Pinned Repositories
Boolean-Retrieval-Model
The objective of this assignment is to make you understand how different indexes work in retrieving different query from a collection. You will create Inverted index and positional index for a set of collection to facilitate Boolean Model of IR. Inverted files and Positional files are the primary data structure to support the efficient determination of which documents contain specified terms and at which proximity. You also learn to process simple Boolean expression queries through this assignment. Datasets You are given two textual dataset for building inverted and positional index on it. Your dictionary must be written to disk, for each word in the lexicon you must store a file offset to the corresponding posting list, and finally, you should process the raw text collection only once (many real-word collections are so big that the cost of multiple scans is prohibitive). For the Quran dataset, each verse constitutes a document. For the Hadeeth dataset, each hadeeth constitutes a document. Query Processing In this assignment, all you need to implement an information retrieval model called Boolean Information Retrieval Model with some simplified assumptions. You will be provided with a bunch of overly simplified documents collection (corpus), you need to implement a simplified Boolean users queries that can only be formed by joining three terms (t1, t2 and t3) with ( AND, OR and NOT) Boolean operators. For example a user query may be of the form (t1 AND t2 AND t3). For positional queries, the query text contains “/” along with a k intended to return all documents that contains t1 and t2, k words apart. For /0 (zero) means phrase or adjacent terms. Basic Assumption for Boolean Retrieval Model 1. An index term (word) is either present (1) or absent (0) in the document. A dictionary contains all index terms. 2. All index terms provide equal evidence with respect to information needs. ( No frequency count necessary, but in next assignment it can be) 3. Queries are Boolean combinations of index terms at max 3. 4. Boolean Operators (AND, OR and NOT) are allowed. For examples: X AND Y: represents doc that contains both X and Y X OR Y: represents doc that contains either X or Y NOT X: represents the doc that do not contain X 5. Queries of the type X AND Y / 3 represents doc that contains both X and Y and 3 words apart. As we discussed during the lectures, we will implement a Boolean Model by creating a posting list of all the terms present in the documents. You are free to implement a posting list with your choice of data structures; you are only allowed to preprocess the text from the documents in term of tokenization in which you can do case folding and stop-words removal but no-stemming. The stop word list is also provided to you in assignments files. Your query processing routine must address a query parsing, evaluation of the cost, and through executing it to fetch the required list of documents. A command line interface is simply required to demonstrate the working model. You are also provided by a set of 10 queries, for evaluating your implementation. Coding can be done
BrainTeaserGame
Distributed_filemanagement_System_Blockchain
FlapPyBird
A Flappy Bird Clone using python-pygame
how-to-create-your-own-haarcascade
LIvecast
Livestream
machine_learning_examples
A collection of machine learning examples and tutorials.
namanr.github.io
Tic-Tac-Toe_Android
naman2716's Repositories
naman2716/Tic-Tac-Toe_Android
naman2716/Boolean-Retrieval-Model
The objective of this assignment is to make you understand how different indexes work in retrieving different query from a collection. You will create Inverted index and positional index for a set of collection to facilitate Boolean Model of IR. Inverted files and Positional files are the primary data structure to support the efficient determination of which documents contain specified terms and at which proximity. You also learn to process simple Boolean expression queries through this assignment. Datasets You are given two textual dataset for building inverted and positional index on it. Your dictionary must be written to disk, for each word in the lexicon you must store a file offset to the corresponding posting list, and finally, you should process the raw text collection only once (many real-word collections are so big that the cost of multiple scans is prohibitive). For the Quran dataset, each verse constitutes a document. For the Hadeeth dataset, each hadeeth constitutes a document. Query Processing In this assignment, all you need to implement an information retrieval model called Boolean Information Retrieval Model with some simplified assumptions. You will be provided with a bunch of overly simplified documents collection (corpus), you need to implement a simplified Boolean users queries that can only be formed by joining three terms (t1, t2 and t3) with ( AND, OR and NOT) Boolean operators. For example a user query may be of the form (t1 AND t2 AND t3). For positional queries, the query text contains “/” along with a k intended to return all documents that contains t1 and t2, k words apart. For /0 (zero) means phrase or adjacent terms. Basic Assumption for Boolean Retrieval Model 1. An index term (word) is either present (1) or absent (0) in the document. A dictionary contains all index terms. 2. All index terms provide equal evidence with respect to information needs. ( No frequency count necessary, but in next assignment it can be) 3. Queries are Boolean combinations of index terms at max 3. 4. Boolean Operators (AND, OR and NOT) are allowed. For examples: X AND Y: represents doc that contains both X and Y X OR Y: represents doc that contains either X or Y NOT X: represents the doc that do not contain X 5. Queries of the type X AND Y / 3 represents doc that contains both X and Y and 3 words apart. As we discussed during the lectures, we will implement a Boolean Model by creating a posting list of all the terms present in the documents. You are free to implement a posting list with your choice of data structures; you are only allowed to preprocess the text from the documents in term of tokenization in which you can do case folding and stop-words removal but no-stemming. The stop word list is also provided to you in assignments files. Your query processing routine must address a query parsing, evaluation of the cost, and through executing it to fetch the required list of documents. A command line interface is simply required to demonstrate the working model. You are also provided by a set of 10 queries, for evaluating your implementation. Coding can be done
naman2716/BrainTeaserGame
naman2716/Distributed_filemanagement_System_Blockchain
naman2716/FlapPyBird
A Flappy Bird Clone using python-pygame
naman2716/how-to-create-your-own-haarcascade
naman2716/LIvecast
naman2716/Livestream
naman2716/machine_learning_examples
A collection of machine learning examples and tutorials.
naman2716/namanr.github.io
naman2716/Natural-Langauge-Prosessing
Natural Language Processing
naman2716/opencv
Open Source Computer Vision Library
naman2716/Python_plays_flappy_birds
naman2716/Q_learning
naman2716/q_learning_player_env
naman2716/react-native-grid-image-viewer
A grid display for multiple images which you can view on clicking in fullscreen mode and swipe through.
naman2716/RealTime-Attendence-Using-Face-Recognition
Using Realtime Face Recognition, recognised face and marked to that for that particular date as present.
naman2716/recommendation_system
naman2716/Self_Driving_On-_Carla_Simulations
naman2716/Single_Shot_Detection
naman2716/single_shot_detection_video
naman2716/smile_detector
naman2716/TensorFlow-Object-Detection-on-the-Raspberry-Pi
A tutorial showing how to set up TensorFlow's Object Detection API on the Raspberry Pi
naman2716/Text_Clssification
naman2716/text_determination
naman2716/twitter_post_determiner
naman2716/Video_calling_android
naman2716/WeatherApp_Android
naman2716/youtube_livestreaming
naman2716/youtube_videoUpload