Tài liệu Báo cáo khoa học: "Joint Word Segmentation and POS Tagging using a Single Perceptron" docx

... used as training and test data for development.The standard F-scores are used to measure boththe word segmentation accuracy and the overall seg-mentation and tagging accuracy, where the overallaccuracy ... character c6space-separated characters c1 and c27character bigram c1c2in any word 8the first / last characters c1/ c2of any word 9 word w immediately before character c10character ... thestarting or ending character)12tag t on a word starting with char c0 and containing char c13tag t on a word ending with char c0 and containing char c14tag t on a word containing repeated...

... hypoth-esis, (Jin and Tanaka-Ishii, 2006) propose a systemthat segments when BE is rising or when it reach a certain maximum.The main drawback of Jin and Tanaka-Ishii (2006)model is that segmentation ... expect a de-creasing BE and look for a less decreasing value (oron the contrary, rising at least to some extent). A threshold of 0 can be seen as a default value. Fi-nally, Jin and Tanaka-Ishii ... systems than those by Wang et al. (2011) and Jin and Tanaka-Ishii (2006). A more compre-hensive state of the art can be found in (Zhao and Kit, 2008) and (Wang et al., 2011).In this paper we...

... mark (x:y) 'separated' else '?' 1.6 Bb ifdts(x:y) is local maximum then mark (x:y) 'bound' else '9' if (dts(x:y) is local minimum) and (a( ats(x:y)) ... > 81 then mark (x:y) 'bound' else '?' ifdts(x:y) is local minimum then if d(dts(x.'y)) > ~2 then mark (x:y) 'separated' else '?' 1.4 Bc ... ~'"'~}~:~'"'~: ~"should be separated and "~: ~'"'~:~'"'~: [] '"'}~: ~J:" be combined by human judgment...

... vector] as 5¢-primer and 5¢-TCTCCGTAGGGGAGACAAAAGT-3¢,5¢-ATCCCGCGGGGGAAACCTCATC-3¢ and 5¢-CTGTTTGGACGAACGCAAGATG-3¢as 3¢-primers for C53S, C175S and W88F variants, respec-tively (mutated codons ... suchas reductants and ROS. An imbalance between thesedual functions is probably associated with manyhuman pathologies, such as thyroid tumors, breast and lung cancer, Alzheimer’s disease and ... and autophosphorylationof rapeseed 2-Cys peroxiredoxinMartin Aran1, Daniel Caporaletti1, Alejandro M. Senn1, Marı a T. Tellez de In˜on2, Marı a R. Girotti1,Andrea S. Llera1and...

... kappa (Fleiss, 1971) and f-measure com-puted pairwise and then averaged across the an-notators. The agreement in group 1 was 0.76(f-measure) and 0.56 (kappa); in group 2 0.68(f-measure) and ... representationof the interpretation of logical metonymy and a more thorough evaluation methodthan that of Lapata and Lascarides (2003).By carrying out a human experiment weprove that such a representation ... -21.19play -21.29stack -21.75make -21.95programme -22.08pack -22.12use -22.23watch -22.36produce -22.37Table 1: Interpretations of Lapata and Lascarides(2003) for finish video2 Lapata and Lascarides’...

... off-line)material in foreign languages. It consistsof a hand-held scanner and sophisticatedparsing and translation software to providereaders a limited number of translationsselected on the basis of a ... which canbe as short as one word or as long as a wholesentence or even a whole paragraph.• The text appears in the user interface of theTwicPen system and is immediately parsed and tagged ... terminological help based on a full linguisticanalysis of the source material. TwicPen uses a very similar technology, but is available on per-sonal computers (or even PDAs) and uses a hand-held scanner...

... (Collins-Thompson and Callan, 2004) is based on web data that have beenannotated and indexed off-line. Also, relatedly,(Schwarm and Ostendorf, 2005) use a statisticallanguage model to train SVM classifiers ... system that performs in real time a) keywordsearch, b)thematic classification and c)analysis ofreading difficulty. Search results and analyses arereturned within a few seconds to a maximum of a minute ... gives a quick and easyway to measure reading difficulty but these formu-las lack sophistication and sensitivity to the abili-ties and background of readers. They are reason-ably good at making...

... (NIPS’10),Vancouver, Canada.Andreas Zollmann and Khalil Sima’an. 2005. A consis-tent and efficient estimator for data-oriented parsing.Journal of Automata, Languages and Combinatorics,10(2/3):367–388.21Proceedings ... Gunn, M. Nikravesh, and L. Zadeh, ed-itors, Feature Extraction: Foundations and Applica-tions. Springer.Percy Liang, Alexandre Bouchard-Cˆot´e, Dan Klein, and Ben Taskar. 200 6a. An end-to-end ... approaches thus has beenon feature engineering and on adaptations of ma-chine learning algorithms to the special case of SMT(where gold standard rankings have to be createdautomatically). Examples...

... src="data:image/png;base64,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 9A1 mTYGuyMPDg5k+oruN9dQ+ql9Lrj01H0wI6fH8ls9Qc2Z5FEJIUlLSnDlzcNBAD4nF4vHjx58/fz4uLs7b27t///6GXI7biGEVFRUVFRXV1dVxcXF2dnZ+fn4oSgEAQBAH0AsTJkyIiIiIiIig08muHf/Kv35r+/f7SW31uvXLHez7MVtKJBKFQsHj8XDQQD/xeLwpU6ZMmTLlzJkz+fn5hBCFQvH8+fM+ffoQQrCaJgCAPjPQaDStvtOUlBQnJyehUCiXy9ENA/pJpVIdOHBAoVB4enoOGjSooqJCawOpVJqZmTllyhRXV1dEGehAIiMj5XL51q1bcSgAAF4nzYrF4raOsqgRhy6Kx+OFhISEhYUZGBjs2rWLvvPnn39Wq9WEkIMHD4pEooiICHd3d6Rw6EBKSkpSUlJycnJKSkpwNAAA9ByCOHRpXC5XJBKFh4fT9eK//PJLQUGBUChk7gHoWJirylOnTuFoAAAgiAN0pAQTExNDURSOBnREdHc4/e/Y2FicyQAACOIAHSnBlJWVsedmBuhwF5MMnMkAAAjiAB0swaBTHDr0xSQjPj4ehwUAAEEcoCMlGHSKQ0e/mKTJZDJ6rR8AAEAQB+gwCQad4tChLyYZ6BQHAEAQB+hgCQad4tDRLyZpKSkpKpUKxwcAAEEcoCMlGHSKQ0dB159ER0efOHEiNTVVLBYTQlJTU/ft27dy5cqEhAScyQAA+glL3EOX9rIv9Mn/OsXpTAOg5yIiIhrfKRQK/f39sbIPAACCOIA+2rVrl7W1tZ+fX9++fXv27Lly5cqQkBBbW9tr164lJibGxMR4enpiZU3Qcw4ODs38L5amAgBAEAfQOxRFBQUFMV2JdMehra2tWCwWi8VhYWGXLl2qrKy0srLCsQIAAAAEcYBWw+Vym+lK5HK5bm5uOEoAAADQRjBYEwAAAAAAQRwAAAAAAEEcAAAAAAAQxAEAAAAAEMQBAAAAAABBHAAAAAAAQRwAAAAAABDEAQAAAAAQxAEAAAAAgGBlTQAAAIDWEh8fr9FoOm77DQwMgoKC8DoiiAMAAAB0MBqNZv78+R23/UFBQQji7QmlKQAAAAAACOIAAAAAAAjiAAAAAACAIA4AAAAA0HlgsCYAAABAO1EqlRUVFTp56h49enC5XLwECOIAAAAAXY5EItmzZ4+vr69Onv3EiROhoaHOzs54IRDEAQAAALoEpVKZnJwslUpnzpz5+eef66pb2svL69q 1a5 s2bRKJRFOnTuXz+XhpdA414gAAAABtaOvWrR4eHuvXr3d2duZyuRRFxR48Oj1w4b7DxymKavIh2blXF67+f3PC1mTnXm1yA4qizmVdXvLRP5vZiVKp3LRj56pPvygqfkgI4XK5zs7O69ev9/DwiIiIwOuCIA4AAADQmclkMg8PD6FQ+N+b94snLlgVllJzTBj6brJy4oJVJSUlWg9ZEbFl+o60uJqxB7niKV9dXvLRP7U2qHxe9fbC5dN3Xt2tfnPp8Qrv9zfkX7+ltc1Xe /a7 vvfFhju225+94bL2IHsnQqFw9uzZEokEr47OoTQF9MXFixefP3+uwwbI5XJCiFQq1e1x0Gg0U6ZMwfkAANA5xMXFrVu3jrn57+9+zLSZqjHgEA2lMrK4aD3l4MGD4eHh 7A+ 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 8A0 PdE1CoVAqlfr7+zN/nuO7VSZoGoytHGNRwf6bDZnp890niU8Ew5h7uj2/6+n5JnOTz+ePslLl1zfYyVjOLfYV7wfBgd+GfVnc7Q3mHrOa0qlvT2Q/5PTp0+vXr8drpFsYrAk6c/jw4eHDhzM3l/xj44bbtpkCr2Ibl4PcN4M27lYqleztb926/feEq4d53mUWDln8sduL+6/54hutff5j07ZVZ2uTzadeNxsZV+MatDmOrvxmZ475/xfzff3kfCuPTIHn5us2yz7e2LhtH0X+Z8Nt24zu04ttXA5b+C3akaS1n6Lih3/ddSbBUEw35mu5qHFjPvn3zrAU1anus66bjTzIfXP2lkR63Dq7MbPXfUU3JqP79E03haGrNrA3mDlzZnZ2Nk4VfUZRlEKhYK4nKYryX/aPqdGZceTNVefqxIvXnsu6rPWQ2INHPcK2bbhte0wYOv3bqz5B7zee8WDJms3ijYd2lIrCfqsRL16bdPqs1gb512/NCN8UfEAWUzH6zc3H54R9rPX3QjdmTtjHdGMick3e/CDyZNr5xhe3ru99seG2bYKh9/Rvr769cHnj/ayI2OL9f3FMY/YdPt64MdOXfkw3ZvqONHZj+Hz+ggULUlNTcapAl+Xt7S2TyZibQf5v95RfI2qK/ukpv+bt7c3efvDgQeNMHxvVVtIbcOpVYyipVr/1soVz2DsxUz72nNQgZHe3sR7frZJTr6I3MKDqnOuuz53+YgBSSUmJh4cHXh0Eceii5HK5ra0tu2wuv5KvJlz6LUOj0RQI3GJ+TGQ/ZO/h04+sREStpn/UxFDylGKHBoqi0mXlKkMLZieynhOTkpLYO9l/NOWKyQiNRkNvozK0uFxuopU8lEplZnEtuzE3TZ21kkRswq+FNq7sxmQW12o3Ju8muzGFNmO+iW/QmKTfMiVGw5jG1HF4eUprduJ3dnbWbaUv/KG0tLRp06YxN4/+duG0ZkSZ+QCNRqMytMiwefvLPfu1HnLk9O/5lu5qAy7RUArTPhfMJmhdbmXnXjn4RHjTeLCacOmd7Dn4q9ZONkbtOs4dp+D30Wg0Tywdj9U5J6Vmam1z5mxGsmoo05hMi8laZyAhJOF4qlZjTp3P1grZ+4osrpuOZBrzw5EUrZ1s33PwpOkUpjFHKJcLFy4w/0uXoqpUKpwt0DW5urrGxcUxN6eLJ+58132m+lzPioJATvrOd91dXV21HhIfHblepHCvTveQn9kw/Nnh76O0NpjoNnrHHOeptb/3rCiYWvv7597dP1w8T2ubr/7f2o8GlIytvTxMKZlvLt0VsZT9ddbBgwfHjx+PVwdBHLqopKSkwMDAF7k28eQdk6HMxT1RU3Uck/PZlxumk8tMOKZ/8jV2p85nsWJHusRwGHsDNeE+ePCAvZPk384y4Zj+uckXsUMDIeTU+ax7RgO0GqM1m0p63g2txtwzGnD45Iuwnn7pag7XUasx6dm57J0cOnqiytiGvc0do4Hxx9LY2zg5OWl1xoNeSU9Pd3BweHG5GLdf6zVNU/RkfxOSf/3WWZU9e4MqY5vTp083uOZMTK7kCZnLPKJWn1X1Z89NJpfL8yv5 7A2 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 2a8 vl8FztLXk05M4LKsTLbz8+Pvc8PggOHVEuZnXDqVU4WKvZ3MlwuV+xsx4zlImqqT/mVkABfrbYtCpxh+yyb2caottK1txE7H9P7YTfG4cm5RQ3/rMIWvuNYmc1ujCMpZE8QxOVyvUQNGtPt+V2tC9fDhw9j1hQA5k+mCz41vPRF2bBhQ6vv9O7duz179jQ3N1epVFjNAV5m2LBh27dvHzt2rJGRESFklNPQBT7uRg8uOlAPvvko8L3gOdpXjRzObL9p8zwGklup73sN2rbm/cEO/bX7GxyHLHp7nPH9jB7lkh3vvb1mxRJjY2Otbeb4T5/S37ji8gm/wUY7VoVMmTyucdtEQxwW+LhzCy85UA/+/d60FYsXcjgcrcYEvO09z2MgufX7B54Dtv0zvHFjhg3sv+jtcUYPLvYol3z2rk/EX5c22Zg3B/ArLp/w6c+NWb 2A3 RiZTJaYmBgQEIBTRZ+Zm5vHx8dPmjSJvikQWLjaCeSZCZWVlU6au+++Yb7x43Ctk8dr3BiLZwWGJXlc5TO/HqUb3589cECDk8fUlD+4l0WNJPmp/Hn/uvuzbZ9/EfGRqWmDak7XkU4mhVmq25nVdWRiTcY/5op93pyk1TaBwGL84O6lFw5UVlaKavIXj7bcsOoD+s+NMdndxabqnvrW7 4a1 lVOtnny+cq7j0AbThhoZGYnselRdPUE35i/Wj/6zeb1WY 8a+ 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 8a9 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 9a9 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 7A/ fuEX9lBXKlU5pbzFPy+REOIRl1l3P1svWvuVYnr6DfoDZydnVetWtUOa1oDgjh0HlKpdM+ePfTa3dbW1n5+fs3XZDffh21sbMykcEKI1oKaPB6P/b80Nze36OjoTz75ZM2aNS+rzRUKheHh4UuXLsWATmhG40Lwjz76yNHRUYdnCI/HE4vFnp6eaWlp7DiOkQ8Ar0wul4tEIubvWqlUXpabaASEaNT0PRpC7lcaKJVKpvjkm/jDpRYDmQ0IIeVm9seOHaM7leh3jxTJA7VFf6KhmG3yVN3Yfbf7j6bkEzv2BpW8Xt8eOM4EcUKIr69vM1+UAYI4wH+pVKoTJ0789NNPzEDMP4wsFEV9/PHHOTk5TVZ1N+nu3bstaYxIJNq9e/fixYtjY2MfPHjArnVpnGnEYjEzoJOeoeIPLx6gK5zPWoXgQUFB+jMJJpfLbRzHxWLxkiVL8IEN0Ao0Grqrm30X+4aJIYdbX6M2fPHJYqCuEwgEzM 3a2 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 3a2 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 8A3 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 8a8 vDz2Y+/cK2rmYGo0msKih4VFD5vfM30aN6O+vl7rJM/Ly4uKijp9+nTzD0xMTIyKirpz5w57V3/YHmnBzaelZa/Z5urqavaLVV9fn5eXt2rVKolE0sIzfOPGjadPn2Yf3od37pz6/vvmz/Bftm49FR/fzItSrVCcjo9v/gzPy8rKy8rS2nNiYmILz3Do3MrLy/fs2bNx40b2X5YOW6L1N/6ajh079umnn+JV1hN3796Ni4tr8r9++umnDv2rzZs3D68vky7aIcqiNKWVSaXS58+fMx2cpc/Klq1af0E9RGFmO6K+wLWX4X8+Xa3VXbppx7dH80vzDIcZ11VOML63zP9NP+9J 7A1 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 1a+ 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 ... src="data:image/png;base64,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 9A1 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 1a5 s2bRKJRFOnTuXz+XhpdA414gAAAABtaOvWrR4eHuvXr3d2duZyuRRFxR48Oj1w4b7DxymKavIh2blXF67+f3PC1mTnXm1yA4qizmVdXvLRP5vZiVKp3LRj56pPvygqfkgI4XK5zs7O69ev9/DwiIiIwOuCIA4AAADQmclkMg8PD6FQ+N+b94snLlgVllJzTBj6brJy4oJVJSUlWg9ZEbFl+o60uJqxB7niKV9dXvLRP7U2qHxe9fbC5dN3Xt2tfnPp8Qrv9zfkX7+ltc1Xe /a7 vvfFhju225+94bL2IHsnQqFw9uzZEokEr47OoTQF9MXFixefP3+uwwbI5XJCiFQq1e1x0Gg0U6ZMwfkAANA5xMXFrVu3jrn57+9+zLSZqjHgEA2lMrK4aD3l4MGD4eHh 7A+ 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 8A0 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 7A2 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 2a8 vl8FztLXk05M4LKsTLbz8+Pvc8PggOHVEuZnXDqVU4WKvZ3MlwuV+xsx4zlImqqT/mVkABfrbYtCpxh+yyb2caottK1txE7H9P7YTfG4cm5RQ3/rMIWvuNYmc1ujCMpZE8QxOVyvUQNGtPt+V2tC9fDhw9j1hQA5k+mCz41vPRF2bBhQ6vv9O7duz179jQ3N1epVFjNAV5m2LBh27dvHzt2rJGRESFklNPQBT7uRg8uOlAPvvko8L3gOdpXjRzObL9p8zwGklup73sN2rbm/cEO/bX7GxyHLHp7nPH9jB7lkh3vvb1mxRJjY2Otbeb4T5/S37ji8gm/wUY7VoVMmTyucdtEQxwW+LhzCy85UA/+/d60FYsXcjgcrcYEvO09z2MgufX7B54Dtv0zvHFjhg3sv+jtcUYPLvYol3z2rk/EX5c22Zg3B/ArLp/w6c+NWb 2A3 RiZTJaYmBgQEIBTRZ+Zm5vHx8dPmjSJvikQWLjaCeSZCZWVlU6au+++Yb7x43Ctk8dr3BiLZwWGJXlc5TO/HqUb3589cECDk8fUlD+4l0WNJPmp/Hn/uvuzbZ9/EfGRqWmDak7XkU4mhVmq25nVdWRiTcY/5op93pyk1TaBwGL84O6lFw5UVlaKavIXj7bcsOoD+s+NMdndxabqnvrW7 4a1 lVOtnny+cq7j0AbThhoZGYnselRdPUE35i/Wj/6zeb1WY 8a+ 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 8a9 du9Z4Vx9++OGRI0dyc3Nzc3Pp/fj6+qIEFtqNSqW6cOFCTExMWVkZIUQsFmdlZVVWvlgF84svvtAqnRKJRCtXroyKimLfuXbtWgcHh48++ggTewMAIIgDtAm5XH7kyJGkpCQ6tbi4uISGhtLJIzc3VyuI09Xh7Ht69uz55MkT5qa9vb2fn5+fn19JScmpU6diY2OjoqKioqICAgKmTZvG7k0HaKOTOTY2lr65aNGit956SygURkdHM5Xi0dHRTZ6H/v7++fn5KSkp9M3PP//85MmTKSkp4eHhDg4Oy5YtGzNmDKbIBABAEAdoHVKp9PDhw0zyWLRo0YwZM5iewh9++IEONIaGhvX19fSdjce0aUWT+/fvr169esuWLUKhMDg4ODAwkO6bTExMTExMRKCBNiKTyeLj4+mTufH3MF5eXnQQ/+yzz5rp3l67du3du3dlMpm1tbWrq6urq+uSJUt27dqVkpKyZs0aa2vrsLAwT09PnL0AbU2pVCYkJDx48ECHbbCzswsMDGxmQQBoZ1jQBzoJrS/uG4djiqL+ 9a9 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 7A/ fuEX9lBXKlU5pbzFPy+REOIRl1l3P1svWvuVYnr6DfoDZydnVetWtUOa1oDgjh0HlKpdM+ePfTa3dbW1n5+fs3XZDffh21sbMykcEKI1oKaPB6P/b80Nze36OjoTz75ZM2aNS+rzRUKheHh4UuXLsWATmhG40Lwjz76yNHRUYdnCI/HE4vFnp6eaWlp7DiOkQ8Ar0wul4tEIubvWqlUXpabaASEaNT0PRpC7lcaKJVKpvjkm/jDpRYDmQ0IIeVm9seOHaM7leh3jxTJA7VFf6KhmG3yVN3Yfbf7j6bkEzv2BpW8Xt8eOM4EcUKIr69vM1+UAYI4wH+pVKoTJ0789NNPzEDMP4wsFEV9/PHHOTk5TVZ1N+nu3bstaYxIJNq9e/fixYtjY2MfPHjArnVpnGnEYjEzoJOeoeIPLx6gK5zPWoXgQUFB+jMJJpfLbRzHxWLxkiVL8IEN0Ao0Grqrm30X+4aJIYdbX6M2fPHJYqCuEwgEzM 3a2 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 3a2 vrTTz9teTu1plxsYU8/dMRLSvZcOvpQCP6alxNaRe34VgdAS5PziG/atElr+sLPYvbcKX4ysG/PNWGhL5l58Mq//vONEd9ixaJ548aMbPymUVT8cMMX0fml9YN6mK9c6Mcu/mbefxKOJP+QdLrGgOflbL/6g1Cm3x3TF7YwFWD6QuhCeaWgoIA9EPMV5jNufmhmGwVx5oGEkMZTqTTvFWrfoaPQenH1rRD8NeM407uPOA7QkiBOz6YlEAh8fHxat8+Foqg//Mhgb0Mv6PPgwYOlS5c22RIE8XYO4ihNAd3nlYSEBGY1HBcXl9DQ0D8bRl9haGYrEovFvXr1Cg8Pb2YqlSbxeDx/f39/f39mNpjw8HB6QCemjeu4tL7V6XyzjtDDHpYsWbJr166UlJTw8HDEcYDm0bNpKZXK5OTkoqIiR0dHnTSjoKCgX79+WOJeryCIg840Xh/+1coz2npoZgujyaFDh/5wKpVmHr5161ZmJB8GdHaCU7rTr+gkFAojIiK04nhQUJCnpye+0gFoEp/P9/f3VyqVFRUVOmmAl5cX/jwRxKGro+du0xqI+cof3u0zNLMlrKysdu/eHRkZ2ZKpVF62B3pAJz1QFQM6O4pOVgj+anGcWcSKLjxFHAdoJo6jQxoQxEEHtL6yDwgImDZt2utUzb7O0Mw2yuJ/aiqVJtHTxonFYmbqRroAHQM69fOqsrMWgv/ZOE4vYpWQkBAbG4s4DgDQQhisCW1Oq7/w1QZiNvaaQzObPG9fbbDmy9r2Z6dSaUnUe7Uaemjrq0osP8k+Y+k4Tv63/C0GPOi/L7/8csWKFTgOraLJwZodCAZrslMBBmtCx0YXPWsNxHz90KzboZktERwc3Ldv38jIyPDw8Ne8TqAHdM6YMYOZVYb+xVvlYgZeQZcqBH+1MzY4ODgwMJCO47RFixYhjuutjRs3njt3DkEcQCcQxKHNwwpp1f7Cthuaee3atVY8AsxUKuHh4X9qKpUmcblcekAn0xEbFRUVFRXVZWsh2l9XLgR/5ThOD3iIiYlBHNfnFC4WiwcNGoRDAYAgDh0ePRAzJiaGmRh72bJlY8aMaa2wIpVKP/nkk7KyskWLFs2fP791M1CrD2NnT6VSUVHRKmNJhULhywZ0oh637c5qrUJwrCvZ8gtIsVjs6empFccx2kGvUvj48ePv37+PowGAIA4dmNZSkQEBAbNnz27dz1pm2GJERIRYLO4Qh4WZSiUxMfH+/ftbtmxplazc5IDOyMhIRJzW1bgQHB26rRXHcT2jPykchwIAQRw6qsYDMduiZJaiqLi4uNYa/viH0bnVd8hMpRIYGNi6Re0ODg4RERGrV6+mF0WiI05r1eJ3ZY0LwfGFQ2vF8YKCgu3bt9Nf5iCOI4UDIIgDvApm9Rn6ZtutPtPOQzPbor+Ty+Vu2bKFvpZYvHjxF1980bpV3Uw9Lh1xMKDzdU42uuaHXQiOS5rW/VsQiUS7d++WSqXsOI6hDkjhAAjiAC3CrMdO/jc9WdtN3CaXyxcvXlxWVubi4tJadR26yh/BwcEWFhZRUVGLFy9urSkXm4w4WgM6X3++9q6AnnSPmeEHPbVtrXEcx2UPUngXocOVNS0tLbGWEII4dOCkwh6y1g6zRrTp0Eyd8Pf3Hzx4cGtNpfIy9IDOwMBAegXTxMTExMTEVh8422mUlJTQq0LSN1EI3v5xnBnqEB4ejjiOFN6JURSVmpp64sQJX19fnTSAfurx48cjjiOIQ0fCfEwySaUdRgR2xKGZLUwe+/btW758eStOpdIkHo9HD+hkyp3pVUix9Az7So/93Q4KwXWFHuqwZMmSXbt2IY4jhXdKcrk8KSlJoVBMmzZt27ZtumrGlClTZDLZrl27BAKBj48PvvRDEAd9v3bXqpcNCgpqh7VL2nNopk4IhcLdu3evWrWqdadSaSb6i0QiDOhs5sRG5tOTvwutOI6rI6TwTmPTpk2RkZFMP3Tl86odu346e/bspEmTVr8X3Lh/mqKoo79d2PPzUUJIoK9n4F98Gv8VKJXK/UdTEn89Pnb0yCZ3QggpKn64YetXZeXytSuXuY4eSb/jhYeHK5XKrVu3rlu3Dn9cOocl7qEJWrO2td1AzCZDkq5WzYyMjExJSUlNTW23ONj+v2njWW661IBOFIJ3xLcgxPF2SOHx8fFBQUE4UK2i8RL3EomEEOLs7EzfzM69umTrfqn1JDXHmKOuFZWd/WltEPO/tIUr1x6pGqIwsyWEmKmeTDO8eiBmi1bCDlz9+WXLiSpjK6P6Kpeqi1+uDnZxHsreZtWGz3+SmTy1HK4x4AiqCsdVnDnx808vaxUDS9yz02w7LHHPwYEGdkqTSqWrV6+eN28e3SG9cuXKEydOREREtE8Kl8vlgYGBOTk5Li4uCQkJnfsqjp5KZdGiRWVlZYsXL6aTcTs8qZub2+7du/ft2xcQEFBWVhYVFeXr6xsdHV1SUtK5g110dLSvr29sbCw96oA+sZHC9RM9zuHEiRP0H0hkZGRgYGBKSgpFUTg4rZ7Coa2lpaUNHz6cuRkVu19iPVltwCUaSm3AlVhPTktLY29f+qzsUmU3Bb8vUauJWl1l3P1Mlb3WZ8Q38UkXraeojCyIhqrj8jIFk3fs3KP1gZ5+V/7E0lFDNERDKUz7ZJmPy869wmwwfPjww4cP49XROZSmACGNegrpuoV2Xr5b50Mz5XJ5+2fxtp5KpZmgEx4evnTpUnol1E48oBOF4B0XPS9nYGBgQkJCbGwss2oVRtMihXcgcrlcIBAw7zlKpfJmtamGpyGa/15Vagi5X2mgVCqZ2pKvfzh4kzeU2YAQIjfte+7cOWbyK4qi0q8Xq3n9ifrFNpcVxuydHP3tvMRwGHuDclP7vYnJrqPfYD6ARCIRKhcQxEH3MYVZuIS010DMxvRhaCad1dofeyqVlStX+vv7t2fQaTygs62npGwfKATvlHGcGeSAOI4U3oH07duX+XdNTU1VTR0xbvDdzo3Hzxs+QkPUakJY26jVCoWCuVVbW1ulMWKHbELIU8q8oqKCCeK37xbWcnjsbTSEPH1Wxn6IhYVFWVkZgjiCOOiASqWi57ZjD8TUSU8hRVF0j6y1tXWrr3TTUTBTqURFRVVWVrb/FwL0gM4VK1YcOXKEyTrtOTagdc9t9tc7AQEBs2fPRglK54jj8+fPT0tLi4mJQRxHCu8orKysTpw4MWXKFOamk4Uyn5WPDTTqsd3r2EMtFwXO+Paj74q7vfFiJ8/vT5s2g7nJ5/OHmFZn19VrDF4UGI8zK2G/0YW88/auC99c5754AzerKQ2aN43dtoyMDKZhgCAO7URrIKZuV3tRqVQRERE5OTkODg7btm3rytflzFQqsbGxeXl5Olm9yMrKis469IBOepkVupyjHWbLaZVzm5kR3NraGimt8+FyuWKx2NPTkx3Hca2FFK7nQkNDJRIJMyzy3cAZF75OeWjprDHgGGjUfSokM8PfYW/fr28fr57VhyofV5l0J4Tw6hST+IVaH9Mr352X+tlheieEEOuqezP8JrM36G5jPYJffq+mXGUkIIRw1HVvVJyfLg5hNpDJZN7e3nh1EMShnejhdBl6uGqmbicst7Ky2rlzJz2VyrJly3R1ZUIP6HRzc2NyLV01pM9xh10IrsOvd0AncZwe4YA5cJDC9dbw4cNjYmKYIO7jNfGQpUXUj0k3yynnnkbvfTCz8dQle/6z+e0jyT8knVarqkLnzAyc8bnWBq6j3zi0hmzdGZdfYeRkWbfkg 8A3 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 8a8 vDz2Y+/cK2rmYGo0msKih4VFD5vfM30aN6O+vl7rJM/Ly4uKijp9+nTzD0xMTIyKirpz5w57V3/YHmnBzaelZa/Z5urqavaLVV9fn5eXt2rVKolE0sIzfOPGjadPn2Yf3od37pz6/vvmz/Bftm49FR/fzItSrVCcjo9v/gzPy8rKy8rS2nNiYmILz3Do3MrLy/fs2bNx40b2X5YOW6L1N/6ajh079umnn+JV1hN3796Ni4tr8r9++umnDv2rzZs3D68vky7aIcqiNKWVSaXS58+fMx2cpc/Klq1af0E9RGFmO6K+wLWX4X8+Xa3VXbppx7dH80vzDIcZ11VOML63zP9NP+9J 7A1 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 1a+ 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 ... src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAA9gAAAFXCAIAAADWMXECAAAACXBIWXMAABYlAAAWJQFJUiTwAAAgAElEQVR42uzdeVxTV/438EPCkrAEBJe4AIorErSKCLhCI0WqI0IVFRWwLm1RnHZ0purgr1Z5nNrq6EBLW6tF24KKLYp1wYVCXQBBUEkQ17gAiooQgpCw3OT5485cLwEpVSABPu8Xf5h4c3O4uSSfe/I95xhoNBoCAAAAAADti4NDAAAAAACAIA4AAAAAgCAOAAAAAAAI4gAAAAAACOIAAAAAAIAgDgAAAACAIA4AAAAAAAjiAAAAAAAI4gAAAAAAgCAOAAAAAIAgDgAAAACAIA4AAAAAAAjiAAAAAAAI4gAAAAAAgCAOAAAAAIAgDgAAAAAACOIAAAAAAAjiAAAAAACAIA4AAAAAgCAOAAAAAIAgDgAAAAAACOIAAAAAAAjiAAAAAACAIA4AAAAAgCAOAAAAAAAI4gAAAAAACOIAAAAAAPA/hm2035SUlKKior59++IQA8DLxMbGLlq0CMcBAAD0TXFxcUhISFs/S5v0iKekpJw7d87c3ByvIgA0w8rKCgcBAAD0kEwma4dnaasecWdn53HjxgmFQryQAPAyGRkZkydP5nA4HA7K5AAAQI9IJBKKojgcjoGBQccL4jSNRkNRFF5LAGj6DcjQ8NGjR3w+H13jAACgVwwMDOhPKBsbmw4ZxDUajVwuR4EKADTzLkH3hWs0GhwNAADQKxwOR6VStelTGLb172BoaIgXEgCaVF9fz+FwuFwu3igAAECvaDQaAwODtu4nQl0mAAAAAIAOtG1pCg1HGQDwRgEAAKAFPeIAAAAAADrQtj3iBGOwAAAAAADaOYgDALTwoh1X7AAA0AWhNAUAAAAAQAcwWBMAdIZ5i8AbBQAA6NsnVDs8C3rEAQAAAAB0AEEcAAAAAEAHUJoCADqGNwoAAOia0CMOAAAAAKADbdUjjjFYANDy9wq8UQAAQBeEHnEAAAAAAARxAAAAAICuoW1X1sQ3zgDQ/FuE1j8AAAD06hOqTaFHHAAAAABABxDEAQAAAAB0APOIA4Au4Y0CAAD08+OpHZ4FPeIAAAAAADqAHnEA0DG8UQAAQNeEHnEAAAAAAARxAAAAAICuoW1LUwimBwaAZt8l8EYBAABdFnrEAQAAAAAQxAEAAAAAugbMmgIAOoY3CgAA0MPPpnZ4FvSIAwAAAADoAHrEAUCX8EYBAABdFnrEAQAAAAAQxAEAAAAAugbMIw4AOsO8S+CNAgAA9PATqq2hRxwAAAAAQAfasEc8NTV1wIABKpUKRxkAmnTnzp179+7V1dXhjQIAAPRKeXl5Bw7iEyZMEAqFxcXFHA463QGgaWPGjCGEUBTF5XJxNAAAQH/U1NR04CBOMzAwwOcrADQPQRwAAPQNh8PhcrltXSnetkHc1NTUysoKryUAAAAAdCCWlpY9e/aUy+VtG/dxoAEAAAAA2h+COAAAAAAAgjgAAAAAAII4AAAAAAAgiAMAAAAAIIgDAAAAAACCOAAAAAAAgjgAAAAAACCIAwAAAAAgiAMAAAAAAII4AAAAAACCOAAAAAAAgjgAAAAAACCIAwAAAAAgiAMAAAAAAII4AAAAAACCOAAAAAAAIIgDAAAAACCIAwAAAAAAgjgAAAAAAII4AAAAAACCOAAAAAAAIIgDAAAAAHQ2hjgEANCe5HL59evX+/fvz76ztLTU0dGRy+Xi+AAAAII4AEArk0qlqampAoHAx8dH6780Gk1MTIxAIPDz87OyssKxAgAABHEAgFZAUdQ//vGP0NDQsLAwutuboqj0nDyeIcd19EhCiFAodHZ2lsvlSUlJAoHA398fBw0AADo91IgDQJvLzs4ODQ11dnamU/i+w8ffXrh8+s68qdGZc8LW5Ehv0JtZWVmFhIQUFRVRFIWDBgAACOIAAK/rzJkzzs7O9L+VSuWOo7mnbN5R8PuUmTskcMUR/97J3tjT0zM7OxsHDQAAEMQBAF5LSUmJu7s7c3P/0ZQ8zmCioZifdOKYnXuF2cDZ2fnnn3/GcQMAAARxAIDXIpVKRSIRczP5t7MqQwuiVjM/z427B0X+yH6Is7OzSqXCoQMAAARxAIBXJxKJpFIpc3PsqBFGtZVETTE/5tUl3388n/0QiUTC4/Fw6AAAAEEcAODVCYXC5ORk5mbYwneGKCXs0hQXw/vjxoxkp/DQ0FAcNwAAQBAHAHhds2bNkkgk9L/5fP4H4uEe5ad5NeWCqqKpNWl/nevDXsonLS3N0dERBw0AADo9zCMOAG0iOjra0tKyb9++AwYMGDx48Ndff11VVeXq6srlcpe/G/R+yJwffjlmbTVguvgDJoXT84j369evsrJSpVLl5+cXFxcPHTrUzc0NxxMAADofA41G0+o7TUlJcXJyEgqFcrkci+QBdE0URQUGBpaVlTH32Nvbm5iYuLm5BQQEaL0zSCSSffv2qdXq2tray5cvM/cvWrQoODgYBxMAANpZSkqKWCxu6yiLHnEAaBNcLverr76aN28ec8/9+/cJITdv3kxKSqLvGTduXHp6OiGkvr6+urpaaw8ODg7z58/HkQQAgM4KQRwA2opQKHRwcJDJZFr3KxQKQkh0dDQ9oUp4eHiTD//oo4/YteMAAACdDAZrAkBbUalUb731VpP/RadwQohIJIqOjm68gampae/evXEMAQCgE0OPOAC0spKSkoyMjKNHjzbuCyeEWFtb7969m11yR2dxrX7x6urqWbNmOTg4TJ48ecKECQ4ODjiwAACAIA4AoI2iqPv3758/fz4pKYkZoOni4uLr6/vjjz/S1eFNpvCXZfHQ0NDCwsKUlBSZTBYbG2ttbe3p6enl5eXo6Ih6FQAAQBAHgK5OpVJdvXo1KysrMTGRuTMgIGDs2LEjR46kV8e8du0aHcRdXFwiIyNftmSmVhb38fERCoVr164tKChITU1NS0tLTEykn0UsFnt7ezP7BwAAQBAHgK5CLpfn5OScOHEiJyeHvsfa2trPz2/ChAn29vZN9li7uLhs2bKl+c7sxv3iXC5XJBKJRKLw8HCZTHb+/Pnff/89JSUlJSWF3uf48eO9vLwwTSoAACCIA0BnxkRhpvjbwcFh+vTpzUfhioqKgICAsLCwlpSUNFkvzjyXg4NDcHCwXC5PTU29cOFCTk5OTk5OVFQUSskBAKAjwoI+ANAciqLo4hB28cmfKg65ePHin10aUyqV9uvX7w/fPejCmNOnT9Md5IQQlJIDAEBrpdl2WNAHQRwAmiCXy2/cuHHw4EF28YneZlzmaiEtLY0ZKopScgAA0PMgjtIUAHhBJpNdvXqVPfMgXXwycuRIfa76aL6UvCX1MwAAAO0PPeIAXR3dnZybm6s18+Ds2bOHDh3acf+E2aXk9D3MiFKUkgMAwB+mWZSmAEBbaVxgTQgJCAjw8vIaNGhQZyrnaOY3RSk5AAAgiANAO6H7ibWKT7rIlCPN9P2jlBwAANo/iKNGHKDze9myl11tEm6mlDw4OJiphqfnQCQoJQcAgHaHHnGATkulUt2+fVtr5kGtZS+hmcWJUEoOANBloTQFAFo5Wb5s2Usg/yslz8rK0rpuQSk5AACCOII4ADTnZcteenh4CIVCHJ+WQyk5AACgRhwAWhQZtRayQWR8TS0pJcflDQAAvD70iAN0PB1r2ctOc8xR8AMA0HWgNAUAGigpKcnIyOhwy152Ms2Ukney+dcBABDEEcQBurSX1Sv7+vq6uLjg70sPX5qOviIpAAAQ1IgDdGVdZ9nLjotdSs58WYFScgAAaDn0iAPoEXrZywsXLmBO6477CjYu30cpOQBAh4MecYCugp55sIsve9k5WFlZubm5ubm5sVdTio2NjY2NJfhOAwAAGkKPOIBuYNnLLoKiqPv37ze+0EIpOQCAPkOPOEAn9LJZ8EaPHo2ZBzslLpfr4ODg4OCAUnIAANCCHnGA9sCsC4NlL4G8vJQc12MAAHoCPeIAHVszy16iJqGL+8NSclQoAQB0BegRB2hl9MyDWPYS/uxlW5Ol5JgwHgBAJ9AjDtCRNLns5eTJkzHzILRES0rJsYQqAEAngyAO8Oqw7CW0BaFQ6O/v7+/vz/52JSoqiqCUHAAAQRygi6PjUVZWltbMg5giGloXj8ejS8mZ8QYoJQcA6ExQIw7QUs0se4lFE6HdNLn8E76EAQBo9TSLGnEAfck9v//+O1P8jWUvQYeYUnL6yhCl5AAAHReCOEATmlz2UiwWe3t7oxIA9ISVlRVTSp6dnf3DDz/cvn2bLiUfM2bM1KlTCSH0l5M4VgAACOIA+g7LrECHI5PJjh07JhAI1q5da2Jicvv27czMzEGDBjk5ORFCpFLp1q1bQ0NDcQIDACCIA+gjqVT6+PFjiqKioqKqqqoIIX369Jk1axa+4gc9Fx0d7ejouGTJEj6fT9/z8HGpha3j22970/cIhcIpU6ZIJJLNmzevW7cOWRwAAEEcQC9QFJWWlpaenu7t7S0WiymK4nA45ubmw4YNS0pKKioqGjx4MI4S6C2VSiUQCKZMmULflN0vXrslOu1573ILh5jkre42qm+3bqSTt7OzMyEkOzvb3d0dxw0AAEEcQMf27t2rUCimTZsmFovpe2pra8ePH0/3I4aEhFAUlZ2dvWnTJn9/f5FIhCMG+ub8+fM+Pj7MzU+2fpnAFRNLQgjJt3QvrCgMuZQ30W0U/b/Ozs6RkZEI4gAACOIAOiaTyfr27RsSEkLfLCp++M2+IynSIoPa575jHT9cssDC3IzL5bq7u7u7u2/atAlBHPRQcnIy0x2uVCovy02IgGL+t5In3PnTASaIE0Lc3d1LSkowdhMAQH9wcAigCzp27JiXlxdzM/hvG/51zy5T4JnRffqG27bBf/uUvfHMmTOlUikOGugVuVw+fvx45uap81n3jPoTDcX8aIim9Hkt+yEikQhnMgAAgjiALtGVtcyotezcKzlmbmrCJWqKqCk14Z6t6Z9//Raz/fDhww8dOoTjBnrFysrqwoULzM23JoztX3OHPofpHwOqrruZEfshJ0+eHDNmDA4dAACCOIDOnD9/fuLEiczNvYknKk16sROMnN9n36+nmQ24XK6dnZ1cLsehA70ya9YsiURC/5vP57v3NTGg6olaTf9YVD9c+e48ZmOKohQKBZagAgBAEAfQJaFQ+OTJE+ZmL5tuBuo6olEzP1yqtpulgP0QhUJhYWGBQwd6xdXVNS0tjbn52cdhs7kZQ+pumakee8hPrx5t4Dr6DeZ/r127xi7HAgAABHEAHRCJRKdPv+jw/iA4sHd5HrtHfEi1JGzhO8wGcrmcXcoCoCe4XO7w4cOjo6NlMhkhpLuN9YFvvkiJnB+3YGjK3q3rP/qA3kypVB46dCgtLQ1jjgEA 9A1 mTYGuyMPDg5k+oruN9dQ+ql9Lrj01H0wI6fH8ls9Qc2Z5FEJIUlLSnDlzcNBAD4nF4vHjx58/fz4uLs7b27t///6GXI7biGEVFRUVFRXV1dVxcXF2dnZ+fn4oSgEAQBAH0AsTJkyIiIiIiIig08muHf/Kv35r+/f7SW31uvXLHez7MVtKJBKFQsHj8XDQQD/xeLwpU6ZMmTLlzJkz+fn5hBCFQvH8+fM+ffoQQrCaJgCAPjPQaDStvtOUlBQnJyehUCiXy9ENA/pJpVIdOHBAoVB4enoOGjSooqJCawOpVJqZmTllyhRXV1dEGehAIiMj5XL51q1bcSgAAF4nzYrF4raOsqgRhy6Kx+OFhISEhYUZGBjs2rWLvvPnn39Wq9WEkIMHD4pEooiICHd3d6Rw6EBKSkpSUlJycnJKSkpwNAAA9ByCOHRpXC5XJBKFh4fT9eK//PJLQUGBUChk7gHoWJirylOnTuFoAAAgiAN0pAQTExNDURSOBnREdHc4/e/Y2FicyQAACOIAHSnBlJWVsedmBuhwF5MMnMkAAAjiAB0swaBTHDr0xSQjPj4ehwUAAEEcoCMlGHSKQ0e/mKTJZDJ6rR8AAEAQB+gwCQad4tChLyYZ6BQHAEAQB+hgCQad4tDRLyZpKSkpKpUKxwcAAEEcoCMlGHSKQ0dB159ER0efOHEiNTVVLBYTQlJTU/ft27dy5cqEhAScyQAA+glL3EOX9rIv9Mn/OsXpTAOg5yIiIhrfKRQK/f39sbIPAACCOIA+2rVrl7W1tZ+fX9++fXv27Lly5cqQkBBbW9tr164lJibGxMR4enpiZU3Qcw4ODs38L5amAgBAEAfQOxRFBQUFMV2JdMehra2tWCwWi8VhYWGXLl2qrKy0srLCsQIAAAAEcYBWw+Vym+lK5HK5bm5uOEoAAADQRjBYEwAAAAAAQRwAAAAAAEEcAAAAAAAQxAEAAAAAEMQBAAAAAABBHAAAAAAAQRwAAAAAABDEAQAAAAAQxAEAAAAAgGBlTQAAAIDWEh8fr9FoOm77DQwMgoKC8DoiiAMAAAB0MBqNZv78+R23/UFBQQji7QmlKQAAAAAACOIAAAAAAAjiAAAAAACAIA4AAAAA0HlgsCYAAABAO1EqlRUVFTp56h49enC5XLwECOIAAAAAXY5EItmzZ4+vr69Onv3EiROhoaHOzs54IRDEAQAAALoEpVKZnJwslUpnzpz5+eef66pb2svL69q 1a5 s2bRKJRFOnTuXz+XhpdA414gAAAABtaOvWrR4eHuvXr3d2duZyuRRFxR48Oj1w4b7DxymKavIh2blXF67+f3PC1mTnXm1yA4qizmVdXvLRP5vZiVKp3LRj56pPvygqfkgI4XK5zs7O69ev9/DwiIiIwOuCIA4AAADQmclkMg8PD6FQ+N+b94snLlgVllJzTBj6brJy4oJVJSUlWg9ZEbFl+o60uJqxB7niKV9dXvLRP7U2qHxe9fbC5dN3Xt2tfnPp8Qrv9zfkX7+ltc1Xe /a7 vvfFhju225+94bL2IHsnQqFw9uzZEokEr47OoTQF9MXFixefP3+uwwbI5XJCiFQq1e1x0Gg0U6ZMwfkAANA5xMXFrVu3jrn57+9+zLSZqjHgEA2lMrK4aD3l4MGD4eHh 7A+ jtPuqJ1ajCNEQQhSmfZIfPywpKWGiPCFkx3c/pVpOrTM0JWqqysQmTTP+s6++/zH6X8wGFEX9lJqXb+lJf648sXQ8VG700fVbTsMG0xu4urrGxMSgXhxBHLo6lUp1/vz55OTkkJAQe3t7nbfH3d1dt4PK8/PzIyMjZ86cKRKJcHp0LCUlJSdPnuzbt69um/Ho0SNCyJkzZ3TYhsrKSgsLiwkTJvB4PJwY0JUplUo7OzvmY0WpVOY8qNBYaIjmv8UkasK98biKoihmm90Jx26aioj6RbXJI0unkydPhoSEMPek592oM7VjttEQclNpqlQqmbLv9EtXr3EGsHci5/f9fn/itg0f0ze5XK5AIGA/BBDEocuJjo4WCAQ+Pj5MH7BSqayqVnW36dbMo7Jzr4ochzTz3kFRVGVlpZWVVTM7kcvlFhYWWpn7nXfe0XoDbZ/GKJVKY2NjujFCodDT05MeT+Pt7e3u7o7zRM9RFFVQUHD48GEnJ6fAwECdf6qNGTOmsLBQ5x1dJSUl3333HSFk9uzZ7J48gC6loqJCIBAwN2tqagprTYlazd6msNaU/TFRXiGnSB92htZoDBQKBfsjo7DOQmsn95T8iooK5v0nLT3ruXEv9jZqYlj0+Bn7IUOHDr19+zY6xRHEoYuSSqWenp7MW0Dl86odu346fuVBYZ1gvGX5/61czHyDxth3+HjC8bSzdQMHGR6d6GC1Ztm87jbWWpHo2wPHfj1z9p5B7zHdVCuDpruOHqm1E9n94s07YjKf8Sw4NW+/Ybv6veDGyYluzImsggcGvccaPVi7clnj/SSdPht/6PgZ5YBBhkddexlu+Ghp48b8kHhi/6GjD/iDR5g8Xb1kXuOdFBU/3LD1q8xnPEH9M9+xjnRj6PE0zs7OmzZtcnV1xbSveu6nn34aPXo0e+RTdu7VqD37Pdw9Fvl7N5nLK59X7dgVdzH93Mer/zZx7Kgmd1tU/HD7rjjRcMe508VN7oSiqKO/XTh9NuOD+QHsPxYrKyv2hR/dmDecncMW+De5H6VSufXbH6U3ZStC54xzGdHk+dbyxoT4T6XPc6FQGB4erlQqExISXFxc 8A0 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 7A2 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 2a8 vl8FztLXk05M4LKsTLbz8+Pvc8PggOHVEuZnXDqVU4WKvZ3MlwuV+xsx4zlImqqT/mVkABfrbYtCpxh+yyb2caottK1txE7H9P7YTfG4cm5RQ3/rMIWvuNYmc1ujCMpZE8QxOVyvUQNGtPt+V2tC9fDhw9j1hQA5k+mCz41vPRF2bBhQ6vv9O7duz179jQ3N1epVFjNAV5m2LBh27dvHzt2rJGRESFklNPQBT7uRg8uOlAPvvko8L3gOdpXjRzObL9p8zwGklup73sN2rbm/cEO/bX7GxyHLHp7nPH9jB7lkh3vvb1mxRJjY2Otbeb4T5/S37ji8gm/wUY7VoVMmTyucdtEQxwW+LhzCy85UA/+/d60FYsXcjgcrcYEvO09z2MgufX7B54Dtv0zvHFjhg3sv+jtcUYPLvYol3z2rk/EX5c22Zg3B/ArLp/w6c+NWb 2A3 RiZTJaYmBgQEIBTRZ+Zm5vHx8dPmjSJvikQWLjaCeSZCZWVlU6au+++Yb7x43Ctk8dr3BiLZwWGJXlc5TO/HqUb3589cECDk8fUlD+4l0WNJPmp/Hn/uvuzbZ9/EfGRqWmDak7XkU4mhVmq25nVdWRiTcY/5op93pyk1TaBwGL84O6lFw5UVlaKavIXj7bcsOoD+s+NMdndxabqnvrW7 4a1 lVOtnny+cq7j0AbThhoZGYnselRdPUE35i/Wj/6zeb1WY 8a+ 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 8a9 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 9a9 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 7A/ fuEX9lBXKlU5pbzFPy+REOIRl1l3P1svWvuVYnr6DfoDZydnVetWtUOa1oDgjh0HlKpdM+ePfTa3dbW1n5+fs3XZDffh21sbMykcEKI1oKaPB6P/b80Nze36OjoTz75ZM2aNS+rzRUKheHh4UuXLsWATmhG40Lwjz76yNHRUYdnCI/HE4vFnp6eaWlp7DiOkQ8Ar0wul4tEIubvWqlUXpabaASEaNT0PRpC7lcaKJVKpvjkm/jDpRYDmQ0IIeVm9seOHaM7leh3jxTJA7VFf6KhmG3yVN3Yfbf7j6bkEzv2BpW8Xt8eOM4EcUKIr69vM1+UAYI4wH+pVKoTJ0789NNPzEDMP4wsFEV9/PHHOTk5TVZ1N+nu3bstaYxIJNq9e/fixYtjY2MfPHjArnVpnGnEYjEzoJOeoeIPLx6gK5zPWoXgQUFB+jMJJpfLbRzHxWLxkiVL8IEN0Ao0Grqrm30X+4aJIYdbX6M2fPHJYqCuEwgEzM 3a2 trGO6lU1rFvlpXLKcJlb6MhpFLRYGVo9kIEgCAO0AT2t/akZYWz5H/F3zKZzMXFJTIystW/W7eysoqLi4uIiKBXvG/+KUQikUgkWrFiBV1Ow8QaDOjsghoXguvtVRkTx+mRDykpKXS5JOI4wJ/9vJBKpTNmzKC7bPh8/iirmmu1dRqD/y5tbqBRW1Jy9ljMD4ID4z/6+jrnxQdEd8VNH58Q5iafz3ext7z45MVOCCHjuynYbyZhC9+J/X1zvuEY5h6B8uGK5XPZbTt//ry/vz9eIwRxAG0URaWlpcXHxzPf2gcFBbVw4KNMJvv73/9eVlYWEBDQ5JDwVsHj8bZs2UJ3us+fP/8PO92trKyCg4Pnz5/PjjV/6veCDo0902UHGsjLjHyQSqXbt29HHAd4BTNnzrx27RpTBb5s4ZzL//mlwHSEmmPEUdc5VufNnNkgH3e3sR4v1Dx8WFjJE2oMOALlw/HG97T+4j5YMOvoP3cXdhut5hgZaNR9KiRBS6axN+Dz+e496gufFSn4fQghvDqFe13uuDHLmA0kEkloaCheHZ3DrCmgX5ilK+mbf7bn+OLFi2vWrCGErFy58s9e6KekpERGRu7bt+9PJQy6DN 3a2 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 8A3 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 8a8 vDz2Y+/cK2rmYGo0msKih4VFD5vfM30aN6O+vl7rJM/Ly4uKijp9+nTzD0xMTIyKirpz5w57V3/YHmnBzaelZa/Z5urqavaLVV9fn5eXt2rVKolE0sIzfOPGjadPn2Yf3od37pz6/vvmz/Bftm49FR/fzItSrVCcjo9v/gzPy8rKy8rS2nNiYmILz3Do3MrLy/fs2bNx40b2X5YOW6L1N/6ajh079umnn+JV1hN3796Ni4tr8r9++umnDv2rzZs3D68vky7aIcqiNKWVSaXS58+fMx2cpc/Klq1af0E9RGFmO6K+wLWX4X8+Xa3VXbppx7dH80vzDIcZ11VOML63zP9NP+9J 7A1 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 1a+ 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...

... boundaries as hiddenvariables and include probabilities for let-ter transitions within segments. The ad-vantage of this model family is that it canlearn from small datasets and easily gen-eralises ... 2006).They used a natural language tagger which wastrained on the output of ParaMor and Morfes-sor. The goal was to mimic each algorithm sinceParaMor is rule-based and there is no access toMorfessor’s ... terms oftraining set size. We want to remind the reader thatour two algorithms are aimed at small datasets.We randomly split each dataset into 10 subsetswhere each subset was a test set and the...