Signal and Data Processing
پردازش علائم و دادهها
JSDP
Engineering & Technology
http://jsdp.rcisp.ac.ir
1
admin
2538-4201
2538-421X
10.52547/jsdp
1
8888
fa
jalali
1396
12
1
gregorian
2018
3
1
14
4
online
1
fulltext
fa
بهبود شناسایی موجودیتهای نامدار فارسی با استفاده از کسره اضافه
Improving Named Entity Recognition Using Izafe in Farsi
مقالات پردازش متن
Paper
پژوهشي
Research
<p dir="RTL"><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">تشخیص موجودیتهای</span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;"> نامدار</span></span></strong> <strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">فرآیندی است که در آن اسامی اشخاص، مکانها</span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">(شهرها، کشورها، دریاها و غیره)</span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">، سازمانها(شرکتهای خصوصی و دولتی، نهادهای بینالمللی و غیره)</span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">،</span></span></strong> <strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">تاریخ، واحدهای پولی و درصدها در یک متن شناسایی میشوند. تشخیص موجودیتهای نامدار نقشی اساسی در سامانههای پرسش و پاسخ، خلاصهسازی، </span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">ترجمه ماشینی، برچسبزن نقش معنایی، جستجوی معنایی، استخراج رابطه و شناسایی نقل قول دارند.</span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;"> در این مقاله ابتدا فرهنگ واژگان موجودیتهای سازمان، مکان و اشخاص با استفاده از محتوای ویکیپدیای فارسی استخراج شد</span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">؛ </span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">سپس با استفاده از قواعد، سامانه پیشنهادی توسعه یافت</span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">. در ادامه دقت شناسایی موجودیتهای نامدار با استفاده از کسره اضافه که یکی از ویژگیهای مهم زبان فارسی است، بهبود داده شد. </span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;">جهت ارزیابی سامانه تعداد 42 هزار کلمه از پیکره بی جنخان بهصورت دستی برچسب زده شدند و معیار </span></span></strong><strong><span dir="LTR"><span style="font-family:times new roman,serif;"><span style="font-size:8.0pt;">F</span></span></span></strong><strong><span style="font-family:b nazanin;"><span style="font-size:10.0pt;"> 92/81 درصد بهدست آمد. نتایج حاکی از آن است که با استفاده از کسره اضافه در سامانههای تشخیص موجودیت دقت آنها بهطور قابل ملاحظهای افزایش مییابد.</span></span></strong><br>
</p>
<p><strong>Named entity recognition is a process in which the people’s names, name of places (cities, countries, seas, etc.) and organizations (public and private companies, international institutions, etc.), date, currency and percentages in a text are identified. Named entity recognition plays an important role in many NLP tasks such as semantic role labeling, question answering, summarization, machine translation, semantic search, and relation extraction and quotation recognition systems. Named entity recognition in the Persian language is far more complex and more difficult than English. In English texts usually proper nouns begin with capital letters and this feature makes it easy to identify named entities, but this feature is absent in Persian language texts. To create a named entity recognition system, generally three methods are being used which include rule-based, machine-learning-based and hybrid methods. Each of these methods has its own advantages and disadvantages. Lack of named entity labeled data is the greatest challenge in Persian text. Because of this problem usually rule-based methods used to extract entities.</strong><br>
<strong>In this paper firstly, the dictionary of organizations, places and people were extracted from Wikipedia. Wikipedia is one of the best sources for extracting entities in which more than 200000 Farsi-named entities are known to exist. The proposed algorithm classify each Wikipedia article title by using its categories. Each of Wikipedia titles has several categories that can be used to partially identify the named entity type. Then named entity recognition accuracy (precision) was increased using the rules. These rules can be divided into 3 categories that include morphological rules, adjacency and text patterns. The most important rules are adjacency rules. By using these rules the type of entity with the word nearby each entity (like Mr, Mrs , …) can be identified. To evaluate the system, 42000 tokens of BijanKhan corpus were manually annotated (labeled). Early F-measure was calculated 78.79 percent. In continue, named entity recognition accuracy (precision) improved using izāfe which is one of the important Persian language features and 81.94 percent for F-measure was achieved. The results showed that using izāfe in named entity recognition systems significantly increases their accuracy.</strong><br>
</p>
تشخیص موجودیتهای نامدار پردازش زبان طبیعی, مبتنی بر قاعده, ویکیپدیا, کسره اضافه
Named Entity Recognition, Natural Language Processing, Rule Based, Wikipedia, Izafe
43
54
http://jsdp.rcisp.ac.ir/browse.php?a_code=A-10-806-1&slc_lang=fa&sid=1
mohammad
َAbdoos
محمد
عبدوس
mohammadabdous@comp.iust.ac.ir
10031947532846006002
10031947532846006002
Yes
دانشگاه علم و صنعت ایران و آزمایشگاه پردازش و تحلیل متن شرکت آرمان رایان شریف
behrooz
manaei
بهروز
مینایی بیدگلی
B_minaei@iust.ac.ir
10031947532846006003
10031947532846006003
No
دانشگاه علم و صنعت ایران