s2_papers.jsonl

{"authors": [{"ids": ["1876168"], "name": "Alex Lascarides"}, {"ids": ["4322924"], "name": "Nicholas Asher"}, {"ids": ["3263707"], "name": "Jon Oberlander"}], "id": "5cdac93dc6d1e08e76d647ff9b50fce62d714190", "inCitations": ["19a32ef669daf7f5478e992c66c19086c09aa000", "f6699c175ad7034fa14148db5f8461857d94c3bd", "247677ab9824d788fd858e47e1f9e060564b92d9", "395d4f33b5830a901926a97e0d0ece5409532a8a", "1b52fa80d8a4a2b10fbe05ab7e01a82994a6273c", "81cc595fdf07c4f560a15d38da52b5cf7f3acba2", "3446a23e07529bdf963dd5a66468ecc770543e6e", "0806f979fc16cf83c762287e34f1c8e2d071d62a", "5dbe5fc6443a6a8a015998f86a56c1f5247f0f52", "c11ba1886b5c5f6d2a009a79067291f26bf0266d", "763656da350127c9b0afbf758b930696a52544f3", "b782c25d75fee4e7d6143994f67e312346fa6dab", "d1ada5962b65b3cc0550cc1a91b40b063e28adbb", "3620a9e4c8adcfdbea240defaacfc9ff11d67360", "796f6a0d8aeaeb6861a134caf218f9e3af2d3746", "49c5b0932d86abba11fc766e312269af4292e951", "284932427c34581c8fc30fc1451924585467343e", "c68b64c6451056e56710b16572640fcac917a0af", "83dc3d673da9e2a488a09452b3b2d41e0d558dd6", "392b5a383dc36c31ea6742dec768e2cc32d126f1", "2d47f6500f58348d4cf16fc84a72906aeee4a7cd", "18c110ddf74437f3873127fc41b9cabb096c93aa", "38f07dfa404d8860c93d2565c016510f533e57cd", "41b0548598d773fabbf3a4266decad35a76c4e49", "50d30ce167918e0edde204eaf97c4da95abe012e", "03a41f390e3be41f7c731d6f779e4cc340bf0c02", "40b054547af5a57fb4f79cc07f42088aecbd2fde", "4b820ae62ec22a0c9ceaaf639a17e177f8469e64", "25755edbd02fb32cd3d6f9c1f6c65abfb993a6fb", "89423ef1fe2f5d0c6286da82d821b2b1c09f14ff", "af0adb031969e8622af109265da5c0cfbbd5f09b", "872c70ba2efbf635520b9de672850159666d4964", "43f2a2220b1494ca230e2fad11e088640411837e", "1de92adf098fbacd4877fb4e1a27922e141250f5"], "journalName": "", "journalPages": "1-8", "journalVolume": "", "keyPhrases": ["Utterance", "Syntactic Level", "Clause", "Contextual Constraint", "Formalisation"], "outCitations": ["e564391324ede7c9771e78b6d8c23bee5afff559", "7dfb1c788fb7dad6aefabe30fd9bde6cfc277d11", "59485516f2e600f2bfe274a5e67a3b5177626bb1", "8c2866c2ec846d0f77d327397a2249afb5f2c80b", "b3e158315d15b531eeab01a988c408a971fb8358", "d1f6f992ecf2948e8f944926299cd21858c39c52", "afb24abe01532069fd3ef8098627d9bdd8bf267a"], "paperAbstract": "We investigate various contextual effects on text interpretation, and account for them by providing contextual constraints in a logical theory of text interpretation. On the basis of the way these constraints interact with the other knowledge sources, we draw some general conclusions about the role of domain-specific information, top-down and bottom-up discourse information flow, and the usefulness of formalisation in discourse theory. Introduct ion: T i m e S w i t c h i n g and A m e l i o r a t i o n Two essential parts of discourse interpretation involve (i) determining the rhetorical role each sentence plays in the text; and (ii) determining the temporal relations between the events described. Preceding discourse context has significant effects on both of these aspects of interpretation. For example, text (1) in vacuo may be a non-iconic explanation; the pushing caused the falling and so explains why Max fell. But the same pair of sentences may receive an iconic, narrative interpretat ion in the discourse context provided by (2): John takes advantage of Max's vulnerability while he is lying the ground, to push him over the edge of the cliff. (1) Max fell. John pushed him. (2) John and Max came to the cliff's edge. John applied a sharp blow to the back of Max's neck. Max fell. John pushed him. Max rolled over the edge of the cliff. a The support of the Science and Engineering Research Council through project number GR/G22077 is gratefully acknowledged. HCRC is supported by the Economic and SociM Research Council. We thank two anonymous reviewers for their helpful comments. Moreover, the text in (3) in vacuo is incoherent, but becomes coherent in (4)'s context.", "pdfUrls": ["http://aclweb.org/anthology/P92-1001", "http://acl.ldc.upenn.edu/P/P92/P92-1001.pdf", "http://anthology.aclweb.org/P/P92/P92-1001.pdf", "http://ucrel.lancs.ac.uk/acl/P/P92/P92-1001.pdf", "http://wing.comp.nus.edu.sg/~antho/P/P92/P92-1001.pdf", "http://aclweb.org/anthology//P/P92/P92-1001.pdf", "http://www.aclweb.org/anthology/P/P92/P92-1001.pdf", "http://aclweb.org/anthology/P/P92/P92-1001.pdf", "http://www.aclweb.org/anthology/P92-1001"], "s2Url": "http://semanticscholar.org/paper/5cdac93dc6d1e08e76d647ff9b50fce62d714190", "title": "Interferring Discourse Relations in Context", "venue": "ACL", "year": 1992}
{"authors": [{"ids": ["2515197"], "name": "Scott Bennett"}, {"ids": ["1802807"], "name": "Gerald DeJong"}], "id": "331d40340b217e10568dc21a32c7520f370f4ee5", "inCitations": [], "journalName": "", "journalPages": "2065-2066", "journalVolume": "", "keyPhrases": ["Planner", "Grasper", "Grasp", "Internal Representation", "Sequence Of Actions"], "outCitations": ["754977cd5b7deb4b7384bc6fda8e640392b28c65", "9d36c8e41742cf115137baaabd4580b9c02d9fd2"], "paperAbstract": "Execut ion of classical plans in the real world can be problematic. Small discrepancies between a planner's internal representations and the real world are unavoidable. These can conspire to cause real-world fai lure even though the planner is sound and, therefore, \"proves\" that a sequence of actions achieves the desired goal. The diff iculty, of course, is that the planner's proof is contingent on its internal world model precisely captur ing all relevant features of the external real wor ld . This is seldom the case, par t icu lar ly in robotics where uncertainties abound. Small but unavoidable sensor errors preclude accurate knowledge of the state of the world Worse, the planner's own characterization of the effects of its actions are themselves only approximations. Realworld execution of a sequence of actions can introduce and quickly magnify inconsistencies w i th the internal mi cro wor ld.", "pdfUrls": ["http://www.ijcai.org/Proceedings/95-2/Papers/141.pdf", "http://ijcai.org/Proceedings/95-2/Papers/141.pdf", "http://dli.iiit.ac.in/ijcai/IJCAI-95-VOL2/PDF/141.pdf", "http://ijcai.org/Past%20Proceedings/IJCAI-95-VOL2/PDF/141.pdf"], "s2Url": "http://semanticscholar.org/paper/331d40340b217e10568dc21a32c7520f370f4ee5", "title": "GRASPER: A Permissive Planning Robot", "venue": "AI", "year": 1995}
{"authors": [{"ids": ["2006247"], "name": "Evdokia Nikolova"}, {"ids": ["1743286"], "name": "David R. Karger"}], "id": "478dac375b3dc60be161e2fb5091ac44a247a48a", "inCitations": ["c597dd2bbb4b336d2bd3410aea6bc67e401033ad", "10ec99ae8062423c313c67bde64289a79cd432b1", "440f775722a7fbe636e197d40bc5dff280fa03a5", "a42faafdf97b4fbfc6a81ec3b1ea39feb9bc9b05", "b401c1f29b302e303b58784092c904865d96d826", "f3a3777c145d6ff5351e783799d0325f0dc70633", "62acd048037f2ad24c60c3af1616ca0c31b32832", "467f2ed69a5cba0d6386418a5b5e9eec514c2991", "09d5a388d90b79cb2238ebe327a27b9655ed9764", "20cdf029c8f5656d2cf0640d2aeaef283206cd73", "4c31851cbbcbba60bfe4c380b1e1034d73a464c0", "4ab127ab180c9b3672db323812e9b53c4dc5afab", "35db765c034f9f5de326f18d03c3401f74002ec5", "24015dfb00f795dc9ebed3496de216a595b049af", "01280438e35228ec2d61daa436ce0e013d4179dd", "5a73acd05c22cae585de433b376d5290a7e737c7", "08cfab93b9070fdff1ac9fae25044894b659c38b", "96ef41d7919fb778a0e413bbc73abffd29c2bacf", "179c8bde910f82d142a103a216d7427f12ca52e3", "fa1d00c70f727d6913d47651ce54d595d43da335", "9f1804c087fa9fe1fe644838e26f61b5f16afae4", "5e52f9c0a1420c316a043883fc2f18df2796d143", "f22d147aca36544974bcb0f7c05c48371e339dfc", "390f363e8e8215496fd1a22306b4425607ec2081", "028c13092d6dfddfd837e4a18946674d180fd6de", "0449613bcf19690c8f9f2e257fdea5bfe280912f", "5b0d6fbdb6578ef85779e7351aef921d83d7e22a", "bc79d4a37993f6c5e97100d8274cd95f4803e3f6", "2371f38fbbdf7cf75606523ef1e7bb1b9427f833"], "journalName": "", "journalPages": "969-974", "journalVolume": "", "keyPhrases": ["CTP", "Travel", "Canadian Traveller", "Transportation", "Disjoint Path"], "outCitations": ["27148896bc12f75584f99c775c8b69f909e25467", "e447b1a2471f0205a912d1a82889a133f7a6b9fb", "224b014a307c6a189464b6bcffb8ab42d6b227a6", "5f0d49f1cfc4dfdc174e5f0c2a74ea073b428b01", "85cdf3aa5b02f1416e5bdfb4db4687ceed611931", "ff187225ff569e01e751ebf004076350d4456a51", "292a10ebe3e2825257ff5617be19d327b6c8a7ef", "e4032760927e8394fb12a5c0276a46b23ed2b9cc", "f049db122fe9ff54b0b5269e169e1a878150bb12", "3c9605965b386a0a70bb0c40123340c0e0a666a2", "5cd8ce0103696e376f15281cb245a273b337ff43"], "paperAbstract": "The Canadian Traveller problem is a stochastic shortest paths problem in which one learns the cost of an edge only when arriving at one of its endpoints. The goal is to find an optimal policy that minimizes the expected cost of travel. The problem is known to be #P-hard. Since there has been no significant progress on approximation algorithms for several decades, we have chosen to seek out special cases for which exact solutions exist, in the hope of demonstrating techniques that could lead to further progress. Applying a mix of techniques from algorithm analysis and the theory of Markov Decision Processes, we provide efficient exact algorithms for directed acyclic graphs and (undirected) graphs of disjoint paths from source to destination with random two-valued edge costs. We also give worst-case performance analysis and experimental data for two natural heuristics.", "pdfUrls": ["http://people.csail.mit.edu/enikolova/papers/enikolova-aaai08-6pages.pdf", "http://theory.csail.mit.edu/~enikolova/papers/enikolova-aaai08-6pages.pdf", "http://users.ece.utexas.edu/~nikolova/papers/enikolova-aaai08-6pages.pdf", "http://www.aaai.org/Library/AAAI/2008/aaai08-154.php", "http://people.csail.mit.edu/~enikolova/papers/enikolova-aaai08-6pages.pdf", "http://www.aaai.org/Papers/AAAI/2008/AAAI08-154.pdf", "http://faculty.cse.tamu.edu/nikolova/papers/enikolova-aaai08-6pages.pdf"], "s2Url": "http://semanticscholar.org/paper/478dac375b3dc60be161e2fb5091ac44a247a48a", "title": "Route Planning under Uncertainty: The Canadian Traveller Problem", "venue": "AI", "year": 2008}
{"authors": [{"ids": ["2522647"], "name": "Jiaxin Shi"}, {"ids": ["1701941"], "name": "Jun Zhu"}], "id": "4bae271e71d00148e494facb31a6fcb3b8f2aa41", "inCitations": ["4db1833a964829540bd69b8278c24381d778be25", "2e17c3b883f0cdfe72e4877cdd88d3cc98e9836c"], "journalName": "CoRR", "journalPages": "", "journalVolume": "abs/1512.01173", "keyPhrases": ["Embedding", "Dialog", "Knowledge Base", "Conversation", "Superior"], "outCitations": ["3219fbcbe0f84e371b3266beb7678db567bd7c5a", "9aa88a8a354f1d322e242376d27d0474e50252f8", "057ac29c84084a576da56247bdfd63bf17b5a891", "68a33a3afac65eb6e0fb3726c1f9c8b727f32a42", "1976c9eeccc7115d18a04f1e7fb5145db6b96002", "50d53cc562225549457cbc782546bfbe1ac6f0cf", "31868290adf1c000c611dfc966b514d5a34e8d23", "04b52c8230c3f9f4f4032b06458069d81c8f07b2", "154728875d4668065ca6ba9fa2f5d2a1bcfc4a6e", "a77cf5d0d0b8fa64890e66152c5f7f6fe75c9b7c", "498ca0a1f8c980586408addf7ab2919ecdb7dd3d", "1a44c5c91c86280e6f68efa581e8e3a3d9d85577", "0c1cf4a619f90b9bbb5838f4a1f02e37c3e69388", "bcae9da4151d4accf3d90ef8bab883fbec35cb85", "762b63d2eb86f8fd0de98a08561b77527ae8f165", "2452d5ce9dc467f44676893a99d14ee9f8a0da84", "8f5450037cba1ba1f5c2f73fa4ffa66558eae5bd", "313b7386bd24bfb1752172a51eea1d55cc80ec8e", "9952d4d5717afd4a27157ed8b98b0ee3dcb70d6c", "8ecc044d920df247fbd455b752fd7cc0f7363ad7"], "paperAbstract": "We present a new perspective on neural knowledge base (KB) embeddings, from which we build a framework that can model symbolic knowledge in the KB together with its learning process. We show that this framework well regularizes previous neural KB embedding model for superior performance in reasoning tasks, while having the capabilities of dealing with unseen entities, that is, to learn their embeddings from natural language descriptions, which is very like human\u2019s behavior of learning semantic concepts.", "pdfUrls": ["http://arxiv.org/abs/1512.01173", "http://ceur-ws.org/Vol-1583/CoCoNIPS_2015_paper_11.pdf", "http://arxiv.org/pdf/1512.01173v1.pdf", "https://arxiv.org/pdf/1512.01173v1.pdf"], "s2Url": "http://semanticscholar.org/paper/4bae271e71d00148e494facb31a6fcb3b8f2aa41", "title": "Building Memory with Concept Learning Capabilities from Large-Scale Knowledge Bases", "venue": "ML", "year": 2015}
{"authors": [{"ids": ["1680574"], "name": "Matthias W. Seeger"}, {"ids": ["2697113"], "name": "David Salinas"}, {"ids": ["5435711"], "name": "Valentin Flunkert"}], "id": "59402496779a6d92afd70a551b64be4356e1a781", "inCitations": ["719e6b3393476b3783c1b9deb55196b1b99bdce4", "0638854d36a96a3fffb6db489a130e352d1cbe40", "7a971b8e5a7bc267ee0617e9747f24b85bf5659f"], "journalName": "", "journalPages": "4646-4654", "journalVolume": "", "keyPhrases": [], "outCitations": ["79b801d78cc71ca6eb43296841c2ee3695ae15e1", "8ea2c08ec9267eebd4e71883bf5f32b848b1678d", "d39483130af04c614bf59a07106129849b87b5bf", "07e4c380bc31d174d3af0d7ea813d3be895e6bbc", "584812bdcfdced80590097fd0d5ed264781151ac", "64cf19058c2de244a5125fd611ec3768693411fd", "00cf63a7926a826f7cf73c1d5edb117f98d70c2c", "0558c94a094158ecd64f0d5014d3d9668054fb97", "37075cfb18376ba24b2abad519f31ca0eba0df91", "0c4867f11c9758014d591381d8b397a1d38b04a7", "143e8726d5ca25af0f6495c39e502213f5802c1c"], "paperAbstract": "We present a scalable and robust Bayesian method for demand forecasting in the context of a large e-commerce platform, paying special attention to intermittent and bursty target statistics. Inference is approximated by the Newton-Raphson algorithm, reduced to linear-time Kalman smoothing, which allows us to operate on several orders of magnitude larger problems than previous related work. In a study on large real-world sales datasets, our method outperforms competing approaches on fast and medium moving items.", "pdfUrls": ["http://papers.nips.cc/paper/6313-bayesian-intermittent-demand-forecasting-for-large-inventories.pdf", "http://papers.nips.cc/paper/6313-bayesian-intermittent-demand-forecasting-for-large-inventories"], "s2Url": "http://semanticscholar.org/paper/59402496779a6d92afd70a551b64be4356e1a781", "title": "Bayesian Intermittent Demand Forecasting for Large Inventories", "venue": "ML", "year": 2016}
{"authors": [{"ids": ["3124342"], "name": "Dan Garber"}, {"ids": ["1678313"], "name": "Elad Hazan"}, {"ids": ["1901958"], "name": "Tengyu Ma"}], "id": "165bfb993552823c3a7d3a7418bd2d5e4800d4c7", "inCitations": ["de72591c02cc962d6cd4fa4040472efa2c1be634", "8f9e4d719d9f61dedbc96172e85b050ec403a197", "0f5a301935de5efae10b9c1dfb3ebe73849d5691", "063e95e1657feaf4c421d5b01ae8ae7c1e80494f", "8d8c9ba9965ef92ce398914dc007bba6171ebac4", "a92d4abe1f42a0ffc30458a486ed578f9ce27324", "233a1636dabbf84629d015248a1c98ed150a947b", "398b2200bd61551a2939226746a3873bfe38851a", "509e6e3f7e2d67dcaf5043b96225811071eac072", "3acbbc05ec8fee9339ce87c91e221b3ac1c29265", "751d8c740ea2dc1587a26ac492ccd0bbbff13bc1", "5794ff142b8997e2f97a4acae1e3f1e6bb63d00e", "551f949e57a9e25cb3d1aafede08d8db04e28c57", "325faac443e5e429802ed6264f1aa926b8560305", "1daa93f5b2469748d632919cf7d97c0d673148e5"], "journalName": "", "journalPages": "560-568", "journalVolume": "", "keyPhrases": ["Regret", "SVD", "Eigenvector", "Online Learning", "Numerical Linear Algebra"], "outCitations": ["9b4d7c76938c4f69eff30a35d5d1c56b07c369f0", "0e239a65896d3dad2de2191de1f7c32b0dbacec8", "29bf872ec9ff3ada2c4ced3449fb963cf03c00d1", "e21e69968f6b4eb29ce49156ababa35fd6c53226", "0fdda242c8bc15390cf6ff7669cb3c274e522b9f", "35a36ecd3a88e20fdcd4ff8a2513f4bfb374caa5", "18460046c2697c932530ece0d986094a5544df99", "015130f5bc3643236f48f47255fb6b4d87c284c4", "11aacb86760d45bbbba4c09354ee2d3431526ea7", "3ad1f4c36b5a48dd0d7cbe0fa2de2d0177692895", "630f710aece5e64563de7fb27ff8a7c6a20384d1", "41d3fefdb1843abc74834226256a25ad0eea697a", "b7919ff2179bea8dbe9241332fbb4137e2661825", "2ea62ecc37684cdcb39b6dad32fdf1387c175f2f", "5cae1bfa625063fe701a9b678cc04c389ccad016", "11573021dd74a26163dec542731d27102550c8f2", "1fbfa8b590ce4679367d73cb8e4f2d169ae5c624"], "paperAbstract": "Computing the leading eigenvector of a symmetric real matrix is a fundamental primitive of numerical linear algebra with numerous applications. We consider a natural online extension of the leading eigenvector problem: a sequence of matrices is presented and the goal is to predict for each matrix a unit vector, with the overall goal of competing with the leading eigenvector of the cumulative matrix. Existing regretminimization algorithms for this problem either require to compute an eigen decompostion every iteration, or suffer from a large dependency of the regret bound on the dimension. In both cases the algorithms are not practical for large scale applications.", "pdfUrls": ["http://www.jmlr.org/proceedings/papers/v37/garberb15-supp.pdf", "http://jmlr.csail.mit.edu/proceedings/papers/v37/garberb15.pdf", "http://machinelearning.wustl.edu/mlpapers/paper_files/icml2015_garberb15.pdf", "http://jmlr.org/proceedings/papers/v37/garberb15.pdf", "http://jmlr.org/proceedings/papers/v37/garberb15-supp.pdf", "http://jmlr.csail.mit.edu/proceedings/papers/v37/garberb15-supp.pdf", "http://jmlr.org/proceedings/papers/v37/garberb15.html", "http://www.jmlr.org/proceedings/papers/v37/garberb15.pdf"], "s2Url": "http://semanticscholar.org/paper/165bfb993552823c3a7d3a7418bd2d5e4800d4c7", "title": "Online Learning of Eigenvectors", "venue": "ML", "year": 2015}
{"authors": [{"ids": ["26367065"], "name": "Michael Roth"}, {"ids": ["1747654"], "name": "Anette Frank"}], "id": "1b81fd32777295dec1fcf2cbcb250e401cc7f353", "inCitations": ["00e6e722afcc64ed9bf0bd6a3b7b96440149846a", "618b5e78062cdeb02da4eb2262ceca5df568c1a4", "56f327daa0bf8465bc3528a752d916fef1ce10b3", "00aa92cf221355a608df2074c5be0ea07056f309", "03098b52e3e60e137c75fcc464346bad9fe25dd4", "0cba030613ef1b25104cbdacb78abfece2d85db8", "6c8a83b4a69c8eb44c872902ea87efa48ff644d9", "0de24a44719e33982db28643a53ca6780579a699"], "journalName": "", "journalPages": "171-182", "journalVolume": "", "keyPhrases": ["Discourse", "Predicate Pairs", "Coherence", "Similarity Measure", "Comparable Text"], "outCitations": ["27e5bd13d581ef682b96038dce4c18f260122352", "167abf2c9eda9ce21907fcc188d2e41da37d9f0b", "4152ed7f2a1fa8a571c2b317e545830849c3f6f3", "51cfde9bbc25a4cff1d5666815674c83886d933e", "02ec888235367184342b9d7295ce99b3da6aea10", "13d7cbe9035abbb0f243a5e63e19d9c01bcf69d8", "2de866180a5329fd02c7f0184e0aa6f72d5fda55", "2c0dd733157e4a824dfe2ce2ce9bd7b29fc8a731", "d65dd6aa2af060497a0daef47de576477772b67e", "528fa9bb03644ba752fb9491be49b9dd1bce1d52", "2ae6014a451801671d41b6171f86e657d8b1fbaf", "0e2795b1329b25ba3709584b96fd5cb4c96f6f22", "32163f8f5114beea5576c93b2ce21ec1e48988ce", "23322eb052d4de32d25a4fe9941175aceb08a804", "581f4e8d74b9ffa3d1e4fbbac8d8742de79cb6c2", "745d86adca56ec50761591733e157f84cfb19671", "7fdf4e6a43ee4b36e91f4d7b3d4c4bf2b2c89d83", "cc68ee0f2fd55aad60680226a8d640719d32a823", "2dd074cf4321525671911d26890e2adb1fe4f608", "4dd266f8c56e3c5981b4f9682629b55103f98e55", "64daf57c5789b57e6562c70fbb7a01e56e888dcd", "17f117a1260ef4c897de3b16d3b637b6af4f1004", "837c2bf28887fc1a00e1b1148e5df748809da242", "fac2ffbd962fe41e9d793bc72cc5853679cede67", "c6afe8a8aa13de8e3f2710ef07b22ce86a005419", "1c23e1ad1a538416e8123f128a87c928b09be868", "20191887f0c97b7e2c56a065854bd704997b3dd9", "9e463eefadbcd336c69270a299666e4104d50159", "5fb74a47bc4305f3bcbd63e14ede262267b0181a", "17ed9ff7ced14bfc336a4784c1bf9771812d1721", "44a9484e0b752e7f1218f0c6dd7461a97bc7ab49", "437d10dbcfa1903e5e868745255d72651e691a5a", "b1a20cb78974059deeeff333c3a553cc4c06a248"], "paperAbstract": "Generating coherent discourse is an important aspect in natural language generation. Our aim is to learn factors that constitute coherent discourse from data, with a focus on how to realize predicate-argument structures in a model that exceeds the sentence level. We present an important subtask for this overall goal, in which we align predicates across comparable texts, admitting partial argument structure correspondence. The contribution of this work is two-fold: We first construct a large corpus resource of comparable texts, including an evaluation set with manual predicate alignments. Secondly, we present a novel approach for aligning predicates across comparable texts using graph-based clustering with Mincuts. Our method significantly outperforms other alignment techniques when applied to this novel alignment task, by a margin of at least 6.5 percentage points in F1-score.", "pdfUrls": ["http://aclweb.org/anthology//D/D12/D12-1016.pdf", "http://aclweb.org/anthology/D12-1016", "http://wing.comp.nus.edu.sg/~antho/D/D12/D12-1016.pdf", "http://aclweb.org/anthology/D/D12/D12-1016.pdf", "http://www.aclweb.org/anthology/D12-1016", "http://www.aclweb.org/anthology-new/D/D12/D12-1016.pdf", "http://www.aclweb.org/anthology/D/D12/D12-1016.pdf", "http://anthology.aclweb.org/D/D12/D12-1016.pdf"], "s2Url": "http://semanticscholar.org/paper/1b81fd32777295dec1fcf2cbcb250e401cc7f353", "title": "Aligning Predicates across Monolingual Comparable Texts using Graph-based Clustering", "venue": "ACL", "year": 2012}
{"authors": [{"ids": ["2921746"], "name": "Ercan U. Acar"}, {"ids": ["26155245"], "name": "Morgan Simmons"}, {"ids": ["2292285"], "name": "Michael Rosenblatt"}, {"ids": ["2849887"], "name": "Maayan Roth"}, {"ids": ["1981508"], "name": "Mary Koes"}, {"ids": ["2338796"], "name": "Yonatan Mittlefehldt"}, {"ids": ["1742948"], "name": "Howie Choset"}], "id": "5308c5951bc760242c31fc1c4200ff1faa4ca43c", "inCitations": [], "journalName": "", "journalPages": "932-933", "journalVolume": "", "keyPhrases": ["Critical Point", "Coverage Algorithm", "Possible Point", "Unknown Environment", "Complete Coverage"], "outCitations": ["f9c2cfed6b365f89aff49f038d7f1e7c259f4738", "93678eae70c29e79aef4e4b649d8d1979c75de53", "9fa660653883207c9d438df441a69c4da2a65855", "3cf005850153d48565ab04312759a47825aebc82"], "paperAbstract": "This paper introduces a sensor based coverage algorithm and an overview of a mobile robot system for demining. The algorithm is formulated in terms of critical points which are the points where the topology of an environment changes. We developed a provably complete coverage algorithm which makes a robot pass over all possible points of an unknown environment. Overview of The Coverage Algorithm Conventional path planning determines a path between two points. This type of planning is suitable for guidance, pick and place operations etc.. Applications such as vacuum cleaning, floor scrubbing, area surveying, demining (Land & Choset 1998) and harvesting (Ollis & Stentz 1996) require more than point to point planning. They require a coverage algorithm which determines a path that passes the robot over all possible points in an environment. In many scenarios, the robot may not know its environment a priori, and thus a sensor based coverage algorithm is necessary. Sensor based coverage determines a path for a robot such that it passes over all possible points in an unknown environment. Completeness of such a coverage algorithm is of utmost importance. As an example, all possible points of a minefield should be covered to guarantee not to miss a single mine. Different types of coverage algorithms were developed by several researchers. Some of the algorithms are grid based (Zelinsky et al. 1993), (Pirzadeh Snyder 1990) and some of them are cellular decomposition based (Cao, Huang, & Hall 1988), (Vladimir J. Lumelsky & Sun 1990), (Hert, Tiwari, & Lumelsky 1996). Behavior based algorithms for coverage are also considered (MacKenzie & Balch 1996). However all these algorithms either work only in certain types of environments, make unrealistic assumptions about the sensors, or completeness of the algorithm is not shown. We developed a provably complete coverage algorithm and implemented it on a mobile platform. Cells Figure 1: Cellular Decomposition Our method is based on a geometric structure called cellular decomposition (Latombe 1991), which is the union of non-overlapping subregions of the free space, called cells. An adjacency graph encodes the topology of the cells in the environment where nodes are cells and edges connect nodes of adjacent cells (Fig. 1). Since simple back and forth motions cover each cell, complete coverage is reduced to finding an exhaustive walk through the adjacency graph (Choset & Pignon", "pdfUrls": ["http://www.aaai.org/Papers/AAAI/1999/AAAI99-144.pdf", "http://www.aaai.org/Library/AAAI/1999/aaai99-144.php"], "s2Url": "http://semanticscholar.org/paper/5308c5951bc760242c31fc1c4200ff1faa4ca43c", "title": "Sensor Based Coverage of Unknown Environments for Land Mine Detection", "venue": "AI", "year": 1999}
{"authors": [{"ids": ["2358905"], "name": "Jes\u00fas Gonz\u00e1lez-Rubio"}, {"ids": ["3932625"], "name": "Daniel Ortiz-Mart\u00ednez"}, {"ids": ["2802518"], "name": "Jos\u00e9-Miguel Bened\u00ed"}, {"ids": ["1696761"], "name": "Francisco Casacuberta"}], "id": "2ed0abd353ab1dcb49651bd425b96606bff36954", "inCitations": ["28c938d64d360cdf97c3584d0452a088b56e85ca", "06e287410c148285ea1b4672ac681d9f077feff8", "36756e46cd21cc4f9a561f681de4d6bee1e6a14e", "d29df6f4b0205bc5af4b8b24f49d58b17ba9d41d", "469d7d50b99a3e505be792aadbdfa21a6e8bf486", "008d13833c2efb653c8f341205deb5eb3ead9954", "8aac1d558cb91e43124d484f7bca14c9b4227e13", "4d0f0179b25e19ffaa7f1b42f2704aa57f37ecd2"], "journalName": "", "journalPages": "244-254", "journalVolume": "", "keyPhrases": ["IMT", "Prefix", "Error-correction", "Reordering", "Statistical Framework"], "outCitations": ["c4d23ade858ead2f2a072e442cd4bad8d788675b", "0709c525b8aa4d0cdd3500baa11c222e9bb7d0bc", "56bc078f0b7b4c6112001af12527b3f7fcf4f021", "37fadfb6d60e83e24c72d8a90da5644b39d6e8f0", "7fa51d9ebf688949571a86411c7baf13d30c74d0", "8b15793f9307b620d7fc85577f88435ad41db2c5", "7181f7a664fbbf34c7c147c8a90f0343cdd1674c", "167496215a29a85bb57c25525e4e34756f30e2a3", "96c14186ebe33b8d3fb1ff251987d81824144481", "04f1bbcc2f497c35313e6577f1e9496594a2df1f", "1d8b713586603dd73a841377b3b7dee85dbd9c73", "926b41fa5b48f85b3983bf1c6bb1c8a937667938", "7fdf4e6a43ee4b36e91f4d7b3d4c4bf2b2c89d83", "46150c4bb8ca6f58fd6a778855ae6e7aeb0f7be9", "21a6ed154f0ec48c312c9de256167dd0722a718f", "26984ac6ef3120c24f4c7742ef901474814f02f2", "1292b63dcfcdceac0c1a10d7b335f90176666d5e", "20a3c066bb375a9d8a2ce293b8209b5ffab2010a", "6b1683c7f8f80df92d32bf97c8400e77a46fdccd", "368f3dea4f12c77dfc9b7203f3ab2b9efaecb635", "11aedb8f95a007363017dae311fc525f67bd7876", "1297074f0e7d6c663c55f7580ca603473842eec9", "d4b9093a658eb15373c4e8f825006cb2aed78b53"], "paperAbstract": "Current automatic machine translation systems are not able to generate error-free translations and human intervention is often required to correct their output. Alternatively, an interactive framework that integrates the human knowledge into the translation process has been presented in previous works. Here, we describe a new interactive machine translation approach that is able to work with phrase-based and hierarchical translation models, and integrates error-correction all in a unified statistical framework. In our experiments, our approach outperforms previous interactive translation systems, and achieves estimated effort reductions of as much as 48% relative over a traditional post-edition system.", "pdfUrls": ["http://www.mt-archive.info/10/EMNLP-2013-Gonzalez%20Rubio.pdf", "http://aclweb.org/anthology/D13-1025", "http://aclweb.org/anthology/D/D13/D13-1025.pdf", "http://aclweb.org/anthology//D/D13/D13-1025.pdf", "http://anthology.aclweb.org/D/D13/D13-1025.pdf", "http://www.aclweb.org/anthology/D13-1025", "http://wing.comp.nus.edu.sg/~antho/D/D13/D13-1025.pdf", "http://www.aclweb.org/anthology/D/D13/D13-1025.pdf"], "s2Url": "http://semanticscholar.org/paper/2ed0abd353ab1dcb49651bd425b96606bff36954", "title": "Interactive Machine Translation using Hierarchical Translation Models", "venue": "ACL", "year": 2013}
{"authors": [{"ids": ["13791549"], "name": "Valentina Bayer"}], "id": "229eb4a24a93c6e7527b11b3c37ae9776d4af485", "inCitations": [], "journalName": "", "journalPages": "941", "journalVolume": "", "keyPhrases": ["MDP", "CoMDP", "Pomdp", "State Of The World", "Approximation Algorithm"], "outCitations": [], "paperAbstract": "Partial observability is a result of noisy or imperfect sensors that are not able to reveal the real state of the world. Problems that suffer from partial observability have been modelled as Partially Observable Markov Decision Processes (POMDPs). They have been studied by researchers in Operations Research and Artificial Intelligence for the past 30 years. Nevertheless, solving for the optimal solution or for close approximations to the optimal solution is known to be NP-hard. Current algorithms are very expensive and do not scale well. Many applications can be modelled as POMDPs: quality control, autonomous robots, weapon allocation, medical diagnosis. Designing approximation algorithms to solve problems that have partial observability is the focus of this research. The model we propose (Cost Observable Markov Decision Processes or COMDPs) associates costs with obtaining information about the current state (Bayer 1998). The COMDP\u2019s actions are of two kinds: world actions and observation actions. World actions change the state of the world, but return no observation information. Observation actions return observation information, but the state of the world does not change while performing them. COMDPs are intended to model situations that arise in diagnosis and active vision where there are many observation actions that do not change the world and relatively few world-changing actions. We are particularly interested in problems where there are many alternative sensing actions (including, especially, no sensing at all) and where, if all observation actions are performed, the entire state of the world is observable (but presumably at very great cost). Hence, COMDPs can also be viewed as a form of fully observable Markov Decision Processes (MDPs) where the agent must pay to receive state information (they are \"cost-observable\"). Any POMDP can be modeled as a COMDP and vice versa. We want to approximately solve COMDPs and determine what POMDP classes these approximations are good for. There are two fundamental problems that any POMDP approximation algorithm must address: how to act when \"lost\" and how to avoid getting \"lost\".", "pdfUrls": ["http://ir.library.oregonstate.edu/xmlui/bitstream/handle/1957/28851/Approximation%20algorithms%20for%20solving%20cost%20observable%20Markov%20decision%20process.pdf?sequence=1", "http://www.aaai.org/Library/AAAI/1999/aaai99-149.php", "http://www.aaai.org/Papers/AAAI/1999/AAAI99-149.pdf", "http://www.cs.orst.edu/~bayer/research/proposal.ps"], "s2Url": "http://semanticscholar.org/paper/229eb4a24a93c6e7527b11b3c37ae9776d4af485", "title": "Approximation Algorithms for Solving Cost Observable Markov Decision Processes", "venue": "AI", "year": 1999}