{"authorId":"2244184","check_arguments":{"unspecified":[],"unsupported":[]},"function":"lookup_author","inputs":{"fields":"papers","id":"2244184"},"papers":[{"bibtex":null,"paperId":"3b6d0eb3c7cd18bff18e90e0506d8fe413f416b5","pdfs":[],"title":"Improved Contextualized Speech Representations for Tonal Analysis"},{"bibtex":null,"paperId":"46cc3955e1ce70609b404d5cb296dd8c0e23d904","pdfs":[],"title":"An Example of (Too Much) Hyper-Parameter Tuning In Suicide Ideation Detection"},{"bibtex":null,"paperId":"9678a51673fd6250f8b479e0e0fb11234d1a6644","pdfs":[],"title":"Emerging trends: Smooth-talking machines"},{"bibtex":null,"paperId":"0aa43be19c0a2c0da91fbb38b77abaecd73924c4","pdfs":[],"title":"Training on Lexical Resources"},{"bibtex":null,"paperId":"3bc077321d66913025f0c63f9c0c4c40c292b49b","pdfs":[],"title":"Advanced Manufacturing and Characterization of mm-Wave Two-Layer Reflectarray Cells"},{"bibtex":null,"paperId":"46cd204c12aaee7234f3752a0d95f4be27962aac","pdfs":[],"title":"Data-Driven Adaptive Simultaneous Machine Translation"},{"bibtex":null,"paperId":"5cb89f053a05794115f79349ec3bf7c6050a019c","pdfs":[],"title":"MARKOV CHAINS AND MARKOV DECISION PROCESSES"},{"bibtex":null,"paperId":"710d50e2a072d4dfc85d76de6684400c80ea59ce","pdfs":[],"title":"ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture"},{"bibtex":null,"paperId":"7467b27d83a4f1f7adb9f5e90a8e49282c5177ea","pdfs":[],"title":"W-CTC: a Connectionist Temporal Classification Loss with Wild Cards"},{"bibtex":null,"paperId":"978dbc014f9d6116169c0dcaf8480c49319703ba","pdfs":[],"title":"Efficiently Disentangle Causal Representations"},{"bibtex":null,"paperId":"b086ecd3d17f1d7ff9ae15e703709ac36e713ad2","pdfs":[],"title":"Data Augmentation for the Post-Stroke Speech Transcription (PSST) Challenge: Sometimes Less Is More"},{"bibtex":null,"paperId":"026a76ef4235e6dac950eecc4281e9069fffa424","pdfs":[],"title":"SSPF: a Simple and Scalable Parameter Free Clustering Method"},{"bibtex":null,"paperId":"09ce767738780c345d1d355411d2fa238b853598","pdfs":[],"title":"Large Margin Training Improves Language Models for ASR"},{"bibtex":null,"paperId":"1c475c8182f411ec28a6c29b6150cd1e282da5b9","pdfs":[],"title":"Photonic Curing of mm-Wave Coplanar Waveguides for Conductor Loss Enhancement"},{"bibtex":null,"paperId":"2a8bb26654c015f663670d1e0745f870071d5507","pdfs":[],"title":"Isotropy in the Contextual Embedding Space: Clusters and Manifolds"},{"bibtex":null,"paperId":"57ed901be5d1b4d853d4f8998dadc1b60e2151f9","pdfs":[],"title":"On Attention Redundancy: A Comprehensive Study"},{"bibtex":null,"paperId":"6a2a09b3bfcdf33829d018fe99715aeb1d160dbf","pdfs":[],"title":"Exploiting a Zoo of Checkpoints for Unseen Tasks"},{"bibtex":null,"paperId":"6f31319545e5ec436c45e6142dff080795b78933","pdfs":[],"title":"Automatic recognition of suprasegmentals in speech"},{"bibtex":null,"paperId":"7447a980dba05d907484ff743a92da67b06b1abd","pdfs":[],"title":"Pauses for Detection of Alzheimer\u2019s Disease"},{"bibtex":null,"paperId":"92ab22ba756823f1ff350a5c052b41420d7fe779","pdfs":[],"title":"Speaking Rate and Tonal Realization in Mandarin Chinese: What Can We Learn From Large Speech Corpora?"},{"bibtex":null,"paperId":"a566da8ac72ad60f3c9380ac9e038a91314ef77a","pdfs":[],"title":"Acronyms and Opportunities for Improving Deep Nets"},{"bibtex":null,"paperId":"b94262a62cd2af728550a99f263a3084d1b4e0f9","pdfs":[],"title":"Speech Emotion Recognition with Multi-Task Learning"},{"bibtex":null,"paperId":"b9b53418233e4b5f303ce8dc1535a4f292dfb58d","pdfs":[],"title":"Pause-Encoded Language Models for Recognition of Alzheimer\u2019s Disease and Emotion"},{"bibtex":null,"paperId":"bfbb6a3a3f7ddb5190e3bfe64438c424e37b1fc6","pdfs":[],"title":"Better than BERT but Worse than Baseline"},{"bibtex":null,"paperId":"ee43494fe4c33102aa10d4b59bcd2bd0e68962ab","pdfs":[],"title":"Decoupling Recognition and Transcription in Mandarin ASR"},{"bibtex":null,"paperId":"f5e609e9f0af19593dd9d462fb7531e23e00a92d","pdfs":[],"title":"The Role of Phonetic Units in Speech Emotion Recognition"},{"bibtex":null,"paperId":"134d608f4e78da82c9c3c119f57cbde32e220f5e","pdfs":[],"title":"Disfluencies and Fine-Tuning Pre-Trained Language Models for Detection of Alzheimer's Disease"},{"bibtex":null,"paperId":"22eb08a8f4d272e82b0f5b554a2f5522785c8333","pdfs":[],"title":"The Third DIHARD Diarization Challenge"},{"bibtex":null,"paperId":"5a09c34160fb9dbb71f9b94db73f7b601a4ca0ce","pdfs":[],"title":"Improving Bilingual Lexicon Induction for Low Frequency Words"},{"bibtex":null,"paperId":"6407e8ab14f73b961798f2487aa53dc0a49773ec","pdfs":[],"title":"Exploring Long Tail Visual Relationship Recognition with Large Vocabulary"},{"bibtex":null,"paperId":"7e69f2255d3685c6aae2790d0807b5df5fd031f5","pdfs":[],"title":"Compositional Continual Language Learning"},{"bibtex":null,"paperId":"83bb82ce434f2c61fe83be75cdd5fa5bbf3e2fd7","pdfs":[],"title":"Emerging trends: Reviewing the reviewers (again)"},{"bibtex":null,"paperId":"8515c83e6562415021b4c536c28ed198f05a8691","pdfs":[],"title":"Emerging trends: Subwords, seriously?"},{"bibtex":null,"paperId":"a2ced1811f12b4a2555254a2e36be71635f45179","pdfs":[],"title":"Third DIHARD Challenge Evaluation Plan"},{"bibtex":null,"paperId":"aefb03008a0a9f582e9b70cfbb7d2029d3a9853b","pdfs":[],"title":"Long-tail Visual Relationship Recognition with a Visiolinguistic Hubless Loss"},{"bibtex":null,"paperId":"b9ec513e5c8ec3af3baada26bc87af9c0c41b758","pdfs":[],"title":"Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training"},{"bibtex":null,"paperId":"c6cb205ee53a31cb8f303d0ddf4618a7be903adb","pdfs":[],"title":"Long Tail Visual Relationship Recognition with Hubless Regularized Relmix"},{"bibtex":null,"paperId":"cff98b4b563ca2668d71b9b0f748428bbf68d041","pdfs":[],"title":"Benchmarks and goals"},{"bibtex":null,"paperId":"1714b1f8de43cc18286b1ba2832a0ddb922161fb","pdfs":[],"title":"Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework"},{"bibtex":null,"paperId":"5292a00eff5f9864adc6a4d159591d3d476cba8c","pdfs":[],"title":"Hubless Nearest Neighbor Search for Bilingual Lexicon Induction"},{"bibtex":null,"paperId":"5b184b43371b31512315c16ea25e24f9522059b5","pdfs":[],"title":"A survey of 25 years of evaluation"},{"bibtex":null,"paperId":"daaf8b821c07dc2de2b8d9e8bbb5cb41cab15f94","pdfs":[],"title":"Compositional Language Continual Learning"},{"bibtex":null,"paperId":"ff88699c6bac1b289272c445581541ad66848044","pdfs":[],"title":"The Second DIHARD Diarization Challenge: Dataset, task, and baselines"},{"bibtex":null,"paperId":"4b33331fc423fd303a8b5854d4da2fc36e1f4970","pdfs":[],"title":"Minsky, Chomsky and Deep Nets"},{"bibtex":null,"paperId":"4da931564482e39d54204df1ab2beb87a1fc02c2","pdfs":[],"title":"Emerging trends: Artificial Intelligence, China and my new job at Baidu"},{"bibtex":null,"paperId":"57c13015444162846b8c9326d3a8be83d3712610","pdfs":[],"title":"Language Modeling at Scale"},{"bibtex":null,"paperId":"831d48f34f2981d6e36e23dfa91a927e80dca903","pdfs":[],"title":"Implementation of Energy Strategies in Communities (Annex 63) Volume 3: Application of Strategic Measures"},{"bibtex":null,"paperId":"eb469747ced0cd5d383430d3d723c50d85cfc72e","pdfs":[],"title":"Enhancement and Analysis of Conversational Speech: JSALT 2017"},{"bibtex":null,"paperId":"f4a1a55c7f5ceec966623e87b2bfd44d11671047","pdfs":[],"title":"A Proposed Hierarchy of Deep Learning Tasks"},{"bibtex":null,"paperId":"fe50912e68690efab3cfa9351ea68716bd20e76e","pdfs":[],"title":"Emerging trends: APIs for speech and machine translation and more"},{"bibtex":null,"paperId":"09b630aa13ecabfd61e2dfc12864ba49e35a3004","pdfs":[],"title":"Symbol Sequence Search from Telephone Conversation"},{"bibtex":null,"paperId":"152050933a7b775cdad7082541f90709c9d35e5f","pdfs":[],"title":"Corpus Methods in a Digitized World"},{"bibtex":null,"paperId":"1ca1a028d10c22b31e18b8bc8bc749f7cc94271b","pdfs":[],"title":"Emerging trends: I did it, I did it, I did it, but. . ."},{"bibtex":null,"paperId":"28e89602aebbc9157552a40f6a5bd9826a201f73","pdfs":[],"title":"Implementation of Energy Strategies in Communities (Annex 63). - Volume 1: Inventory of measures"},{"bibtex":null,"paperId":"3696f26aefc8f4483c827198c7f63d77b07ba323","pdfs":[],"title":"Emerging trends: A tribute to Charles Wayne"},{"bibtex":null,"paperId":"6648a1fbd58cf1c09edddf90cecdd8a6a757ac1a","pdfs":[],"title":"Implementation of Energy Strategies in Communities (Annex 63) Volume 2: Development of strategic measures"},{"bibtex":null,"paperId":"6ebf67d5eac645287b96cf977943b0b06bb70284","pdfs":[],"title":"Word2Vec"},{"bibtex":null,"paperId":"97a1edb81a44f6d73e6124afc617f947ffa26328","pdfs":[],"title":"Emerging trends: Inflation"},{"bibtex":null,"paperId":"a2c8a64b6f582fa525cac7c4ee0a3acebb3a4840","pdfs":[],"title":"Speaker diarization: A perspective on challenges and opportunities from theory to practice"},{"bibtex":null,"paperId":"3bb2bd25b2424c7ea8d17430ba892bae793a894d","pdfs":[],"title":"Real-Time Atmospheric Phase Fluctuation Correction Using a Phased Array of Widely Separated Antennas: X-Band Results and Ka-Band Progress"},{"bibtex":null,"paperId":"487e5698f6cd496e13b3e32c0d2838fefcc37636","pdfs":[],"title":"C2D2E2: Using Call Centers to Motivate the Use of Dialog and Diarization in Entity Extraction"},{"bibtex":null,"paperId":"993339d02c3f97bec0524ecb04ca057b14548aef","pdfs":[],"title":"Proc\u00e9d\u00e9 et appareil permettant la fabrication en 3d"},{"bibtex":null,"paperId":"78947dba7445f06ccf723fccbc695adcbc405a49","pdfs":[],"title":"TALIP Perspectives, Guest Editorial Commentary"},{"bibtex":null,"paperId":"c9fd24aeb1783d735b6a48e5c1d0ba29114a90b8","pdfs":[],"title":"The Case for Empiricism (With and Without Statistics)"},{"bibtex":null,"paperId":"da2536c515a40f6e92100b316ea25269c9bb40c6","pdfs":[],"title":"Statistical Models for Natural Language Processing"},{"bibtex":null,"paperId":"23bd8ab0ec8c6a79d3c501daa7bb1284cd2c7849","pdfs":[],"title":"Deep neural network features and semi-supervised training for low resource speech recognition"},{"bibtex":null,"paperId":"7a0b8cf76de636d30b30e53a72f896fcad0b7055","pdfs":[],"title":"Micro-Dispense Direct Printing for Thermal Management Structure Using LTCC"},{"bibtex":null,"paperId":"a2a0f0adb2b61ba21c8146b554b4416fb96d7aae","pdfs":[],"title":"A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition"},{"bibtex":null,"paperId":"a5be0177798bdf8186d3a89664cf4de4de2e31c9","pdfs":[],"title":"Analysis and Word Pronunciation in Text-to-speech Synthesis"},{"bibtex":null,"paperId":"b64cb73ed528d4960b43ba3aa94b238e2ad0fc8d","pdfs":[],"title":"Text Analysis and Word Pronunciation in Text-to-speech Synthesis"},{"bibtex":null,"paperId":"ea1850ffd17a8a8e5d3170b3a9e6531af43f1982","pdfs":[],"title":"Intent classification of voice queries on mobile devices"},{"bibtex":null,"paperId":"f87b69a3783af760139543a22aa65226945613a6","pdfs":[],"title":"Intent focused summarization of caller-agent conversations"},{"bibtex":null,"paperId":"fd5b8d53bdcfe4e959388f74207da09e10509297","pdfs":[],"title":"AD-A 269 768 Good Applications for Crummy Machine Translation"},{"bibtex":null,"paperId":"98742d20a13366fca25ebffa499247d691105833","pdfs":[],"title":"Approximate inference: A sampling based modeling technique to capture complex dependencies in a language model"},{"bibtex":null,"paperId":"b27412142aeedad7113eac939e953f1578c8c81e","pdfs":[],"title":"Inverting the Point Process Model for Fast Phonetic Keyword Search"},{"bibtex":null,"paperId":"0591a9a6ec348559dc3d8f88956e301200aaf4f8","pdfs":[],"title":"A Fast Re-scoring Strategy to Capture Long-Distance Dependencies"},{"bibtex":null,"paperId":"08369fde25b3ec363b572c2ccf42da94ed8dd8e1","pdfs":[],"title":"Search and decoding strategies for complex lexical modeling in lvcsr"},{"bibtex":null,"paperId":"38f3a353652713ac478b9e5c80f1479816cc95b0","pdfs":[],"title":"A Pendulum Swung too Far"},{"bibtex":null,"paperId":"548a07ffc1b9f771b7fce1680b2a5755d9867362","pdfs":[],"title":"High Aspect Ratio Fine Gridline for Front Side Metallization of Industrial Silicon Solar Cells by Direct Printing"},{"bibtex":null,"paperId":"55db7b549af4f945b929cfb5eb8b99915cdd93d0","pdfs":[],"title":"Using Large Monolingual and Bilingual Corpora to Improve Coordination Disambiguation"},{"bibtex":null,"paperId":"5ffa9b8521e17c4f13f3fc2eff8fcbe4cf7892f2","pdfs":[],"title":"Bootstrapping a spoken language identification system using unsupervised integrated sensing and processing decision trees"},{"bibtex":null,"paperId":"865bc77fcdea5dcd035768bcf512bbee34fdb73d","pdfs":[],"title":"Towards Unsupervised Training of Speaker Independent Acoustic Models"},{"bibtex":null,"paperId":"b64152e5050497350258fc98e01f192203836458","pdfs":[],"title":"How Many Multiword Expressions do People Know?"},{"bibtex":null,"paperId":"e4bdfa3fb661a7978c5b8a7043763a4a5bea5996","pdfs":[],"title":"Direct Printing for Next Generation High Density Packaging"},{"bibtex":null,"paperId":"33d70a6cbf5fd15a865ebc09bfa134477b65b616","pdfs":[],"title":"More is More"},{"bibtex":null,"paperId":"7a29bbb30bf72cfc7ac52a351a04a1178e29dd7f","pdfs":[],"title":"Towards spoken term discovery at scale with zero resources"},{"bibtex":null,"paperId":"84a2929615a231151bb7177d1fe495181538fdcb","pdfs":[],"title":"Direct Printing/Micro-dispensing Solution for 3D Coating Applications"},{"bibtex":null,"paperId":"881782d11dd4babf4fa5156d57504ce093c5aa8e","pdfs":[],"title":"New Tools for Web-Scale N-grams"},{"bibtex":null,"paperId":"b268eb411c846b04159a0bef2c30e30489517713","pdfs":[],"title":"Unsupervised Acquisition of Lexical Knowledge From N-grams : Final Report of the 2009 JHU CLSP Workshop"},{"bibtex":null,"paperId":"d7c3435dfafa3f7fdc546de6dbd53dab74a604a4","pdfs":[],"title":"Reviewers for Volume 31"},{"bibtex":null,"paperId":"e6e767d15f8d2e652b6e7e9b51cbaa72f7857f71","pdfs":[],"title":"Using Web-scale N-grams to Improve Base NP Parsing Performance"},{"bibtex":null,"paperId":"44825e49d3cd2dd84a325a20c5cd14ab5bd61fd6","pdfs":[],"title":"Priors in Web Search"},{"bibtex":null,"paperId":"7124edca72ff281f20562c4ff2c33ef1542a6103","pdfs":[],"title":"Substring Statistics"},{"bibtex":null,"paperId":"bffb78613248c9933e833bf6f23b72c8fffee220","pdfs":[],"title":"A Data Structure for Sponsored Search"},{"bibtex":null,"paperId":"f2e3d3bc6ae8626b1ed73d4be4336ce8932a734d","pdfs":[],"title":"Through the Looking Glass . . . Mediating the Inevitable and the Impossible"},{"bibtex":null,"paperId":"0a60086660a878f23e081d79bf96a256f362accc","pdfs":[],"title":"On Delivering Embarrassingly Distributed Cloud Services"},{"bibtex":null,"paperId":"0f72d6545d2c6754f3c7e8b6919aabecfcecbd39","pdfs":[],"title":"Approximate Lexicography and Web Search"},{"bibtex":null,"paperId":"2a869f1ccc422d7d21ffd0a055d7469a15112468","pdfs":[],"title":"Entropy of search logs: how hard is search? with personalization? with backoff?"},{"bibtex":null,"paperId":"4b89c4b519791264bd0106c62af1fd98b70eb16e","pdfs":[],"title":"One sketch for all: Theory and Application of Conditional Random Sampling"},{"bibtex":null,"paperId":"76ef18cfde62ee3c97d6ec88dff21625c58245b8","pdfs":[],"title":"Query suggestion using hitting time"},{"bibtex":null,"paperId":"dd78e170a35c469e4040761caab4a6fcdae4b258","pdfs":[],"title":"Variable selection for ad prediction"},{"bibtex":null,"paperId":"088b0de596bca15cf01cbc45a15dae0e665f7db5","pdfs":[],"title":"Compressing Trigram Language Models With Golomb Coding"},{"bibtex":null,"paperId":"308d8fdaabb3a4b6f24c33621be06db36dbf03cf","pdfs":[],"title":"K-Best Suffix Arrays"},{"bibtex":null,"paperId":"32d0ff3d26e0e8c082d5910d23ed79e429c73b63","pdfs":[],"title":"Nonlinear Estimators and Tail Bounds for Dimension Reduction in l 1 Using Cauchy Random Projections"},{"bibtex":null,"paperId":"50c85e87f8a4b7605334c8b91b96cd8116d7e142","pdfs":[],"title":"Classification \u00e0 base demographique pour recherche instantan\u00e9e/recherche web"},{"bibtex":null,"paperId":"5261d0c5ca515cb0a41ecdd5c534ae66737a49bd","pdfs":[],"title":"Auf demographie basierende klassifizierung einer lokalen wort-wheeling- bzw. web-suche"},{"bibtex":null,"paperId":"9883f04c04e9c466f2c7d3fed89d9b2f6c4fbe0e","pdfs":[],"title":"Heavy-tailed distributions and multi-keyword queries"},{"bibtex":null,"paperId":"b420edceb80f581fba60ffecb380cca7e05b8eb8","pdfs":[],"title":"The wild thing goes local"},{"bibtex":null,"paperId":"c3d332dc9c04341dfd81c5d607ddb9bcfcac9717","pdfs":[],"title":"Red light emission from hybrid organic/inorganic quantum dot AC light emitting displays"},{"bibtex":null,"paperId":"dce5a1735c8e467735587d1242606ce9f92754e7","pdfs":[],"title":"Best Recognition Exponents Min Mse Exponents Unitary Exponents"},{"bibtex":null,"paperId":"f153f9a68f73e4f3982ae3bcd83eeed1ceeb7a90","pdfs":[],"title":"A Sketch Algorithm for Estimating Two-Way and Multi-Way Associations"},{"bibtex":null,"paperId":"0393eaa7d18b9dc117743350efa7388b363985f9","pdfs":[],"title":"Nonlinear Estimators and Tail Bounds for Dimension Reduction in l1 Using Cauchy Random Projections"},{"bibtex":null,"paperId":"065f4e51976a38ab4352b2ad4052e1956eef2eb7","pdfs":[],"title":"Modeles de compression de langage ave codage de golomb"},{"bibtex":null,"paperId":"2ca59d9e88682a56b6f8fc748d3186d089749bf2","pdfs":[],"title":"Conditional Random Sampling: A Sketch-based Sampling Technique for Sparse Data"},{"bibtex":null,"paperId":"94a0af72b9ed4891404ca412698652b3999e8ce6","pdfs":[],"title":"Improving Random Projections Using Marginal Information"},{"bibtex":null,"paperId":"c129e8025fffa065edb5b27dd7c2269abc0a138b","pdfs":[],"title":"Very sparse random projections"},{"bibtex":null,"paperId":"e285767797cc58b615d28197850ae8ece702341d","pdfs":[],"title":"Emploi de modeles de langage pour l'elargissement de caracteres de remplacement"},{"bibtex":null,"paperId":"e771805f0cf9ed40ac63c997a7d968bc2d6382aa","pdfs":[],"title":"Margin-constrained random projections and very sparse random projections"},{"bibtex":null,"paperId":"e9d92c28095d0174439e304931b3098cde743982","pdfs":[],"title":"A Sketch-based Sampling Algorithm on Sparse Data"},{"bibtex":null,"paperId":"301a71bc7344c9aca8af105db0b8134103ab7b25","pdfs":[],"title":"Using Sketches to Estimate Associations"},{"bibtex":null,"paperId":"65a977eb4a2051f2e75aea1993e5ad428d33345d","pdfs":[],"title":"Using Sketches to Estimate Two-way and Multi-way Associations"},{"bibtex":null,"paperId":"ca96839fc28a899d5fd8830175e241cac11ae276","pdfs":[],"title":"The Wild Thing"},{"bibtex":null,"paperId":"d375c102866226fe1ce8f59a0769d21d1f408864","pdfs":[],"title":"The DDI Approach to Morphology"},{"bibtex":null,"paperId":"382d7ba13ffbd42d1eb2d3b35cbc519cabb84722","pdfs":[],"title":"Termight: Coordinating Humans and Machines in Bilingual Terminology Acquisition"},{"bibtex":null,"paperId":"4995166a2ddea929ebb090e84832d9945c430587","pdfs":[],"title":"Speech and Language Processing: Can We Use the Past to Predict the Future?"},{"bibtex":null,"paperId":"71635093dd792b5e0b6cdcc5ddcec2b0095988e0","pdfs":[],"title":"The submatrices character count problem: an efficient solution using separable values"},{"bibtex":null,"paperId":"78447444b667eed4979b9d39352d481a8c5e232d","pdfs":[],"title":"Iterative Denoising for Cross-Corpus Discovery"},{"bibtex":null,"paperId":"c73b500b5490189bfe1025e605a01f7bd3bb856b","pdfs":[],"title":"Preface"},{"bibtex":null,"paperId":"976df999eb48761c442758743b4ee7bf24292b0c","pdfs":[],"title":"Speech and language processing: where have we been and where are we going?"},{"bibtex":null,"paperId":"ccd5898c79f90c25e24222410d5613edfd007985","pdfs":[],"title":"Using Statistics in Lexical Analysis"},{"bibtex":null,"paperId":"2e4bf64cf8980dedc663d750f899d4d269bce0b4","pdfs":[],"title":"In situ chlorine detection by ultraviolet absorption spectroscopy"},{"bibtex":null,"paperId":"4866020354e421f7d19b2a01f587111d00718d67","pdfs":[],"title":"Nikolas K. Gvosdev, Imperial Policies and Perspectives towards Georgia, 1760\u20131819. \n New York: St. Martin's Press, 2000, xxi, 197 pp. + maps, notes, bibliography, index."},{"bibtex":null,"paperId":"648d973a946cbb78ee8e2ef75e8c59fcab23a8f7","pdfs":[],"title":"Dedication to William A. Gale"},{"bibtex":null,"paperId":"67068b542acf46c121e6caaac197bddb201488a5","pdfs":[],"title":"What\u2019s Happened Since the First SIGDAT Meeting?"},{"bibtex":null,"paperId":"d794a7050c2f326eac0c5030700b428f91f684a2","pdfs":[],"title":"Separable attributes: a technique for solving the sub matrices character count problem"},{"bibtex":null,"paperId":"df8e9a525770cae8cec6830a11373c7069cee798","pdfs":[],"title":"Meta-materials concepts in high-frequency applications"},{"bibtex":null,"paperId":"7259b5119c4a7d2893efddf282f906d5a6e0af2a","pdfs":[],"title":"Using Bins to Empirically Estimate Term Weights for Text Categorization"},{"bibtex":null,"paperId":"b1d4f71bb455e8cc1b49319e836450d85292f632","pdfs":[],"title":"From dynastic principality to imperial district : the incorporation of Guria into the Russian Empire to 1856"},{"bibtex":null,"paperId":"bf17c0266f835fa5ad8ff5304916c6419cc02108","pdfs":[],"title":"Using Suffix Arrays to Compute Term Frequency and Document Frequency for All Substrings in a Corpus"},{"bibtex":null,"paperId":"10ae2d947b79c09585cf9abe18c4404adf03631d","pdfs":[],"title":"Engineering the compression of massive tables: an experimental approach"},{"bibtex":null,"paperId":"67e9fb2295d973fbd9db17464cc0a883c6d0d190","pdfs":[],"title":"Empirical Term Weighting and Expansion Frequency"},{"bibtex":null,"paperId":"8e9f1a9d0a29ab40df66be1e600ccd5a358bb1f1","pdfs":[],"title":"Dynamic programming: a method for taking advantage of technical terminology in Japanese documents"},{"bibtex":null,"paperId":"bd1fd0489c6271272d56372c1c719c9233fdbbb6","pdfs":[],"title":"Stress AJ~p,aMm is Lett~ m Se,,,td Rats fer Speech Sy~"},{"bibtex":null,"paperId":"efada5827fd7eedecb4a7dc101caa4509a9f770f","pdfs":[],"title":"Empirical Estimates of Adaptation: The chance of Two Noriegas is closer to p/2 than p2"},{"bibtex":null,"paperId":"efef737f5c31f6e47d2c6f7809fc3eb45dfa2396","pdfs":[],"title":"Using variable length ngrams for retrieving technical abstracts in Japanese (poster session)"},{"bibtex":null,"paperId":"23e1993ad65ef984bd11d58463d59f1e3cec1341","pdfs":[],"title":"Robust Bilingual Word Alignment for Machine Aided Translation"},{"bibtex":null,"paperId":"ad1ff0eb310fe24abbaa88ca82996c605671f6e4","pdfs":[],"title":"Virtual Data Warehousing, Data Publishing, and Call Detail"},{"bibtex":null,"paperId":"b8241680d2158f41ac9cb7cbdfda588c5c3504f9","pdfs":[],"title":"Japanese Word Segmentation Using Similarity Measure for IR"},{"bibtex":null,"paperId":"ef847e14d63341274f5f2dcf978786b721bcfcd8","pdfs":[],"title":"Techniques in Speech Acoustics"},{"bibtex":null,"paperId":"91478ee741867052897858c7b3054ec6edc72b02","pdfs":[],"title":"Applications of Natural Language Processing"},{"bibtex":null,"paperId":"896f0c598c4f6de934083fc9fdb357864c977529","pdfs":[],"title":"Statistical MT/spl ne/stone soup"},{"bibtex":null,"paperId":"13d3ada414ce8071efd165e074bdfd1a5e8ad64a","pdfs":[],"title":"One term or two?"},{"bibtex":null,"paperId":"25fcfd7c56248cba82d93978e1aefebff94aa840","pdfs":[],"title":"Discrimination decisions for 100,000-dimensional spaces"},{"bibtex":null,"paperId":"439bff5ae1525801acb95ad02d4389fb0e7bffeb","pdfs":[],"title":"Poisson mixtures"},{"bibtex":null,"paperId":"60cab0000cd12a405ec5014892ff37e5db39e59f","pdfs":[],"title":"Inverse Document Frequency (IDF): A Measure of Deviations from Poisson"},{"bibtex":null,"paperId":"a84e6ad289428e03579995ad1ee459b6e0119383","pdfs":[],"title":"Commercial applications of natural language processing"},{"bibtex":null,"paperId":"d3697b25ff9fa3a8e93f7d3424a2af325994d440","pdfs":[],"title":"You shall know a word by the company it keeps"},{"bibtex":null,"paperId":"fa2c2894e51aaa0d8a0773333ac582655d153411","pdfs":[],"title":"Commercial of Natural Language Processing"},{"bibtex":null,"paperId":"fc7dc16bd366a6ce1af98eaf00b6b047c47d8d3a","pdfs":[],"title":"A method for reducing the sampling frequency of documents"},{"bibtex":null,"paperId":"0ceab4bab5462584b0c6124ba1d95636d50904d0","pdfs":[],"title":"Termight: Identifying and Translating Technical Terminology"},{"bibtex":null,"paperId":"3491aa4a9a66ba3d1603230a70d82c7479666a7d","pdfs":[],"title":"K-vec: A New Approach for Aligning Parallel Texts"},{"bibtex":null,"paperId":"928afe2f95fabb10e0dfb73be7881b346ba5d738","pdfs":[],"title":"Is MT Research Doing Any Good?"},{"bibtex":null,"paperId":"9e09439f009dd0d4618949e4e01964df2e1f1d2d","pdfs":[],"title":"- 1-What \u2019 s Wrong with Adding One ?"},{"bibtex":null,"paperId":"b927a722e9d8a1be4ce03293ac622ec6b91e17f3","pdfs":[],"title":"Method and apparatus for speech processing using morphology and rhyming"},{"bibtex":null,"paperId":"e24114c9a06e5aa14b8cb2f25e50edc06c3a7eeb","pdfs":[],"title":"Fax: An Alternative to SGML"},{"bibtex":null,"paperId":"fa83b65e65821cd1ec51099252962bf41d43b38c","pdfs":[],"title":"Using OCR and equalization to downsample documents"},{"bibtex":null,"paperId":"1cf01798f07e1f13cd44daad6119f4978721c61d","pdfs":[],"title":"Char_align: A Program for Aligning Parallel Texts at the Character Level"},{"bibtex":null,"paperId":"291e7ed5e5e2bdf9580a5c0498bf89a01587bcd1","pdfs":[],"title":"Text analysis for speech synthesis"},{"bibtex":null,"paperId":"3a77058b626b3670f5b5afba81e47a430c0b0196","pdfs":[],"title":"A statistical approach to aligning sentences in bilingual corpora"},{"bibtex":null,"paperId":"4fe2a45babab10c1bfae05d2464363f4e52bbaf9","pdfs":[],"title":"A Program for Aligning Sentences in Bilingual Corpora"},{"bibtex":null,"paperId":"5417b3403bee25c2fce7418cb88624d62d39bf32","pdfs":[],"title":"Dotplot : a program for exploring self-similarity in millions of lines of text and code"},{"bibtex":null,"paperId":"8d021434c8da92634a49cead486826789af8ffff","pdfs":[],"title":"Aligning Parallel Texts : Do Methods Developed for English-French Generalize to Asian Languages?"},{"bibtex":null,"paperId":"c0e1753473752a231443fc368962582542b8fdf7","pdfs":[],"title":"Good applications for crummy machine translation"},{"bibtex":null,"paperId":"0fa28d8a77e438d58b3d3670028b4e4f5380732b","pdfs":[],"title":"One Sense Per Discourse"},{"bibtex":null,"paperId":"137e654cc632c96a2b0bea5f3f442a929b8b6495","pdfs":[],"title":"One Sense per Discourse 2. Our Previous Work on Word-sense Disambiguation 2.1. Data Deprivation"},{"bibtex":null,"paperId":"54859dd7fcfd9112e01eded68a29cd26611d66e8","pdfs":[],"title":"Work on Statistical Methods for Word Sense Disambiguation"},{"bibtex":null,"paperId":"553fa529ba615e4bddea81e9a231ae19d5a870a4","pdfs":[],"title":"Estimating Upper and Lower Bounds on the Performance of Word-Sense Disambiguation Programs"},{"bibtex":null,"paperId":"809d6ee2b1a1dfa1623360ee94cd4efacbd7edf1","pdfs":[],"title":"Using bilingual materials to develop word sense disambiguation methods"},{"bibtex":null,"paperId":"bf35ed0864ff6cf524a24f0a65aa6951f9d6f214","pdfs":[],"title":"A method for disambiguating word senses in a large corpus"},{"bibtex":null,"paperId":"130b3fc5591ecde99706842131d9fc231b07a2e9","pdfs":[],"title":"Review of Theory and practice in corpus linguistics by Jan Aarts and Willem Meijs. Editions Rodopi 1990."},{"bibtex":null,"paperId":"5051e54af8c0d6b84f8459c57d55bd19be9f0cee","pdfs":[],"title":"Identifying Word Correspondences in Parallel Texts"},{"bibtex":null,"paperId":"cde4cf53049eea9851b3fb860ef303d4dc8acea7","pdfs":[],"title":"Text analysis system with letter sequence recognition and speech stress assignment arrangement"},{"bibtex":null,"paperId":"d8d59ed7bfde36fd640cec30b2537630f3e30ff7","pdfs":[],"title":"Probability scoring for spelling correction"},{"bibtex":null,"paperId":"df563691b20b727fe346fc00f6b2afc25d97fb8d","pdfs":[],"title":"Identifying word correspondence in parallel texts"},{"bibtex":null,"paperId":"ef9190e7669ea5523c3ef61180b35385b0ea345f","pdfs":[],"title":"A comparison of the enhanced Good-Turing and deleted estimation methods for estimating probabilities of English bigrams"},{"bibtex":null,"paperId":"2d30aa623fd96da99a16c0c3bde73f50c92a5c42","pdfs":[],"title":"Poor Estimates of Context are Worse than None"},{"bibtex":null,"paperId":"31ef8b3ebc50d682cbd6ce95505ab49802be6bd7","pdfs":[],"title":"A Spelling Correction Program Based on a Noisy Channel Model"},{"bibtex":null,"paperId":"5042cea2b584fbdfe3126bd5b3f4c65ec95e2fa1","pdfs":[],"title":"Morphology and rhyming: two powerful alternatives to letter-to-sound rules for speech synthesis"},{"bibtex":null,"paperId":"f0132fb9fb941183cc451c3df02f5e4bffb6aa8c","pdfs":[],"title":"Estimation Procedures for Language Context: Poor Estimates are Worse than None"},{"bibtex":null,"paperId":"145b0981d3b7068b24b5f2e60dc5e04ef585fcb0","pdfs":[],"title":"Parsing, Word Associations and Typical Predicate-Argument Relations"},{"bibtex":null,"paperId":"264e107971a50eaf6dfcbd02e9c3fa8fdb83c20f","pdfs":[],"title":"Enhanced Good-Turing and Cat-Cal: Two New Methods for Estimating Probabilities of English Bigrams (abbreviated version)"},{"bibtex":null,"paperId":"9e2caa39ac534744a180972a30a320ad0ae41ea3","pdfs":[],"title":"Word Association Norms, Mutual Information, and Lexicography"},{"bibtex":null,"paperId":"a16459748e22d172ccb7a956d9ec0357e1f1a392","pdfs":[],"title":"Session 11: natural language III"},{"bibtex":null,"paperId":"b8888524e4d4d027b89d8435fd4370f1ca61e31a","pdfs":[],"title":"M\u00e9thode pour la d\u00e9termination des \u00e9lements de langage et utilisation"},{"bibtex":null,"paperId":"ff6961eb57f9e85a47db2282f59a46102bbd38bc","pdfs":[],"title":"Typical Predicate-Argument Relations 1"},{"bibtex":null,"paperId":"ff97fa9912e4e0517208bf45ef0f646f995e09d2","pdfs":[],"title":"Parsing, Word Associations and Typical Predicate-Argument Relations"},{"bibtex":null,"paperId":"a7e084fe51a40eeaaf79bf0b78e837d5bc4a8e10","pdfs":[],"title":"A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text"},{"bibtex":null,"paperId":"c63b2456416f1bf952834dc8cd04288bafa2cbd6","pdfs":[],"title":"Complexity, Two-Level Morphology and Finnish"},{"bibtex":null,"paperId":"01abae976a378ed41c380647a552b405971e9c81","pdfs":[],"title":"Phonological parsing and lexical retrieval."},{"bibtex":null,"paperId":"10a5447b024f174503253276f719f991784a5ac4","pdfs":[],"title":"Phonological parsing in speech recognition"},{"bibtex":null,"paperId":"246f95abe01ff04cba3f6243c6187ea88ec53d4a","pdfs":[],"title":"When Phonotactic Constraints are Not Enough"},{"bibtex":null,"paperId":"67b4de38535074e6f89b26d053cff5d4af8ce884","pdfs":[],"title":"PRELIMINARY ANALYSIS OF A BREADTH-FIRST PARSING ALGORITHM: THEORETICAL AND EXPERIMENTAL RESULTS"},{"bibtex":null,"paperId":"98244ec672aa77af46d0919128f591adce0255d3","pdfs":[],"title":"Representation of Segments"},{"bibtex":null,"paperId":"a08140e1b6696641f208c6971f139dfabb8d0eab","pdfs":[],"title":"An Alternative: Phrase-Structure Rules"},{"bibtex":null,"paperId":"6bfae86f0f2e3e721eb3203b956129329a4e2fc7","pdfs":[],"title":"Stress Assignment in Letter to Sound Rules for Speech Synthesis"},{"bibtex":null,"paperId":"b5805709d9093e8a69c7bb55c3844433153e2c8e","pdfs":[],"title":"Morphological Decomposition and Stress Assignment for Speech Synthesis"},{"bibtex":null,"paperId":"60647ca320696b2d00bbc60b17d47f948aca3fbb","pdfs":[],"title":"Stress Assignment in Letter to Sound Rules for Speech Synthesis"},{"bibtex":null,"paperId":"c5d27fa0b0559a34f61b581ddd8a7bf160e3f119","pdfs":[],"title":"Stress assignment in letter\u2010to\u2010sound rules for speech synthesis"},{"bibtex":null,"paperId":"1037b3850dedde5e48ff1fdfc0a0d3cdf0d494cd","pdfs":[],"title":"Allophonic and Phonotactic Constraints Are Useful"},{"bibtex":null,"paperId":"3de07152a1e8ed61d52b3d2f266ef17cde220dee","pdfs":[],"title":"Phrase-structure parsing: a method for taking advantage of allophonic constraints"},{"bibtex":null,"paperId":"6b24cac9acef164953969c4043f5c14b25561cc6","pdfs":[],"title":"Plans, goals, and search strategies for the selection of a move in chess"},{"bibtex":null,"paperId":"7b17d71d49739f08f5ed48dbd45f78fef1ba1ab0","pdfs":[],"title":"A Finite-State Parser for Use in Speech Recognition"},{"bibtex":null,"paperId":"a0876f4589bd112e5b6e7c67580dc0ab8102ad83","pdfs":[],"title":"Coping with Syntactic Ambiguity or How to Put the Block in the Box on the Table"},{"bibtex":null,"paperId":"a42397893746da6488f70bfc0d48e66763860f0f","pdfs":[],"title":"On memory limitations in natural language processing"},{"bibtex":null,"paperId":"53fcdf6fe588981e50a110d07a8d246fd611e8e7","pdfs":[],"title":"On Parsing Strategies and Closure"},{"bibtex":null,"paperId":"bd9629da489ef8b1f5b079f176554cfe9e5aa2e5","pdfs":[],"title":"Co-ordinate Square: Solution to Many Chess Pawn Endgames"},{"bibtex":null,"paperId":"0528e7bb3e119e6ec76269fc7c33264150c53df9","pdfs":[],"title":"Feasibility of applying a computer program to handle the large amount of analytical sata received from direct reading optical emission spectrometer"},{"bibtex":null,"paperId":"216525f35945dac210f8f30f07524e8455ee02e9","pdfs":[],"title":"Discrimination decisions for l O 0 , O 00-dimensional spaces"},{"bibtex":null,"paperId":"ab1dfead0e82e57d6728475802d93ec8c57a52a0","pdfs":[],"title":"Practical Procedures for Dimension Reduction in l 1"},{"bibtex":null,"paperId":"f73a9ee4db8a2891d4eb99cbe95ee3ec338d0566","pdfs":[],"title":"- 1-Word Association Norms , Mutual Information , and Lexicography"}],"time":0.34553050994873047}