A Tutorial on Sentence Semantics Using Lambek Pregroup Grammar and Categorical Quantum Protocols /
تخصص البحث : Natural Language Processing
هندسة اللغة: / عدد(1) -مجلد (3) - أبريل 2016
تاريخ تقديم البحث 03/05/2016
تاريخ قبول البحث 03/05/2016
عدد صفحات البحث 11
Prof. M. Adeeb Ghonaimy( adeeb.ghonaimy@eng.asu.edu.eg - ) - مؤلف رئيسي
Sentence semantics depends mainly on two basic principles: the principle of compositionality [Partee et al, 1990] (sometimes called Frege’s principle), and the distributional principle. Briefly, the compositionality principle states that the meaning of a complex expression is a function of the meaning of the parts and the syntactic rules by which they are combined. The distributional principle is that words that occur in a similar context tend to have similar meaning [Turney and Pentel, 2010]. In this tutorial, the syntax used in compositionality is Lambek pregroup grammar [Lambek, 2006]. In order to integrate the above concepts together, categorical quantum protocols were used [Abramsky, and Coecke; 2004] to develop a categorical compositional distributional model of meaning [Grefenstette and Sadrzadeh, 2011][Coecke, et al, 2010] [Kartsaktis, 2014]. This model is sometimes abbreviated as DisCoCat model. This tutorial gives outline for this model explaining the basic elements of the principles involved including Lambek pregroup grammar and categorical quantum protocols.
Building a POS-Annotated Corpus for Egyptian Children /
تخصص البحث : Large Corpora
هندسة اللغة: / عدد(1) -مجلد (3) - أبريل 2016
تاريخ تقديم البحث 03/05/2016
تاريخ قبول البحث 03/05/2016
عدد صفحات البحث 12
Heba Salama( Heba.salama.slp@gmail.com - ) - مؤلف رئيسي
Sameh Alansary( Sameh.Alansary@bibalex.org - )
POS annotated corpus, CHILDES database
In this paper, we present an attempt at developing a POS annotated corpus for Egyptian children.Linguistic annotation of the corpora provides researchers with better means for exploring the development of grammatical constructions and their usage.This is an initial annotated corpus for Egyptian children. It implements part of speech tag (POS) especially a morphologically annotated corpus of spoken Arabic child language.POS are made in ”%mor” ’morphology’ tiers manually. Coding language transcripts for computer analysis is a daunting task. It approximately took 170 hours, and thus manual annotation focused on a particular child.The POS coding process started with a purely manually annotation of 2701words. 1380 words annotated for an adultand 1321 annotated words for the child was handled. Annotated child language proved to be challenging, and time consuming task.The MOR grammar exists in many languages, such as English, French, German, Japanese, Cantonese, Hebrew, and they are generated automatically, the CLAN has the automatic coding system ”MOR program”. In Egyptian Arabic, this is not applied for two reasons. First, there is no previous Egyptian Arabic work done on a constructing system for such a representation. Second, morphology of Egyptian Arabic is very rich and different from other languages. Thus, their rules cannot be applied to Arabic. In the two Arabic studies of Qatari and Emirati languages, semi-automatic and mini automatic MOR is used.Finally,certain applications of linguistic analysis commands are provided by using CLAN software. The analyses include frequency counts, word searches, co-occurrence analyses; MLU (mean length of utterance) counts and analyzes specified pairs of utterances. Transcript data provide some morphological analysis, such as mean length of utterance (MLU) counts, lexical analysis, such as frequency (FREQ) count, syntactic analysis, such as searching the data for specified combinations of words or complex string patterns (COMBO) count, as well as the discourse and interactional analysis, such as analyzes specified pairs of utterances (CHIP) count.
BASMA: BibAlex Standard Arabic Morphological Analyzer /
تخصص البحث : Natural Language Processing
هندسة اللغة: / عدد(1) -مجلد (3) - أبريل 2016
تاريخ تقديم البحث 03/05/2016
تاريخ قبول البحث 03/05/2016
عدد صفحات البحث 10
Sameh Alansary( Sameh.Alansary@bibalex.org - ) - مؤلف رئيسي
Arabic morphology poses special challenges to computational natural language processing systems. Its rich morphology and the highly complex word formation process of roots and patterns make computational approaches to Arabic very challenging. Morphological analyzers are preprocessors for text analysis. This paper sheds the light on BASMA-Tool (BibAlex Standard Arabic Morphological Analyzer) that has been initiated at Bibliotheca Alexandrina (BA). The BASMA tool is based on Buckwalter Arabic Morphological Analyzer (BAMA). It focuses on fixing its problems, adding a set of useful morphological features that BAMA does not provide, and disambiguating its multiple solutions. This is done depending on a well training data and a hybrid system (Rule based and memory based). Precision and Recall are the evaluation measures used to evaluate BASMA tool. At this point, precision measurement was 93.37% while recall measurement was 96.9%. The percentages are expected to rise by implementing the improvements while working on larger amounts of data.
The subject of this study is to identify unknown speakers particularly from their speaking tempo represented in Speech Rate SR and Articulation Rate AR as temporal parameters. The fundamental goal of this study, on the acoustical level, is to prove acoustically that every speaker has a significant speech rate SR and articulation rate AR through which the unknown speaker can be discriminated and to investigate which of them (SR or AR) could be of more benefit for identifying unknown speakers and to what extent. Also, the present study is essentially concerned, on the perceptual level, with listeners’ perceptual abilities in perceiving and differentiating different speaking tempo for identifying unknown speakers in order to utilize this exceptional ability in forensic speaker identification FSI; aiming to provide some useful acoustical and perceptual data to be used in forensic phonetic filed. The most important characteristic of the temporal aspects of speech, that they are not easily disguised or imitated by accent or fundamental frequency leveling; so they could be useful for identifying unknown speakers particularly in forensic phonetic field. The speech rate SR and articulation rate AR of ten unknown speakers / informants of colloquial Arabic are calculated. The speakers were recorded while talking spontaneously for a radio program. Only 30 seconds of speech are cut for each speaker from the entire episode. After that 60 naïve listeners are asked to listen carefully to the 10 unknown informants in order to mark the fastest speaker and the slowest speaker depending only on their ears.
جميع البيانات التي يتم تسجيلها على النظام هي ملك للجهة صاحبة هذه البيانات
لا يتم الاطلاع على هذه البيانات من قبل مهندسي المركز إلا للضرورة القصوى ولغرض الدعم الفني وبالاتفاق مع الجهة صاحبة البيانات شفوياً أو كتابياً
لا يتم إعطاء أي بيان من بيانات النظام لأي فرد او جهة فرعية تنتمي للجهة صاحبة البيانات او لأي جهة أخرى إلا بموافقة كتابية من الجهة صاحبة البيانات
يمكن استخدام البيانات المسجلة على النظام بهدف عمل إحصائيات يستفاد منها فى قياس اداء النظام وكفاءة استخدامه من قبل مستخدميه
يتم تأمين جميع البيانات الخاصة بالنظام من خلال تأمين الحاسب الخادم الذي يستضيف البيانات ومن خلال تأمين انتقال البيانات بين جهاز المستخدم والحاسب الخادم وكذلك تأمين واجهة النظام التي يستخدمها المستخدم
كل مستخدم للنظام مسئول مسئولية كاملة عن كلمة المرور الخاصة به وعليه اتخاذ كافة الاحتياطات الممكنة حتى لا يستطيع أى شخص آخر الحصول عليها
تسجيل دخول 
Download Paper
