• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¸»¹¶Ä¡ ÀÚ¿ø Èñ¼Ò¼º¿¡ µû¸¥ Åë°èÀû ¼öÁö ½ÅÈ£ ¹ø¿ª ¹®Á¦ÀÇ ÇØ°á
¿µ¹®Á¦¸ñ(English Title) Addressing Low-Resource Problems in Statistical Machine Translation of Manual Signals in Sign Language
ÀúÀÚ(Author) ¹ÚÇÑö   ±èÁ¤È£   ¹ÚÁ¾Ã¶   Hancheol Park   Jung-Ho Kim   Jong C. Park  
¿ø¹®¼ö·Ïó(Citation) VOL 44 NO. 02 PP. 0163 ~ 0170 (2017. 02)
Çѱ۳»¿ë
(Korean Abstract)
Åë°èÀû ±â°è ¹ø¿ªÀ» ÀÌ¿ëÇÑ ±¸¾î-¼öÈ­ ¹ø¿ª ¿¬±¸°¡ È°¹ßÇØÁü¿¡µµ ºÒ±¸ÇÏ°í ¼öÈ­ ¸»¹¶Ä¡ÀÇ ÀÚ¿ø Èñ¼Ò¼º ¹®Á¦´Â ÇØ°áµÇÁö ¾Ê°í ÀÖ´Ù. º» ¿¬±¸´Â ¼öÈ­ ¹ø¿ªÀÇ Ã¹ ¹ø° ´Ü°è·Î½á Åë°èÀû ±â°è ¹ø¿ªÀ» ÀÌ¿ëÇÑ ±¸¾î-¼öÁö ½ÅÈ£ ¹ø¿ª¿¡¼­ ¸»¹¶Ä¡ ÀÚ¿ø Èñ¼Ò¼ºÀ¸·ÎºÎÅÍ ±âÀÎÇÏ´Â ¹®Á¦Á¡µéÀ» ÇØ°áÇÒ ¼ö ÀÖ´Â ¼¼ °¡Áö Àüó¸® ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. º» ¿¬±¸¿¡¼­ Á¦¾ÈÇÏ´Â ¹æ¹ýÀº 1) ±¸¾î ¹®ÀåÀÇ Æз¯ÇÁ·¹ÀÌ¡À» ÅëÇÑ ¸»¹¶Ä¡ È®Àå¹æ¹ý, 2) ±¸¾î ´Ü¾îÀÇ Ç¥Á¦¾îÈ­¸¦ ÅëÇÑ °³º° ¾îÈÖ ÃâÇö ºóµµ Áõ°¡ ¹× ±¸¾î Ç¥ÇöÀÇ ¹ø¿ª °¡´É¼ºÀ» Çâ»ó½ÃÅ°´Â ¹æ¹ý, ±×¸®°í 3) ¼öÁö Ç¥ÇöÀ¸·Î Àü»çµÇÁö ¾Ê´Â ±¸¾îÀÇ ±â´É¾î Á¦°Å¸¦ ÅëÇÑ ±¸¾î-¼öÁö Ç¥Çö °£ ¹®Àå ¼ººÐÀ» ÀÏÄ¡½ÃÅ°´Â ¹æ¹ýÀÌ´Ù. ¼­·Î ´Ù¸¥ Ư¡À» Áö´Ñ ¿µ¾î-¹Ì±¹ ¼öÈ­ º´·Ä ¸»¹¶Ä¡µéÀ» ÀÌ¿ëÇÑ ½ÇÇè¿¡¼­ °¢ ¹æ¹ý·ÐµéÀÌ ´Üµ¶À¸·Î ¾²ÀÏ ¶§¿Í Á¶ÇյǾî ÇÔ²² »ç¿ëµÇ¾úÀ» ¶§ ¸ðµÎ ¸»¹¶Ä¡ÀÇ Á¾·ù¿Í °ü°è¾øÀÌ ¹ø¿ª ¼º´ÉÀ» °³¼±½Ãų ¼ö ÀÖ´Ù´Â °ÍÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Despite the rise of studies in spoken to sign language translation, low-resource problems of sign language corpus have been rarely addressed. As a first step towards translating from spoken to sign language, we addressed the problems arising from resource scarcity when translating spoken language to manual signals translation using statistical machine translation techniques. More specifically, we proposed three preprocessing methods: 1) paraphrase generation, which increases the size of the corpora, 2) lemmatization, which increases the frequency of each word in the corpora and the translatability of new input words in spoken language, and 3) elimination of function words that are not glossed into manual signals, which match the corresponding constituents of the bilingual sentence pairs. In our experiments, we used different types of English-American sign language parallel corpora. The experimental results showed that the system with each method and the combination of the methods improved the quality of manual signals translation, regardless of the type of the corpora.
Å°¿öµå(Keyword) ¼öÈ­ ¹ø¿ª   ¼öÁö ½ÅÈ£   Åë°èÀû ±â°è ¹ø¿ª   ¸»¹¶Ä¡ ÀÚ¿ø Èñ¼Ò ¹®Á¦   sign language translation   manual signals   statistical machine translation   low-resource problems  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå