Schoobrary رجوع
العودة إلى البحث
رسائل ماجيستير الانجليزية 2019 027522a3-1fc8-4ada-a047-4007c7cb0126

Positive Unlabelled Learning to Recognize Dishes as Named Entity

التعلم من الأمثلة الصحيحة والمجهولة للتعرف على الأطباق ككيان مسمى

Sherief Abdallah, Aiman Tarek

الجامعة البريطانية في دبي · الامارات

الموضوعات

علوم تطبيقية وتكنولوجية

الملخص

With the growth of social media, there is a need to analyse the user-generated content; especially the text reviews. Online text reviews have a lot of potential and opportunities for both users and business owners. Many researches target analysing text reviews extracting useful info especially Named Entity Recognition.In this research, I focus on extracting food and dish names as a named entity. With the lack of labelled data, I try to overcome the cold start and avoid manual labelling by building a lookup table from a dictionary.I work with Yelp dataset, going through each text review, using each noun as a candidate, label the positive samples using the aforementioned lookup table, then using Positive Unlabelled learning techniques to recognise more entities within the unlabelled data, by predicting the probability for each candidate. I considered the surrounding words; preceding and following in building the model, as well as Part of Speech tag for each. To eliminate duplicates due to repeated candidates from different reviews or sentences, I calculate the average and represent each candidate entity only once.The results show how we can automate entity recognition process, using dictionaries and machine learning techniques and achieve an acceptable accuracy of 67% and boost the newly discovered entities by around 15% using Positive Unlabelled learning over automatically build lookup table.This research has the potential to be extended to other topics other than food and dish names, also it acts as a framework and algorithm independent.

التعريف والنوع

رقم الوثيقة
027522a3-1fc8-4ada-a047-4007c7cb0126
رقم العقد
0
نوع الوسائط
Crawler
نوع المحتوى
الرسائل العلمية
صيغة المصدر
رسائل ماجيستير
نوع الملف
pdf text
أسماء الملفات
2104109_1.pdf

بيانات النشر

ترجمة العنوان
التعلم من الأمثلة الصحيحة والمجهولة للتعرف على الأطباق ككيان مسمى
ألقاب المؤلفين
[{"name_ar":" Sherief Abdallah","title_ar":"اشراف","title_en":"Supervision"},{"name_ar":"Aiman Tarek","title_ar":"اعداد","title_en":"Preparation"}]
اللغة
English

المصدر والدورية

اسم المصدر
Positive Unlabelled Learning to Recognize Dishes as Named Entity

المحتوى والصفحات

عدد الصفحات
0

إشراف وإعداد

الإشراف
Sherief Abdallah
الإعداد
Aiman Tarek

الاقتباسات الببليوغرافية

APA

Sherief Abdallah و Aiman Tarek. (2019). Positive Unlabelled Learning to Recognize Dishes as Named Entity. أطروحة(رسائل ماجيستير). الجامعة البريطانية في دبي. الامارات .

MLA

Sherief Abdallah و Aiman Tarek. Positive Unlabelled Learning to Recognize Dishes as Named Entity. 2019. الجامعة البريطانية في دبي، رسائل ماجيستير.