Task 1: Verb ambiguity in Arabic morphological analysis

Task Description:

Verb ambiguity in Arabic is a challenging problem at all natural language processing levels.
This task is concerned with verb ambiguity which can be in:

(A) Verb type and tense (imperative, past, present).

(B) Active and passive voice.

(C) Verb morphological features (person, number, and gender)

An example for (A): The verb forms تعلم/تعلموا which can be an imperative تَعَلَّمْ/تَعَلَّمُوا, past tense تَعَلَّمَ/تَعَلَّمُوا, or present tense verb تَعْلَمُ/تَعَلَمُوا.

An example for (B): The verb form حمل/يحمل which can be active voice حَمَلَ/يَحْمِلُ, or passive voice حُمٍل/يُحْمَلُ.

An example for (C) : The verb form فعلت which can be first person singular past verb فَعَلْتُ, second person singular masculine past verb فَعَلْتَ, second person singular feminine past verb فَعَلْتِ, or third person singular feminine past verb فَعَلَتْ.

Sub tasks:The task has sub-tasks:

Input: white space tokenized sentence

Task 1.A. Verb tense classification

Output: A list of the sentence tokens, each token is annotated as follows:

O: If the token is not a verb

TENSE: if the token is a verb, where TENSE:=PAST|PRESENT|FUTURE|IMPERATIVE

Task 1.B. Active/passive voice classification

Input: white space tokenized sentence
Output: A list of the sentence tokens, each token is annotated as follows:

O: If the token is not a verb

VOICE: if the token is a verb, where

VOICE:=ACTIVE|PASSIVE

Task 1.C. Verb morphological features classification

Input: a white space tokenized Arabic sentence.

Output: A list of the sentence tokens, each token is annotated as follows:

O: If the token is not a verb

NUMBER-GENDER: if the token is a verb, where

PERSON:=FIRST|SECOND|THIRD

NUMBER:=SINGULAR|DUAL|PLURAL

GENDER:=MASCULINE|FEMININE

Complete Task:

Input: a white space tokenized Arabic sentence.

Output: A list of the sentence tokens, each token is annotated as follows:

O: If the token is not a verb

TENSE-VOICE-PERSON-NUMBER-GENDER: if the token is a verb, where

TENSE:=PAST|PRESENT|FUTURE|IMPERATIVE

VOICE:= ACTIVE|PASSIVE

PERSON:=FIRST|SECOND|THIRD

NUMBER:=SINGULAR|DUAL|PLURAL

GENDER:=MASCULINE|FEMININE

Example:

Input: التركيز على تناول أغذية غنية بحمض الفوليك حيث تشير الدراسات وجود علاقة بين النقص في حمض الفوليك وحالات الإكتئاب كون نقص حمض الفوليك يساهم في إنخفاض مستويات مادة السيروتونين في الدماغ

Output:

التركيزOOOOO
علىOOOOO
تناولOOOOO
أغذيةOOOOO
غنيةOOOOO
بحمضOOOOO
الفوليكOOOOO
حيثOOOOO
تشيرactivepresentthirdpluralfeminine
الدراساتOOOOO
وجودOOOOO
علاقةOOOOO
بينOOOOO
النقصOOOOO
فيOOOOO
حمضOOOOO
الفوليكOOOOO
وحالاتOOOOO
الإكتئابOOOOO
كونOOOOO
نقصOOOOO
حمضOOOOO
الفوليكOOOOO
يساهمactivepresentthirdsingularmasculine
فيOOOOO
إنخفاضOOOOO
مستوياتOOOOO
مادةOOOOO
السيروتونينOOOOO
فيOOOOO
الدماغOOOOO


Data and tools:

later

Important Dates: http://nsurl.org/importantdates/

Results:

Paper submission:

Task Organizers:

Abed Alhakim Freihat, Mourad Abbas