translation Quality and CLIR Performance of Query Sessions |
| Authors | Xabier Saralegi, Eneko Agirre, I{~n}aki Alegria |
| Abstract | This paper presents the evaluation of the translation quality and Cross-Lingual Information Retrieval (CLIR) performance when using session information as the context of queries. The hypothesis is that previous queries provide context that helps to solve ambiguous translations in the current query. We tested several strategies on the TREC 2010 Session track dataset, which includes query reformulations grouped by generalization, specification, and drifting types. We study the Basque to English direction, evaluating both the translation quality and CLIR performance, with positive results in both cases. The results show that the quality of translation improved, reducing error rate by 12{%} (HTER) when using session information, which improved CLIR results 5{%} (nDCG). We also provide an analysis of the improvements across the three kinds of sessions: generalization, specification, and drifting. Translation quality improved in all three types (generalization, specification, and drifting), and CLIR improved for generalization and specification sessions, preserving the performance in drifting sessions. |
| Tasks | Information Retrieval |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1064/ |
| https://www.aclweb.org/anthology/L16-1064 | |
| PWC | https://paperswithcode.com/paper/evaluating-translation-quality-and-clir |
| Repo | |
| Framework | |
The JHU Machine Translation Systems for WMT 2016
| Title | The JHU Machine Translation Systems for WMT 2016 |
| Authors | Shuoyang Ding, Kevin Duh, Huda Khayrallah, Philipp Koehn, Matt Post |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2310/ |
| https://www.aclweb.org/anthology/W16-2310 | |
| PWC | https://paperswithcode.com/paper/the-jhu-machine-translation-systems-for-wmt-2 |
| Repo | |
| Framework | |
