What is a Chatbot and How is NLP Used in It?

This language flexibility expands the reach of chatbot applications, ensuring effective communication and assistance across different linguistic backgrounds. Named Entity Recognition (NER) involves identifying and classifying named entities in text, such as names, dates, locations, or organizations. Chatbots utilize NER to extract relevant information from user inputs and provide more accurate responses. ” the chatbot can identify “coffee shop” as a named entity and generate a response with the relevant location.

樂威壯
nafEugzbvUo3kbq+B3u6pnP9O7Cz6Qx7QQrwRcNwsT79gVKNgidyRcPDuec9wwL409vh0cau2ApU7VoTZ+s1ffsK6Btc40fx+CRxq7diz5K/dsTxw95hr1l+BZ9IY9oIV4Gy8kAcsJSM2Gg+jt+rEk5PNw7FSsS7VBkVSsgGd90Xw0gzmucuSL4QFTFZakA5trFIEj3kAq5bYSvMROJ1HMXOWMltcLnnPcMC+NPb4dHGrthHpFH9qnY1k7gnVCEAynnjLjm/wAxlxzf5jLjm/zGXHN/mMuOb/MZcc3+Yy45v8xlxzf5jLjm/wAxlxzf5jLjm/zGXHN/mMuOb/MZcc3+Yy45v8wlE5ynbx7FnyV+7Ynjioe51HeUlpJrOH8xNm5OiPuWha/oj7loWv6I+5aFr+iPuWha/oj7loWv6I+5aFr+iPuWha/oj7loWv6IZUe5FET31ArJNorKlMbQQrwJVmR2nYUVvOhlCXEcQ2S1d8PfDWZuChAVi1VC1JO0nI+4wwHW1OSo9tlsdza6Dta9bgB0wpsiaKLWI4a10dz0KSZVXK50FQjukHEkqKAkGW6kJQhjEupOLqzKZC6EMpbdS6izajanlhNa+VuBzznuGBfGnt8OjjV2wEqnYtCrP0Gt7tiQRZDRSDi56rD+FZ8lfu2J44e8w16y/As+kMe0EK8BZfmhKdHbsVOpFhtVwbPGS20pT4MBDaJTv2bnnPcMC+NPb4dHGrtialAWgW8Nn4tnyV+7Ynjh7zDXrLh5htW3VULVmaRn2Q4tDqU11tobJlJNk1GKAUOKTjErr1EVzNMJJNRwNVlWaVSEUcKVtAg42zx0gkw4Q2W14tLiLjNJMoQiqUKD6UKFhsUJxR8YCpRQFLI4TKGfSGPaCFeArZkdp2NEcWZqWyhSjwkYKw3BOrw7nnPcMCkpEzZ2xkTrEZE6xGROsRkTrEZE6xGROsRkTrEZE6xGROsRkTrEZE6xGROsRkTrEZE6xCUqEjb2wj0ij+1T+LZ8lfu2J44e8w16y4Q8Ud8SJAwio1KrOX7r4xiW5Kmo351Xw5XTOuAFftisGraylcqrDC0YraqEjabhmgSRcuveb7obGL3IkLTdfbphn0hj2ghXgAM96uPY0D0dv1cCkm4iRj9JuPhnPOe4bJNWjuOz/JVs5xEJxPclxWms6hPYTCW19z0sKUCUqU5jBteBPHG7Y6NXzRP7as8BSiXLICN2x0avmhYb7lh2oaqlh4JE5TuPHAxnct5Ks4SttQ11hAUW1IP5VSn1T2CUplY60q39Cwr3fi2fJX7tieOHvR2vWX4Fnz7HtBCtnwIt5c2yCUpASBIAZsJSq4xVVyHTCVKSZzOc6Y3B5xjcHnGNwecY3B5xjcHnGNwecY3B5xjcHnGNwecY3B5xjcHnGCECQnPZJxz7bc7qygmeuN/0fpExRcS+25Jt2dRQVK1OjYUtLtJabVjpyUoDxE6Y3/R+kTAW2tK0m5STMfjxXF11pHZFyueqLlc9UXK56ouVz1RJPbOKh7nUd5SWkms4dJNm5OiPuWha/oj7loWv6I+5aFr+iPuWha/oj7loWv6I+5aFr+iPuWha/oj7loWv6IZV/wDiKInvqBWSbRWVKY2ggpVdFyueqLlc9UXK56ouVz1Q6kXA2Z80EmLd0bVbJp1M6riAoT4bdhI35jAQTcT27AqNwEzHj8xXwjx+Yr4R4/MV8I8fmK+EePzFfCPH5ivhHj8xXwjx+Yr4R4/MV8I8fmK+EePzFfCPH5ivhHj8xXwjx+Yr4RVdZxiZzkpontEWUMJ4UNFB1pEWCkA6ZumWuLaTSiNFSU9SY3FI5z0bxSeEsknlJEBDbZQkXJS2QOyPH5ivhHj8xXwjx+Yr4QQJ2aQR2wgpUR39gWcLgH9he9Ha9ZeEd62+PxNWefTCCpUlFFeqLbIxlaXe65BzCMXjNvo64adlKumcsDPpDHtBsn/KHqiBoTtj7tnQPR2/V8C/5tXZ+Jd8hHaYR6RR/ap/sL3o7XrLw/aa+bcfqunqjKT7ziruGc4CPtIyGJO0zC7PCXDSLAqYBHBKV8NNVp1EyngZ9IY9oNk/5Q9UQJi1W2OzaaTOq2gJE+CzwL/m1dn4l3yEdp/sT3o7XrLwvATq0NZcHCFGfZCNuElTZeAKZ4xSzOrFNrLkhDjaQiXCk3wyhTg2tKkG5ZgLDy4WfSGPaDZOpzVgVah4AKSoFJEwRn8C/wCbV2eBo/2ZciSqdgMwkTzxRkNL/wCMoCYkLSU1oyTmKxmLx0trWimJYQus0BNwAVUk8cKbUk1kUcOkxRCFVWF0ZThB4Iq4taJoK0T8ZI4o2jKwmUwqwjlkbD4F3yEdpgKqzm42jnqCff8A2F70dr1l+BZ9IY9oNkpQFqrz4Cgejt+r4F/zauzwNGUVSDSiZSvmJRRZPzxTi17m+sJRi/tR+y43GYqryynoilhFLxbb8itFSdoiu3Sak2MSvazmOCKOFOzDdHUyRK+tnieNSZIqpqtJSeMnTCX1OgkJI2qKk5/mlf4F3yEdphHpFH9qn+w1naM0tUpTUkHtjeNH6NMbxY6NMbxY6NMbxY6NMbxY6NMbxY6NMbxY6NMbxY6NMJUmhMhQMwQ2LPDUZpUqzbSUmXAJeBf82rs/Eu+QjtMSUJislXKkzH9rXU3UjV44objQT9pcLlcSzN3xREIKQyaLj3eWA224axnVmkitLROHBSlyUH1ImEmQGaf4J/zauyMsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6MsjnRlkc6HSlQO0RdywCoyFZKeVRkP7ZS1uo/4/fMVaP6l8d0UUiwuN4loz8Xkih4+jrAo4O3U9WH7RFMof2NMqQ+VYyuNqJ5xyQhM5yAE/AAGmMKkLywbdS4VjnW1aKiCntJwKq0hgJnYCyT/3hNakMFM7QGSP++DvTzSUyuU2VdihG+qP0KvngViCqVpFkd6WhKp3qTW7CI31R+hV88d9WhSp3pTV7ScG+qP0KvngYx9lSc4S0UnXWOA4t9lKcwU0VHXWEb6o/Qq+eO9PNJTK5TZV2KEb6o/Qq+eE1iCqVpAlFVumNBwKkoVS6R+1BnFlo04iU9bsHH0xutO8oLPr3wapAMrCbY31R+hV88DGPsqTnCWik66xwHFvspTmCmio66wjfVH6FXz4E4lxtOmugq7CI31R+hV88DGKSpWcpFUarYOLUlKsxUKw1WQhLlJZqhxCzVaIO0VW/MdH9sKStVUKqlyqak+PYIY21ZSSRZZZ+KOLSlSswUao98Wu0ZHmyRrrJVDX2oBxC11RN5bsjIm5Y4IAAswuJorSEFKUkqCy0dtOzaDgjavMKF0nFFQ6kg9cf8hDQVIWtqJnrAl/dXnKLTk4oLM6FSEgmc7oYbXNtr7KHEoxuJt4+CO4DblKV3zHBa21boCF1FOKQ/R6jczWk4myO5jBdUoiirrTVeqKNSHu6TopS3yFN1iZ27mroiluY+o+ik1UzeqgAHc1M4/FUPz/AP0VsKZ5trtV/d8YqjNlf5qonAxzKHJXVkzhs4pM29xZueKE120qqmaZicjpgOFtNcCQVK2C6KO2HD49UT1wHTR2y5+eqJ6/xVD8/wD9FbCmeba7Vf4qpvGuNz8Zs1VDijvXdJ9XA44uZPGkiWqElxp1yrtppeLgGa5UjPkiTisWdDm0P+2CpWmv8ibVahFZpl5FYSrlwtCzSBb1QK/dBxGkJccVqUVDshQ+0Pu1je6ut/iVV2ktoMpyUoCMoocJbWBrIhWJfQ5K+qoGWrBVdpLSFSnJSgIU6hqiqbTOsRVq8uaMXRWq4F2LkGxy/CLVUefm1fNE/tZTwISmXWDA2zSgNKCCeUH3QA+0Wv1bpGv4wFJIKSJgjP8A4epLSqjUyKwO2X8BBkLzM8J4cAUU7YXKuIloMJTSHi6kGYSoJlPkAiSEhI4LImttKjwieyNHrEt4sqQPyVTKQ1/4eGVghbYqmyV1kxwHN4QV0JVLSJxNsYs6W9of9YFV4rT+Ry3rvgkpCXEnbInOWjX/AIVXcVIXaSeKNsrEp/Ig28qvhBUEisb1ZzxnCwJ2Ysw04WRUUqrfFLr5NA03CGwpCQF3SVMjjh1WJFRFa2eiKPWZkl2wWwvaiolVU7bbccoWjxAnT17EynLEqraxKfXL/CqGc1V0T4TV+GxQ9W3KSJQ0zjNwqtOUOuYzauCSky4JQjvs0puFWWuHm6+7rWy0xRRXyR0XwopdkhSqxFW3XGOS5LayKZYSpVwvjJ4pP5nPlHvlBCZqUb1qvOr/AAcuOrCUAgEnhMoC21pWk3FJmMFRfGCLwdIg1Kryeav4RI0Z+fmlHsEKElAgyIUCk9fhaPPRtPInter/AAhSVAFJEiDnh4NKNhlXQSFS/KVCU4tqPD9W0VrFnVCXUpUkEqElX7UyzYQpKqjosrSnZoMd8oyvKb74Oq3qiRdSDnBMiIrlQq6c0CTqSSZAJtJnwCJid5FoldZgFhJNwAmTyCDUWlXEZ4SlG3UL0oFc6hB+1IqtyydbbHjldyYUYuWMWsJTWExpM+QRIvoRwtokf9q0BgUp1apVpTxQkM9ZAEBBdW4bypaibeXN/gRUogJAmSc0VWVKQ3nVKqpWu4dcAAWYKZ5//onYDGupTO4E2mWgZ4OKcBleLiOMG6MamjNhyZNcJE7eHAVqRVWfHSap5dPLG/H/APT5YJbb235iSpXFM5oTjmG3JXVkgy1xWdo1FQJympKREm6PRiq+riwFajbASlICQJADYSzMoq/uXaeqWBLiFVVpuPuPBCVgSNy0/lVo/wAAo7iEzTjpOD9JB98IfLoDawCk6Z6BpiayUtz2rXvVw4SGRdes2JszDs4IpwIIUlDQUk3i1WBX2bF42yrjJ1eWUPOvPN1EpKlJaWUbnRtZ9cEhNpvOc8cAlNouOccUMOIWwtpaUqqurJVVPCE38c4GMSlKs4Saw12YV4urjKpq1rp8MbZ5hIuk2opHWknrhD1XbrSCVE1lW8JiS0BQ4ROK9GdbU3NQAfUVXGRuE+uDjWwhU8yqw5LsC3FmSUJKieARjHjiCubkhfWUa1ozDgiSk1VixSdB0YA6kTsktP5h8RmhDiDNKgCDwH+/ucC2yeILBJif/wBE75aMBJNkVnK7bejcqVruHXASkAJAkAM0Y7FjGSIrccvhhp3mHPVw0HzDfq7Kj+bT2YE+cd9c7EOtjviRKr+YfHRCVC4iYwSUe8Kv/QrTxaYozNFNinRWcIsIG2ITyC/+/UttAmpTS0pHCRAWhU0m4wJm+wcJ0CEOv7q8N5k6J6TsSohUh+VJUdQilJZWtZW0tKZNrtJEtGGhpVTWQoMtgguCyyAttaVpNykmYwlRnYJ2CfZCgHF7UyPel2HRdDAItCE9mAIcpbSFBx2YUsA7sxWadQ4mcppM+zYl9A72Zl3gP5vjhpD35JNJ9ZXu/v5UtkVzetO1UeVMd5exnA5tSOEKQPdAFJYUhxIkSau24dqdkVFuTh/qJsVrz8sd6eS4NDm1OtPwjvryWxob2x1q+EbZrGH/AMhrjjkbNjNxkFUpV7lDlFsd5pFfgdEv9k/CO+ONtj9M1k65SjviMcf/AC7bqugJSAEgSAGbYpU8uVaxKc5iTQrAeK0C4EDMLJ9cd7ojxlfNNT15Q22TtrSrRWUZmXB/dlvBFYgpEpy3RlG80dL9MbzR0v0xvNHS/TG80dL9MbzR0v0xvNHS/TG80dL9MbzR0v0xvNHSn5Y3mjpfph5KmQioEmxVadafANEYlNHC+9hUyureSNB0RvNHS/TG80dL9MbzR0v0xvNHSn5Y3mjpfpjeaOl+mN5o6X6Y3mjpT8sbzR0v0wpX2JFgnlfpiulFY1kJAJlu1VeHTG9WemPyRvVnpj8kb1Z6Y/JG9WemPyRvVnpj8kb1Y6Y/JG9WemPyRvVnpj8kb1Z6Y/JG9WemPyRSCtlKHELDZqmtOysLZD80Poao7ZDagmanCme1CvynTG9WOmPyRvVnpj8kb1Z6Y/JG9WemPyRvVnpj8kb1Z6Y/JG9WemPyRvVnpj8kb1Z6Y/JDjqqKzJCSoyeOb9n9uc8tr1x4OmeQ1/2g+Yb9ZXgnvIMJ88x7QeD7oefHs0x3Q88PZp8FTPMr7P7c55bXrjYV8ZtAqpVn1w6lLc6gBNsJS23OaK98NKCd3pzQlWnlw0zyGv8AtB8w36ysDSK6kgpNxlFLTXO0KZKz2w2JugEHKZ+KAiqLVSvtipVAtlfbFWQlWq328cFuqN1K028eB7yDCfPMe0ELTOUwROKNUdVWoyCt63dSXKRinUqtXSp8NNJKpJszw8pG1cbdQDUVYbcxikNUhsNqbRXsVMVYGMpFZNKCilFaeLINg4LIU4qjAMpexSlVrb5TlFMq0UKRRyK5rSsOiEthCJFKVArVVrVtGbB3Q8+PZpjuh54ezTg7oY12lhtGLq4lViZpzxQ5rUpyc3AhQClJ4DFOQzSHMam5L1ikTzTgNOLpCFFB729tpnSlUMtgIrLmduqqABHctbCQEvKVWSTnTmhWKo1ZlLpbKq1tmeWjBTPMr7P7c55bXrjYVKvLnh2alBJCQLb4BBKUhurMGEJClCrogITcMNM8hr/tB8w36ysCVVlAjRCm7dtec8JUVrURdWMJ2yrFVgICqyjIzAMVgpV86s7JwFFSr5ywPeQYT55j2gwUwif/ACZ1+XRCKKCuqlVZKp7YGc5wplx11YUqsSVWxSEl50l0AKWTtpDNDUkYstqCkqQADZCy+pY/5CnMWFbU6CYpynVrS26pNiVboAZ4M3HAkgAoB2plAAuEd0PPj2aY7oeeHs04KU4ZnHhIWDdtRKGmcY73tU21T2yeKKQhRW5jsopZmTKA6XXXFJEk11TqjghtddaFonVUg22xRhjXAWTNKp29cYwLcAxmMLdba1tOCmeZX2f25zy2vXHg6Z5DX/aD5hv1leCe8gwnzzHtB4Puh58ezTHdDzw9mnwVM8yvs/txQ4hK0m9KhMRvFjo0xvFjo0xvFjo0xvFjo0xvFjo0xvFjo0xvFjo0xvFjo0xvFjo0xvFjo0wrEsIbnfVSBPVFZ2jNrVKU1JB7Y3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aYKHEJWk3pUJiN4sdGmN4sdGmN4sdGmN4sdGmN4sdGmN4sdGmN4sdGmN4sdGmN4sdGmN4sdGmKrTSECc5JEuyCtyiNLUb1KQCY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0aY3ix0af/6J/8QALBABAAECBAQGAgMBAQAAAAAAAREAITFBUfAQYXHBIIGRobHxMNFAUGDhcP/aAAgBAQABPyH/ABuGGoah4RQVHGOEf47DgafTGCcqs74Nkxp5EsCuGJa2VIlFIjiJU4pDfMEIgtNuVFPDRx9ScmiLhwQlzzo+W2Bna9rFTBaZiXAZI8+dEzw2KLk0tHJM6Lqc6bczzMRBmi0lWJIJXmfAmzU6/wCOw7jnpxUuiB1LEuLl/VGOhcIcK9BA1XVz+jW7aVsmitk0qyl2YIsjJyrn2UjERGAY00og4YYydaNfjEklhVg/miSUn+xw7rnoyJFDRt0Gr3+WgMc7ralDRNQQBlS59qdoDKmS86xNKECyC2yo+OVTTHSBoM0gG3brqEFDwBdnDPu1ZxUFKwNKGuC+t0nMNOCIJ1+88E2MKweIKwnYxdx9GpGGT1SD1pFspu4gpWO2GZyv7U4wuY7MtTlSC2C/OhJHFKeRwYADCGnq1h4ySR8ypkCXjI3HIFMZ6iEJ8uD3Uvoy05UwCskPVrmBEHoPEU1YJn3rkh532eGFJGTSe3i9sprirYS7LNqbEmnIU1KMgYKbZUMbf1wtDN6xJeF59anbZjafSpWChlJPgp3M4BzstKU7IE2pzSMXongEcsEz706Csx+NPfvAzBWziag3koOS0OlOB4YmQSVoU5UgbLlAsKLXD4eNwvP+ywxmXA+a90qJfWRfuVlLesI+xWOAV1DH1mrWR5CF/NYkk5CR+ShsCQV01ItQt66zgShGtRF8ghowK50aRW9EBI9aZUKQSTvhTqCTjMoGXThsmtKHMWICpWmah1hS0fVFIXw5I5pfg42YLU5LbOiksydxcoElMrj6wTRS+vA6WvCR0bvjgcGGAEFTACK0gRRdFWCixkkxpGk5FwYQ8qeKziJLNjSOVL7+M926wSU3La24knW9YwfJZ3qrGRKATXsozZ2UNlAEC80gMo1uhJPNmhHIJ4jgnmAqYRGWA3MMQaj450XAD0oFcFiQFvwLNDNisQaDNo4BFDCyIOR/Pw3EHgkMCc6R2kMSNnpUz8wJj5qMkogM4C5araFymxYyazqVqfSbjOpg8iwheryq+ZMosGM2tj9tD4/AyZBnyra/bS420mWicZjKuT286hhqSiJri8NoZF8ifdTPrY5CEqsXTz149qSKTpoqACCxw0W66lBbXqI9VHgQmLIbYFnWi0bCm4wPkf8AhQ95YBLAYwa8Nk1p4YZKLo5Ka0H8uMMs5AiOdNjUJMWxblwZOgRgBgTkU4OQYJHVximJMGCmMWl0bUiXjARLc3cqVQAVDUTpyo5kJ3E3RbxTcuVexfCuehAEEFSXrCXm8xERkVAPkpgBlu6xTIhiX3K1a69hLKcMK1ip5KXymg8WKJnSc7YVGZbPIJ9aR6IuWPEBen5B2CMOA0wiQ43IJSfnzMsFiWy4XLbIcIzCm8/0GH2XzeB74JoiGejT4q0dxsYFo0ipEvke6Ct11pOjNkkSzmVm3miZFZKNGYTAtdR8uqZsBO+F1BqiwQScijU6jggiS9KxeEEl7hC8ljgaRCyELbBYoXZBRyagFgt2HU1DWKOzHqKscHjCMHpRhVSBXkvzU5pIw6sUVpDhqBpJlVgBFcYJxcMbwEnnsqVz2sDoCGjbKMh6KWHzoABAWA4Of2ylSZ7QipcVDL51C+ecwGBLwDD7JmHklyr/AC6RMeU386PYECgDkFRUMoN8Fhi1R5HEySdSKs0TrxwzNRpUmOrmKpn3BBzjMifOjJku/IYXx86YjKmsiGy1ir2japEvQ0CGQNTmaLWrnikW6sJ86szuJHymUeVJQQJIjk00EJI4jQnhJMxYEpbJ0/oMPsvmpmOtBeES8VAzEgvbGlG3B7nwjzqTC2xbDAeVb7rTurcc9GR50MjZv5VGI9oGCMqbay0NdbuiX+NZfMSETBMfPhQ0WPPsEjDnRY5DFmc4wVAlp6ws4GtK4lzNhEuHmoHLSaceTQYJsMovJnGs3rQebNzpIohgOiXcnWvoNIlyOHMxRzpUqc0NHVYFyHoI4bf6avxon3dKEQMW3CrE7PlSOz8UKgbPSrc7flWx+mvMcPrrY/TU86N+FYGrfhW9+uvLcfrre/XVicO/KklG/flUm/8AFWp3/Ktn9dZOmfe0qzO/5VZne8qytE+9pW/+urE73lSGO10oZg2ulWp2vKtr9VYOrD6q2P1Vi7XpWDtelbn6qxtOP1VvfqqzO95UmxveVDb3xVqd7yrb/VXc7it39Vbv6q77cVu/qrN2vKo9r4oextdKz9ryra/VWBqw+itr9VbH6KwNj0rc/RWPpx+itz9FZu55VHufFT1N/wDRwZsqt9cOQf8AattVsKoP+lTf9K3FTko6zAp963d2rc3at3dq2N2rc3atvdq2N2rb3atvdq292rb3atvdq392rf3at3dq3V2rd3aj2Hepi+r2Kj2HesZstXsVHsO/gDDsxrBsx4Ozrwfcdq9yrE7LV8jt4N8ThhA1aPeKxmy1ezUe04bPXhg3Y1g6O/B2deHzNe/ax+T8V8z4N8xSxsxOB7xWLyPivflHvHAx2z4YOnvTh09+Djvnw+Zr3VY/J+K+Z4bPLji8jgYupWLyK95Ri6nDmAGCLc00RjkAGcVItGlLycnLANUDep5jiC7DhLTeKjAWjMmfm1OTck5AnlNTpSl44VCPJT0kC2uGQOkTWY41MEFJnS1SRrxEQQggZpi2mhvcFbS+NNQWIOIXkb1PJsRHJgeTRDMbZGGcRyiKtJcTobvo1cdE++VkUJi9XRmmb9Ul5Jm/VNWCmb9VfGaZv1S00TNp0oBWHjdr0q+M0zfqvtX6oJfqms6cOEapRY0zgJn8t5uFWRraNTOtBvS+oq2NbwFiOV6I4MgieUwpiNJg0ijphOmrwzjJUv6lETCdFXBnGSvqlAuWxs1r6JQZmjRTHkjRX1SmbNcmtfXKsjOclLTO0UJ5Tkq0M5yV9MpCUXBYaRW1+yrw1GyaW9BsmiUm3ZnRKNRsmkvSbJoKOfZero1mya2v2UTaOPU61t/soi5Oy9MXJ2Xrd/ZTLq4dTrW7+yrI1uyaSmvZehvS7Jq2Nbsmtv8AZXsDBp1rf/ZVwajJ+6ZOgyfut8furjmMn7rYH7oQdWj91ecxkrYH7qCPbMinRGikYnG1XzWrShJIYzg4qjm02+azqzNDW4NI5JJvFY2EMLYHOgAW6AAhzzr4cABDnnSBKgA6GL2edSwSBYZJeje8tZbBoSIGJiaGgUZGUCkC9isXcTkq4hPKgyDJhnCLEMyY1cy2h0WdcZzxo5iBKcxBxc4oQJ25H8UitlcoAfh+LFixYsWLEx5oVgjlCZif9DsAy7TQ9En+NyAGYfKcm9QQcvr/AKGIpQ4YPrrMspp6RZHE8NjDGrSoYEQLZpbW1pzWQwsdaVGg6LsE1GKYU3uaOZ4wLet/Ul7yfaf8dkWQcbG+rGuqN0oYROSYzotOkeExQSYmospEluhFKjDQVAEKTF5vUuYz4h3XufFTOElukrirJfGBImkjUNfV1OKZeb5/xeWOIzjBmtp962n3rafetp962n3rafetp962n3qALC8eSPjIX0hdpz+fGGMZFM6RY8MqSwBIgOYKElAnHRZjrc8MumhxrrNnxyjN8wE6Kb14DNsyE6iL145cdDOFdIu+GVE4aLMazc0gsgSILkKDBwypjCRTOkWPAIThISZSShpIRhIQZwQl4a6HCukXfDKkb5kQ6Il6UkbZkU6gh6cMumhxrrNnxyjN8wE6Kb14BjGRTOkWPDKksASIDmChJ/LD+y72rOTrX3in3in3in3ih1mQg/QVIrZXKAH4eiRIkSJEiRMWaFQRyBMxNC5RFljF1vX3in3in3in3ig7kDAzEDFBpQELJD50BnK+cZ+ZfxAKUtIG4iZfmkkosnujOKBAhImZ/EABPQSHnFn8vfNfC2/L8awD8f58czcvqTd6sefi3nRSnTGBsScitg9q2D2rYPatg9q2D2rYPatg9q2D2rYPatg9q2D2rYPalB8ULFGtRFxibk7W8EctSMTiDOtk9q2T2rZPatk9q2T2rZPatk9q2T2rZPatk9q2T2rZPatk9q2T2qeWpWIwRl/MIb5r4W35cVkEcYxOAsetFYTlQ7rBVu2QvS+V0oGK20IwlXmxR3GG5XWFyySjJxMy6QL5nED8f58Zr4BPWpDiNgyGP/OXhQNI2BSUcq2TT+dGU2n7cdg0/n2DXRIAQBN1B6iW/l75r4W35cVk8cUkpihhV1C/5Bq5lWoP2AMHyCosGNFxwu60khmil03LMGlCGslPItxA/H+fwXY/AOD54eni2TT+dIoeaHlDhoJw2DT+fYNdTNwDE2BW1XxFpGQ5sEv8XfNfC2/L8awD8f5/BASU0TEdTnUuxIw5Cw9fAhdQJUmVda2TTwdgOIR8DhYcAZh58U0JYQlzR0pMwChouddKenAlTAFZkEg17eAcRURrH7KaGRJya2DT+fYNfiIJW5BmtClUyLIJ2P4u+a+Ft+VKmIzCAQZJT6XX6XX6HX6XX6HX6HX6HX6XV2KDEuBzAWca+P8AP4Zl1Dpdw9vABdQIUGRNa2TTwn0ZMaeKFSZyVk4JcnkUQkZgLo1YWLJK9AedWMmFhg660RNToSQvhpRfe58NAsmeYGUetX/tysmSawTSAcuVShynhwKwe71X83Ktg0/n2DXWv6ETknnZ4I3lGFf0Rp+2hRAGCkT0rbfett96233rbfett96233rbfett96233rbfett96233rbfett96233rFhgUtnr4d818Lb8vxrAPx/n8IUwAitEuNCKRC5olk8nwbJp4DsQyC8NafbcQGPWnG4LAINCviLe6lbkuLLjN50FQggGDCdal9UQiJnAxaWRBIIXB50oqckQhautYI5KASaNAAAEAZeDBiLUakpKvNNbBp/PsGvwRzDleRUhew+bz/hbjr8O+a+Ft+XgWOSYhMBK87TpVvj2UMwMGYslAxW2haSrzYp2WNUZxcmh4APx/n8Uz4X3IQnoW8+IhAGwCSjlWyaf4Fmrayc6OuvDYNP59g18SCIACVcAq8waxmtXsfw9x1+HfNfC2/LwLATY0oi5N+RhqrLFRYLVK35F3Wl0SEQYMCU2PAB+P81FB0wLGWVQL54Q4CfL8DGXDyczXk51hRiYcTk8zPhvOitk0/nziKOotPl88dg08Y0oLbpLrlLat5Ik+vgnusAhtOHAYNueHR4dg11AtEExc6+gcDJbkuqdj+JuOvw75r4W35fjWCfj/ADW7aKQpEiii4AmSBiOlFFsUoAJsVExUCTPZVKKCKuDTA3Ib6xRaJcTBAZhw8DI4DyYsPefXhe2oEwEBehySjKUQBry/KkkkkkkkkkkkkfCBWsWc3WoLEMbmb7UCABAGAcdg08ZlskEjCYfKn9eKS1EUwnDRUnOljXw3bpnEpMxW8l6egKuJLsYkLtqlwCds6QTUaqXxWeU1fXnRBHNWMQyr55iQh47Br4IxQSWwv6fPjBE3ZYCTHJrCPSoJoGAKMkEBsjKYqYUJlWvfCmF4R6IYI9KeUYtCGEpFBbjC5mFCM0TIWTLCkAR4qYLtScoDvS0JC8vSXtiVCBJTMzbF5vHcdfh3zXwtvypU3GYQCDJKfS6/S6/S6/S6/S6/S6/S6/S6uxQYlwOYCzjXx/moMG0EjEL1jF0wOLFHIyJclIfF0/T+faeFhegJISN/BbalZoatSGE66s/wzuH0TU8qDnbFXFavg2DT+LGEA+dX0G9sdPBsGupFohibHX1GoMG0/Ss00x8WBqMS05ItWMYpTgCCKSSpQPRbKrrVylOKMXOgG9giMjCjNc3EjTEJ50qVHFGXPXyrS7UPLhhSa5l4sDQbxG+9C0FK5NGTad/WiMRhRWNLacdx1+HfNfC2/L8awD8f5qYaO0SsrViC7kkLcwmpYkbj0AM5xmgti+xS7FqzkRgALWjVGNX+UtVwsnBzqUdQ7TjdWp+LwIaLgJJpxkHn0Bu80jy4bzo44xPO39UkUvK1aQFEi3Z1K5FJyKTkUnIpORScik5FJyKTkUnIpOXSA+cCIRA5zrw2DT+fYNfEgKDCIGX9n8Tcdfh3zXwtvy8CwRJJE8t8tSMU3ZVp1TWPx+xjLq9FNLHglisnn4APx/n8TNFLw83sZ8qlUgicYLcOWyGM0jnwTvbAM10KfY2GQNPze9cLYNP59g1+BnFsQz582pnRf+FuOvw75r4W35eBYybBo7pi8rEFzzLKcblTKSUUnNmBwYuYVYmh/Y5eAD8f5/FCz5bN29fBHsNV6VKR6D5vP8/vXC2DT+fYNdEUjqIR5Td4Lvlp7zaP4W46/Dvmvhbfl+NYB+P8/hwCFwMJUE8qwoxEuLzebxUKv0qTAAz3Xt4c+OgURbWhhGMbWacYDOjnkhGBCWawLL4c6BrCwusXpenVLZGIMFHCwzOiTWLM9Qox4+9cLYNP59g1+Ig6B8y5dNKBamkiYgXt/AyyyyyyyyyyyyyyyzFysjFPPw75r4W35UqYjMIBBklPpdfpdfpdfpdfodfodfpdfpdXYoMS4HMBZxr4/wA/hm3QOl2H38ED0KEKoDcxiMM6x8JDSB0WRyDOrZriN6USdSi/5BJSmJQoAEyvExLFHS6n5h60xXzoMwvozRA4UsVI1pULyPBIY1dOwIt/FpBovzZ8PeuFsGn8+wa6YoHUQjym7wggUQjglOUSI43Wn9/xd818Lb8vxrAPx/n8CQslIDVbBQiswu6q6+b4XkK0Hu6a+OwwfrkxwIAVNyq9Xx+9cLYNP59g11EgMhRdQOqtv5e+a+Ft+XBYYvLZiR11GI3miLJ0msE8GWPAhtNT4PlOIzjMSTaoAB5hf0Iir08BYR8jfCnLPgyJN+dQqFwiBhBnhfgB+P8AP4GHmZ5UR6N/Lw2G6REhVtwdR+Zcumn5/euFNLVhMYBzrZPetk962T3rZPetk962T3rZPetk962T3rZPetk962T3rZPetk96ilq0mcU5fzKG+a+Ft+XDYQBVPbDjSyDV1DqOdDICVlgAomLxXOyIkikLdaeknNlw5I5lYEABa5IJbE5FCnBArMSDK3goMEQoMIwLrJ14Afj/AD44CwvIxXQ5tTnE7hmsfLTl4d50cAhlQcmom3+jef5vevFZ2xMjZrm+Va6XDekXNGimhAgcD3HAaOBAZllGUlHR4TYcs0SisGT1UoXjATovgpZSmUQ6zHv4EAD0Eh5xZ/L3jXwtvy/GkE/H+fGV/AGaq3oieseIBShoAWADLjMNyMkuNRQ6GA5fqk7HKxYIya2D3rYPetg962D3raPeto962j3raPeto962j3rYPep65Jdb4Z+LPicsMY5K3l3rmgmggnwCWxE9SCYWFby71KrKASLWT+eq0WdmIxxGlbo71ujvW6O9bo70tNBZuvlNKmIzCBQZJT6XX6XX6XX6XX6XX6XX6XX6XVrbBiXA5gLONBgyxhT3K3R3rdHet0d63R3qQ+LBWFrnQMLBL5UghhfOcvIt4iXANigwnn4MNg8v/lCIW5OafAmsKTQK5dZy6zl1nLrOXWcus5dZy6zl1nLrOXWcus5dZy6wI8IB84TGJTAV0t6ESmFtqxmNYkPmRUFf10INJFPJmtsd6DAVBi1zQV5tSa6gZN7BTl1nLrOXWMXoCisOGA0pEDcKLJHRGH+kyAcx5FLNGEXqBfEhnXLcqIWcCGZYn1Ks00XYxZOExWTmXpifwgSET0+pk9SfLx7zo/w9EkhkAU3StZi+ighNs5ObMdahAWLmaUZHWpOg2KhgGwPKsmEtRMcvwAWDrAXKGRAyDjfCeYW8bLpGxQYTz/w9EnJY2NGRx91QxcsivsRheny0cJFuOSjpHBBGXer8IFteT0IiPN9p/AApS0gbiJl/CobJfaQKx0qAKBITOOJtJSbwskGlrMc6frMcYOOb0orTaNCORzpvgXiTUvKj6n6i5hJN+VXUKdekldB/FJ0/QmM08rv7DIBKSMOcwQfg3nR/ConXh3o2GNqTSthYYeY2iKUW8SxTM+pUkKzBbYjJZzrClwxiZ3WayUcTGxxWqDc6cHPMrSEXzHz0kL+rkkBAlA9jSRhW+u1b+7Vv7tW/u1b+7Vv7tW/u1b+7UETQCouIxj+ZAkjYFJRy/o6JJOOAJiwa2if1eJwvjhZapwGJEBW3pDU4UQmBgvlFRxqoycSxeKsVgXbxKWJ/h0fVq+rV9Wr6tX1avq1fVq+rV9Wr6tX1avq1fVq+rV9Wr6tX1avq1fVq+rV9Wr6tX1avq1HLYJU3nTUzcAxNgVtV/rOuOgXlgXLWq59EE4UnFa9a6qAYgjwHOoVYir4GczRFK61OM4In8C6ABmYZsBLWmhwrrN3wSk4SEGUsJaCkYSEmcMoeAZxkUzrNjwygDAECC5oKwUCMdFmOlzwyqjDRZjSLnjlUb5kJ0UXpwUbZgJ1E3pwygnGRTOs2PDKAEQWAuaCsFOIQjFMRAL5tSESawEGsAnmTTRDgC00BsjOKDFiokByUEk4ZVG+ZCdFF6cFG2YCdRN6ccuulxrpFnwygd8yKdEw9aANsyIdQy9aPTEiyCAsU8n9ZYIwGGigiCNuLXJZCs1P8pI2jIp1Q+FQNm5xtSIqPwQCLtsOqgQAIAsBxYx8mDxEUz1FxQgcHVd5qqCGrBVnboGP9o4YTWCyxGYRK8ypWgRiHisLumpixqJbRfNjOgaNq6hlvqMurTxMiiX1WeeFB+Y0lIGZiGeVXjjfDYsXNaJgkv/lDppYlZG09ZiiyM5hR6TShrJKMyt0+VTON4qBgJwaS4ckRHIcYrFTEAfyowxwSW+r/AGb03IMcqGbqlkYJlNBFDzUaJmLDnEpDRcqXwDISxrEGOfBGP9srTNWBUkMTxmtihCnG/QeYOtlBJGReyMjIP8kIV4FsawtCC6cGuaADm1loueWE8ApSgWxrC0QEYNGLrHEGbhRc86BUb6CFxvioCBC4ITRk0OVHpN96hrDJgM1gC6nkpJCznc6LnNAFAJUhIHBE/wAe4IgWwWkczJLtmSsKFwxUxVmurwN3KJXSkguRVjh+ZBJxGNXkZMAE+VGgwiRUefiTKTCIhLMhy5Rb/HghECpa1ExXZ/k5IRFD1rBRYWYNJgxypCGuTjF5/NWNKZggLNXTBIMHy/xWMcQAUaAutCJEC/8AQw+zzrSogmbHMV58TormMs6P+nnHM4hQwLFeQkQ51N4aROgc6L5XeamYilYnSE0emlAwfWhyaKigIbZB+Xh8kNwndHP/ABVgXpqRB1Renhw64CxnnRD3lV1iJ51LKLm0ZlJDf7RX1ZxWLKawIjFdJz0PilmCBJlmGik7IcWSHPihyFKBYPKoOxycZRwhJ6ihTy5TLWAwCDIP8PggESIhPm1KxKESLWTg6Nx+2RSCicL5mEN6ZsnSkQgYQuuqD1KJ2AkhibkHB/Ly3P1Hb56/4hAKhJA2RHKr72wuAYsYyYuF71bXkPcIq6QqwFAEFHMkxOMahIWjoZJNNKWuSYgUW9j3UUiHmBkaI3E0qAnEZpY86vgUJTFAEitQAxARCpCNyHhBCQQkzG0i1ghMYoenFYmVIDGsqFYmtEMTa/C5K/FSE2kGywEcSOdCFyT6EZiPKh2CyiFhS2cRfHClnUqxVpNgZH+CQSpCAGKtftFwQhPOzYUCABAFgPE8WnQ9YRjLkUsI4sZeFkyi041K5YBTxNky58HgCupWIGFo5XcFow6IYQ5lcGGFZ6DnljFBCvAPXSUpuMRTHC0pAPKgEKAgAwAPBbupdAnoIdeGh6XOOIZrMrVSZlguuzmX/wAAoiICL5k4NkYS2pXwCxikMRWmNQgANiCMEMeTA9+K8AOQqSxoZVJRROd0wMF3fh/0SC+bhUWi1SBN9vCihQs57qsV5tKFKznuqxHmUyoKBAmATY3aEjfMiHREvTj6jCw7WXicakpoSeDqO8wUMYmEkJhvMUMmSYIT50bn0vX05gtLtUQJhEznKheoX4WtqFMBK2qfBAXr4GzXNKYpTuxReOf/ANZ48G3YVYzf+jmZ1lj/AGm4Y/34VgXoZQcgJagic4JUxIMJN2MeAIAEq2ArBP4R5uYT6SyoBKgIAYAFAxBICylydcPHZ9XHZ9H5Zr8Vy9WGfE6NVrutJjJk1G5wwbzs8E9q999aKtCakaYymnT++uQXCJSBej8FkKwpSgzTAM1yCmkcXBrGLQ9YMsJ8K7kElwWsKtWSo6kATZjxCdsCoMiLjUq8oBItZOIFIIpFbQkrypVCqeGYrKlMkAkcR4ImVaSXuLSg4kGZ0nN4bc8AMMazIb+/XjLkWagUPIR9H9/KlBIYhEMSnKiwAWuzi+gMsWc0PwCSHokicUy8Q7/KOQSMBpIrOuWDzUkekKzrlw80IDpKoBtUMyPkj0Dwt23AWQzBEDo1exswiXokHmpXFpNqZwgrSzRl2C6oPPLTUKAeoSAFgAy8Jo0nNJpp1bFJUxAj4hErLHFUh5CH5/KiHIll5DKYm3L+2cRKHdhxw619mp9mp9mp9mp9mp9ip9mp9k4DH2aif39UgRQZdTZkiCh9mp9mp9m4DH2an2an2bgMfZqIVBlCyoqJbi1C5iEcn4xQoUKFAhQoUKfvA2QN4kGSlGvGicAe4/ECFChQoUKFCnkiyTBlj+5U9s1/GkbTp/HVy1+z6/7KmJQx9UZw60HksrLJNAwi3QtQjgSu2EZWKtIEMB+Rx27XikCeanSVMnb6wLWr7ZgpkUkPhS2Y5sU6YwQwMZw4+VIN1jfgaUrAIswepbhtOnBWxDZgYSTEp2CZjmFztib0jXD8EYhOA4tM1JqcUaFmkg/NklngYUqljGhWZxUjIlwM6BhQ3jOMhNkYlZYaH+rDZnLRfwS15wqbwY1oJcKM84VtTVYxjGga44tuxJvOTUrG61K7UnCHNzEsOOVWyDAzYUxge9RowByeIowdeGz6/wCxppIkxzoOzSG8Mec0J3CgSAhmlAKiE44elMYkQSxnWa5KhPHbteKRBX0C4qSdFTNczONSpFxATScR3hYaJ1cQSDTsMnFiKTgCNsk8Np04qx9eAUsSkstjQglkBmRGJQ7wy5JeC0B0qUt5lyYYw1oCMGAuG8Xp5FoAG/IKtOZCDDDfOox/FwYLIx5UCUBAcjwS188zEJhgPKgbCaLJckGFI2I8lS/LKmPte9McBWEK5CGMuNqtJSM3NmWWNQJogLvK4bPr/uae3a/jSNp0/jq5a/Z9f9dA5KASL3Gtndq2d2rZ3atndq2d2rZ3atndq2d2rZ3atndqy0XLLCeShAtA9jGJGFbO7Vs7tWzu1bO7Vs7tWzu1bO7Vs7tWzu1bO7VA5KASL3Gtndq2d2rZ3atndq2d2rZ3atndq2d2rZ3atndqUPcgyuExmqBRUhItdStndq2d2rZ3atndq2d2rZ3atndq2d2rZ3atndv/AET/2gAMAwEAAgADAAAAEPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPKLLxuKJFg/PPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPKK6qxAeUL/PLEGIOGFIOPEJCLINPPELDFPPPPPPPPPPPPPKEcfxJ/R1svPBCDGFHDCLFDIJFMAFNDOPPPPPPPPPPPPPPKN1q64CBsc9eICKcOhv8AbYfPbr/PrTnXDwnXjzXHZPvfbr+lM0voPKzEIAuaYlkmbbknwlZY8l3pQR+fVp0Pkl3DedgKeO//APtKZjqO8888O8888+8808888888888888888888888888888888888888+O8z7888K88888888888888888888888888888888886wzTCCCSSwxLK88EccscM8TMcM8cs8MsI8888888888888988U4y+/o888388UBBBBBBTD5yzzzzzyn8888888888888988UtMfcp888518+BKEDKJDDrADDDDDAT88K8888888888988FOOOOo8888Z8+BUDQpGDBoADDDDDAX8A38888888v88988U8R18o888879WDDDDDDDbqALAHCAADkp99999999+88988Cyyyyq8nsd8Jp87888+7cqABSgT7ATe99rt5OKCk+88988U8/z8p/k/v8ApHBQgAAAAFagAwwwwwBzOvffffffffvPPfPFPTPvafPPPPfCQwzxQyw1agAwwwwwE/AHs888888/vPPfPBTjjjqPPPPNPFwgEjwwkFagAwwwwwE/PDfPPPPPPPPPPfPFEpOm6fPPOvPFLAAAAAAFWfvtPf8Ab6Hzzzzzzzzzzzzz/wB9Byyyyj997888c2TOKDDDOzzjFz7bz08888888888888888+8qT8888H888c888oBBBBBBBBBBBB78888888888888888+/vv9988H888U888oDDDDp9a2DDDDv8APPPPPPPPPPPPPPPPPvvvmPOPPPPHPPPKMcMMMMIMMMMMNfPPPPPPPPPPPPPPPPPPPPPALNPPPPLHDHHrnjn8HWljvnvPPPPPPPPPPPPPPPPPPPPPPCBAJPPPPPPPPPPPPPvfvPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPbMMPrNPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPGUAgwAyS/PPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPAY1nx3oQRPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPOJqdjxCAwBYBUvPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPJLnqoQxantMvMOtPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPAYdnHv9fCP1/P/wCjzzzzzzzzzzzzzzzzzzzzzzzzzzwHLLILADILEKhINLHCdLHDDfzzzzzzzzzzzzzzzzzzzzzzz4AfP0CtJLKVYcIg+D4oYMH77zzzzzzzzzzzzzzzzzzzzzz0X9rUCtkYTRdCP8I/9ePGPz7zzzzzzzzzzzzzzzzzzzzzw044442044453zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz//EACsRAQACAQIEBQQDAQEAAAAAAAEAESExUUFhcfEQkaGx8CBQgcEw0eFAYP/aAAgBAwEBPxD7N04iThGlc5TaZcIBg39n0MvE4xtdOEN3CKK1tNDMqqSaX2dQKtBldoKCGl7KlLiarOvSUaI6W1ct6dVeaq5baIGuGJbU1FtMWEV2fs+j39qVOnDX4jgMWTmVOalHMheKUslwElijSoYxls6tIFDQWs8JpYlm85DznKec5bznJ+c71O+TuhO9k76TupO1p2ZOyJ2hO0J2fO052POz52jOwZ2bO3Z2H4KV/M9fEhj4h+5kr5HWV/O9ZX871nwb9z5d+5wcny4zThQDL6xdQFOGjNBB0xYMamGkAW1tK6x5LaXjmoqm2qleMABQlNhx5wMItaWE952PHYjJl1Tdo72O78pzvlHJ7EXedtEP6p+WPCOL2Z6vwjZzdph1o7RIV5UauVGF9xNb3E5RvdGvLOKZ+48bGo1iuOF/KeOO3b3zArT3RgV56abgbt4U+4bTE7W6OXi5kYK0SCrpcoO72vhUCXb+GJcXAt/IlCml8sR2oXG3HXXlCmRhykEvTo40zEAllUS6ATW01d4B1l8QaGvGi+rDREyZKiBd8yOY6MwL5m4FkBFAtqyGTFwgbsRxGeGZpoXjs/TqPFV+WfET4ifET4iPa7EYPtPs/cgYyKrGhFUIUPOYRQFCtbiogcjPCqnrPseN7uSx0+xokoNXx7tINUfFXgviqfFUwBCq7ePcLK8mOJAANiWfxBUNFLyX/wBbey94xmqh5zSwXXGZgu2MXpcRtQr1nzOX0WSc6OniINAKWtZ3Zndmd2Z3Zndmd2YUogErEfuW4jEYilBh2Qja+9O9TvU71O9TvULje3jCWku6n/C2n0e8KIliT4jNXj51dY6ja8+U+Zy+hh9DDzGDYJ4kXRUZoLxv4CChg15eGSs21N617xIjUQUOvg+obV4v6iFDj7UdXr9RqdZ8tt4ikpS7nY/mY1JAr8s5HlnI8s5HlnI8sr1sBjp9OdvB/HiRlQnZoIHPlDiwS0uzPmwOhwBSlEbqLTgABaoKYoyXBCqpSjfIZDkRyFCFeDiFABrbGiRSvTT8R1ev1Gp1ny23gTKjTww/uMAAqxY9Z2zO2Z2zO2Z2zO2Z2zEdRYoF4+pvZe/hRr270uDdGgYzjw+ZyghYkzw2+jahw/mCJZ/CSkpnm8zqz5DaOr1lKrAtoZLPMlO0DIaC0GAlsVpbRdHOU7Q1Os+W2goc+AG8rLBq8V3/AIfVfb6mKoSL2Znav9nbv9nbP9nav9hSjSs6TUg26mclQAidfPTlymiyOVtaS4UpCuvhYA2YveosI6NuXgCyAAOF/SAAFICgdP6PD5jaOr1ikBd4Uq77xnOZhoLTqw5HONcVEknQG+Gg3psVDCwCvNlY1xnT1jKHLRI55Z1hqdZ8ttGlAbK5eZy8bK0cZq6MS6BWZRu1rWcYAumsmL/cRjagvApWdQxA7aqqhqhR5bzKNp0Mt+2JZbQFm2yeq+31N7L38BBFNLq8xPCje/D4nKaDwN68buAgFUpd9JdlddRh8Rt2tsYgtWj8wi9ArwVgibyubyjdzVgb858/9E+f+ifP/RPn/onz/wBEpb7BQyJtPkNo6vX6jU6z5baWSlYzSVRvj/X8Pqvt9TafR7ynZgYBQaFuJwcfVlOzPmcvpvEwYOvgyVrBarLfK8g2PC6OWQ46dI1SrS/gLYij0vAbF/qDlg1T1LPRhNrJV8p6j7k+Y2jq9fqNTrPltvCskmpwTZjzSLJlW076nfU76nfU76nfU76impRbK+pjUkCvyz4Scjyz4SfCSvWwGOn0IAFq0HWGPwMvPwGMFm2E3Oc0g0jAAmVSmqKY9NYjoxidLRMIJhQoLDah4uKYQp5WFAGj8Qw2xg1X9J6j7k+Y2jq9fqNTrPltvGqHQeCfzN7L3gLLoHDiSlriN5OcXDYCsVzmOrcJ8zl9F0jY6/RaKpUuHM5Sl4SnZlOzKdmU7Mp2YEwcfuTTOCPR8SECUha8BBpTXto9IZbFpaY/J4kIejgB0P5kPaUq52idohUYADwaztX+ztX+zt3+ztX+wJkWORSdonaIq2tGscZvlq9X6ARFjhHiQjBaF2vTM7Unak7DnYc7DjluaXROQzkM5DDY0sDV1LRZONie04T2imqP6nIZyH/i9n7ngmbN4aN3UjcDrNTrQ10nrPseNxmW/wA/wGsP5PVf8Ps/eU7RKBCQIVTA1XCypTsz1n2PE7jVK/wGsNPoRYcWcdo4s6Plw4h1+n1X2K9xL3EvcS9xLNyWbkpuSm5L3EvcS9xL3Ey632ZUFBeUArEFGmnC4NW9iR/cqFixUyfh+2eje74ehfagXQhlWXWLToFGVD83AzN5v9wyIYP6hiyta4B5X9pIoN1FXXMev2oBILWdXGWYOJqIUvhhKY/GxSyms+sqnLaEtfZlQGNOiuLvBJFoCiC4sa6sDmDKVyQArA1qDUqnpd0t0UYvFw4IwWjcjpgYCtKgo2tKrhAQAKroBKcGWTQbw8fsuXxVblfk/cesJS6l+GULhCKDnrBS5V00T8MBsSryDG8LshYGxGVcNXiunlOW85g4iItXnWkxYFlo0LgqyFlFU/E5XCih6fYUlEYLZ5Bf0S55MvAdWBlIA7hUZES2K/c/EW7L8oAKJfB4eU5GuUPSJtvUZfOAuSI3lZymS1Ag658OFBAboaX1nEAZPF/UG/sBIqFCwdEuWUw6p6G7C9E4vF5vgAqA3fCNDwQFUIxU0/dPSvbwtUBSRA8vO8RZgQqvWnD/ALAEapDRZ2admnZokpW+CR9GAqq3SXwAoYaxOzREiR1En+RnlpAgCHAgvi2NSRURaOuIiIU2KPLSAkA0AwTnJzkqUCtAWvVg2TALk4nOTnJzkTLV/wBHw200gzQOKNAWwOGGICOja2pyGMZ1iK2AOj4R9T7sBnOQGpzliFSW0iLap2xrxm2CDLR+IW6i4EpOs9V94VbLsuYXelrcImndW1TFdvkxMK618EERrVqGYLLL9LiHiBqDtZ4VjW8z1b/oJYDc6RYR86Z0alCqwEB85qCuqXS26NtJZ0AA4BEAB5sMKDPFzx6sUa3dKfMgYNHJeV576QBEsKW+MdTTtDqxjQjnp1jSUGtPzOQ0r8TDVIGBwPWJKavghKLpqZ9GlQwAVrOQ7RH53/QKaKTmPOcx5zmPOcx5xTVYBopzHnOY85zHnOY84q6t/wDgf//EACoRAQACAQIDCAIDAQAAAAAAAAEAESExUUFh8RAgcYGRobHwUNEwQMHh/9oACAECAQE/EPwrF6qjzgUM68UfNDivjMKBIYxABG6WaVbY1hyQlDwYjbJ+HdLsIM2BLyENpDoboTIV2KcYjClAdiBoAIr4UgrZIdDSj8OFAGXaLe93dJK2RMHjUC0VDGOE4mNWeUVw0vDeUilYBmdgeKTH4b26IbgTwxDV9CeBhEdU9CMqF8HjFXOkXXhE61aXwQoSthwmdGls6EzqadbTqadbTradbTrqddTrqddTrqdVTqqdFZ0VnRWdVTradbTradbTradbTradbTradbTradcTrydUTridUTqidURLKYc0CC4b0moD6RCKFFjiRVyhRjhAlFXWN5xQANOBFRUI2UQZLC6oUzoUyOM5HhMVVhk+aGT5pk/2jg+aZD5pg/2h/wBKHpHGanyT2DjPQ94ZPlhZ/rPVd44fnmj8sK+TvD/uww7ZxJnfjR9H4J5L2Qy/Ghl+NMvP2RtPjTR+BPJWyBj8CHlhwTP/AIItXwJi5GyGbc2QueAVhrisdL0xIqSuMHjLf8GstBCcNFXCqurfB5ThMHJmECgaLaakKy/Qd3RlbuvCcj1Tkeqcj1T6GXh0hzn8T8z4jehXfOCsCC+kymxbIuAgsKMHHG57H89tIGAPF+DBBa6HbVcVA9ndW2ySoAb57apiNYM8GIApGn+IYQWlm1/261/tiExoCs1MJNSpgXBnNbQBoN+09×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” width=”306px” alt=”nlp based chatbot”/>

Where manual customer acquisition may cost up to 5-6 times of money, these bots are the real savior. They help in reducing the cost and maintaining the balance by offering solutions and gathering useful information and timely feedback for more accuracy. Natural Language Processing is a based on deep learning that enables computers to acquire meaning from inputs given by users. In the context of bots, it assesses the intent of the input from the users and then creates responses based on contextual analysis similar to a human being.

Why use NLP chatbots?

Kompose offers ready code packages that you can employ to create chatbots in a simple, step methodology. If you know how to use programming, you can create a chatbot from scratch. If not, you can use templates to start as a base and build from there. When a user punches in a query for the chatbot, the algorithm kicks in to break that query down into a structured string of data that is interpretable by a computer. The process of derivation of keywords and useful data from the user’s speech input is termed Natural Language Understanding (NLU).

This URL returns the weather information (temperature, weather description, humidity, and so on) of the city and provides the result in JSON format. After that, you make a GET request to the API endpoint, store the result in a response variable, and then convert the response to a Python dictionary for easier access. You will get a whole conversation as the pipeline output and hence you need to extract only the response of the chatbot here. For example, PVR Cinemas – a film entertainment public ltd company in India – has such a chatbot to assist the customers with choosing a movie to watch, booking tickets, or searching through movie trailers. Still, all of these challenges are worthwhile once you see your NLP chatbot in action, delivering results for your business.

Ways to Build an NLP Chatbot: Custom Development vs Ready-Made Solutions

As a result, there is a risk of chatbots misinterpreting user inputs and providing inaccurate or irrelevant responses. While advancements in NLP are addressing this challenge, achieving a comprehensive understanding of language nuances remains an ongoing area of improvement for chatbot technology. Machine learning chatbots leverage algorithms and data to learn from user interactions. They use training data to identify patterns and generate responses based on the context. These chatbots can handle a wider range of queries and improve their performance over time as they gather more data and learn from user interactions.

This is a popular solution for vendors that do not require complex and sophisticated technical solutions. And that’s thanks to the implementation of Natural Language Processing into chatbot software. Learn how to build a bot using ChatGPT with this step-by-step article.

However, our chatbot is still not very intelligent in terms of responding to anything that is not predetermined or preset. In terms of the learning algorithms and processes involved, language-learning chatbots generally rely heavily on machine-learning methods, especially statistical methods. They allow computers to analyze the rules governing the structure and meaning of language from data. Apps such as voice assistants and NLP-based chatbots can then use these language rules to process and generate utterances of a conversation. NLP algorithms for chatbot are designed to automatically process large amounts of natural language data. They’re typically based on statistical models, which learn to recognize patterns in the data.

• This tutorial does not require foreknowledge of natural language processing.
• In our case, the corpus or training data are a set of rules with various conversations of human interactions.
• The code samples we’ve shared are versatile and can serve as building blocks for similar chatbot projects.
• It also means users don’t have to learn programming languages such as Python and Java to use a chatbot.
• The final else block is to handle the case where the user’s statement’s similarity value does not reach the threshold value.

A simple bot can handle simple commands, but conversations are complex and fluid things, as we all know. If a user isn’t entirely sure what their problem is or what they’re looking for, a simple but likely won’t be up to the task. In this article, we dive into details about what an NLP chatbot is, how it works as well as why businesses should leverage AI to gain a competitive advantage.

There are many different types of chatbots created for various purposes like FAQ, customer service, virtual assistance and much more. NLP (Natural Language Processing) is a branch of AI that focuses on the interactions between human language and computers. NLP algorithms and models are used to analyze and understand human language, enabling chatbots to understand and generate human-like responses. To a human brain, all of this seems really simple as we have grown and developed in the presence of all of these speech modulations and rules.

Encoder-only Transformers are great at understanding text (sentiment analysis, classification, etc.) because Encoders encode meaningful representations. Decoder-only models are great for generation (such as GPT-3), since decoders are able to infer meaningful representations into another sequence with the same meaning. In the following section, I will explain how to create a rule-based chatbot that will reply to simple user queries regarding the sport of tennis. With the growing pace of technology, companies are now looking for better and more innovative ways to serve their customers. For the past few years, we’ll have been hearing about chat support systems provided by different companies in different domains.

Customer Support System

The combination of topic, tone, selection of words, sentence structure, punctuation/expressions allows humans to interpret that information, its value, and intent. On the next line, you extract just the weather description into a weather variable and then ensure that the status code of the API response is 200 (meaning there were no issues with the request). Next, you’ll create a function to get the current weather in a city from the OpenWeather API. This function will take the city name as a parameter and return the weather description of the city. Put your knowledge to the test and see how many questions you can answer correctly.

Next, we will perform some preprocessing on the corpus and then will divide the corpus into sentences. We have moved so far in the field of technology today and NLP has taken the support system almost everywhere. From search queries to answering relevant topics, it can do many things and they are improvising every day. NLP is not only the solution for the company but also for the customers which means it’s a WIN-WIN for both ends. The market is likely to grow more by $27 Billion USD by the end of 2024 which is currently standing at somewhere around $600 Million USD. Through NLP, it is possible to make a connection between the incoming text from a human being and the system generated response.

Read more about https://www.metadialog.com/ here.

• This increases accuracy and effectiveness with minimal effort, reducing time to ROI.
• Chatbot or chatterbot is becoming very popular nowadays due to their Instantaneous response, 24-hour service, and ease of communication.
• Then it can recognize what the customer wants, however they choose to express it.
• In the above, we have created two functions, “greet_res()” to greet the user based on bot_greet and usr_greet lists and “send_msz()” to send the message to the user.
• You can come back to those when your bot is popular and the probability of that corner case taking place is more significant.
• The rule-based chatbot is taught how to respond to these questions — but the wording must be an exact match.