The first 37 questions are presented below. Other questions and answers to all questions can be found in the video below.

1. What is NLP?
2. Mention the important components in NLP?
3. What are domains are currently using NLP?
4. What is stemming in NLP?
5. What is Lemmatization in NLP?
6. What is tokenization in NLP?
7. What is the difference between stemming and lemmatization?
8. What is NER?
9. Where can NER be used?
10.What is feature extraction?
11.What is the procedure to do feature extraction?
12.What is latent semantic indexing?
13.What is recall?
14.What is precision?
15.What are the metrics used to test NLP models?
16.What is Python?
17.What are popular libraries in Python?
18.What are useful libraries for NLP in Python?
19.What are important terms in NLP?
20.What is TF-IDF?
21.What is POS tagging?
22.What is the difference between NLP and NLU?
23.What makes NLP difficult for beginners?
24.What is ngram in NLP?
25.What are stop words in NLP?
26.Give examples of real-life applications of NLP?
27.What is syntactic analysis?
28.What is semantic analysis?
29.What is NLTK?
30.What is Uni-gram?
31.What is Bi-gram?
32.Can you explain the stemming procedure with an example?
33.Can you explain the Lemmatization procedure with an example?
34.What are regular expressions?
35.What is dependency parsing in NLP?
36.What is pragmatic analysis?
37.Where can NLP be useful?

The post 101 NLP Interview Questions and Answers appeared first on New World : Artificial Intelligence.

Natural Language Processing is a field of computer science that deals with communication between computer systems and humans. It is a technique used in Artificial Intelligence and Machine Learning. It is used to create automated software that helps understand human spoken languages to extract useful information from the data it gets in the form of audio. Techniques in NLP allow computer systems to process and interpret data in the form of natural languages.

NLP can help people with many tasks. Some examples are given below.

Diagnosing: Prediction of diseases based on the patient’s own speech and electronic health records.

Sentiment Analysis: Organizations can determine what customers are feeling about a product or service by extracting information from sources like social media.

Translator: Online translators have never been so successful before NLP was used in that field.

ChatBot: To communicate with the customer like an actual employee.

Classifying emails: To classify emails as spam or ham and stop spams before they even enter the inbox.

Detecting Fake News: To determine if a source is politically biased or accurate, detecting if a news source can be trusted or not.

Intelligent Voice-Driven Interfaces: Apple’s Siri or Android’s Iris are examples of intelligent voice-driven interfaces that use NLP to respond to humans.

Trading Algorithms: Tracking news, reports, comments about financing to sell or buy the stocks automatically.

Recruiting Assistant: Both the search and selection phases of new employees and identifying the skills of potential hires.

Litigation Tasks: To automate routine litigation tasks and help courts save time.

Source: 

The post NLP || Dan Jurafsky || Stanford University appeared first on New World : Artificial Intelligence.

Natural language processing (NLP) deals with the key artificial intelligence technology of understanding complex human language communication. Natural language processing (NLP) is one of the most important technologies of the information age.

Understanding complex language utterances is also a vital part of artificial intelligence. Applications of NLP are everywhere because people communicate almost everything in language: web search, advertisement, emails, customer service, language translation, radiology reports, etc. There is a large variety of underlying tasks and machine learning models powering NLP applications. Recently, deep learning approaches have obtained very high performance across many different NLP tasks. These models can often be trained with a single end-to-end model and do not require traditional, task-specific feature engineering.

This lecture series provides a thorough introduction to the cutting-edge research in deep learning applied to NLP, an approach that has recently obtained very high performance across many different NLP tasks including question answering and machine translation. It emphasizes how to implement, train, debug, visualize, and design neural network models, covering the main technologies of word vectors, feed-forward models, recurrent neural networks, recursive neural networks, convolutional neural networks, and recent models involving a memory component.

Lecture 1 | Natural Language Processing with Deep Learning
Lecture 1 introduces the concept of Natural Language Processing (NLP) and the problems NLP faces today. The concept of representing words as numeric vectors is then introduced, and popular approaches to designing word vectors are discussed.

Lecture 2 | Word Vector Representations: word2vec
Lecture 2 continues the discussion on the concept of representing words as numeric vectors and popular approaches to designing word vectors.

Lecture 3 | GloVe: Global Vectors for Word Representation
Lecture 3 introduces the GloVe model for training word vectors. Then it extends our discussion of word vectors (interchangeably called word embeddings) by seeing how they can be evaluated intrinsically and extrinsically. As we proceed, we discuss the example of word analogies as an intrinsic evaluation technique and how it can be used to tune word embedding techniques. We then discuss training model weights/parameters and word vectors for extrinsic tasks. Lastly, we motivate artificial neural networks as a class of models for natural language processing tasks.

Lecture 4: Word Window Classification and Neural Networks
Lecture 4 introduces single and multilayer neural networks, and how they can be used for classification purposes.

Lecture 5: Backpropagation and Project Advice
Lecture 5 discusses how neural networks can be trained using a distributed gradient descent technique known as backpropagation.

Lecture 6: Dependency Parsing
Lecture 6 covers dependency parsing which is the task of analyzing the syntactic dependency structure of a given input sentence S. The output of a dependency parser is a dependency tree where the words of the input sentence are connected by typed dependency relations.

Lecture 7: Introduction to TensorFlow
Lecture 7 covers Tensorflow. TensorFlow is an open-source software library for numerical computation using data flow graphs. It was originally developed by researchers and engineers working on the Google Brain Team within Google’s Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks research.

Lecture 8: Recurrent Neural Networks and Language Models
Lecture 8 covers traditional language models, RNNs, and RNN language models. Also reviewed are important training problems and tricks, RNNs for other sequence tasks, and bidirectional and deep RNNs.

Lecture 9: Machine Translation and Advanced Recurrent LSTMs and GRUs
Lecture 9 recaps the most important concepts and equations covered so far followed by machine translation and fancy RNN models tackling MT.

Review Session: Midterm Review
This midterm review session covers work vectors representations, neural networks, and RNNs. Also reviewed is backpropagation, gradient calculation, and dependency parsing.

Lecture 10: Neural Machine Translation and Models with Attention
Lecture 10 introduces translation, machine translation, and neural machine translation. Google’s new NMT is highlighted followed by sequence models with attention as well as sequence model decoders.

Lecture 11: Gated Recurrent Units and Further Topics in NMT
Lecture 11 provides a final look at gated recurrent units like GRUs/LSTMs followed by machine translation evaluation, dealing with large vocabulary output, and sub-word and character-based models. It also includes research highlight “Lip reading sentences in the wild.”

Lecture 12: End-to-End Models for Speech Processing
Lecture 12 looks at traditional speech recognition systems and motivation for end-to-end models. Also covered are Connectionist Temporal Classification (CTC) and Listen Attend and Spell (LAS), a sequence-to-sequence based model for speech recognition.

Lecture 13: Convolutional Neural Networks
Lecture 13 provides a mini-tutorial on Azure and GPUs followed by research highlight “Character-Aware Neural Language Models.” Also covered are CNN Variant 1 and 2 as well as a comparison between sentence models: BoV, RNNs, CNNs.

Lecture 14: Tree Recursive Neural Networks and Constituency Parsing
Lecture 14 looks at compositionality and recursion followed by structure prediction with simple Tree RNN: Parsing. Research highlight “Deep Reinforcement Learning for Dialogue Generation” is covered is backpropagation through Structure.

Lecture 15: Coreference Resolution
Lecture 15 covers what is coreference via a working example. It also includes research highlight “Summarizing Source Code”, an introduction to coreference resolution and neural coreference resolution.

Lecture 16: Dynamic Neural Networks for Question Answering
Lecture 16 addresses the question “Can all NLP tasks be seen as question answering problems?”.

Lecture 17: Issues in NLP and Possible Architectures for NLP
Lecture 17 looks at solving language, efficient tree-recursive models SPINN and SNLI, as well as research highlight “Learning to compose for QA.” Also covered are interlude pointer/copying models and sub-word and character-based models.

Lecture 18: Tackling the Limits of Deep Learning for NLP
Lecture 18 looks at tackling the limits of deep learning for NLP followed by a few presentations.

Source: Stanford University School of Engineering

The post Natural Language Processing with Deep Learning | Stanford University appeared first on New World : Artificial Intelligence.

The University of Oxford in the UK teaches a course on Deep Learning for Natural Language Processing and much of the materials for this course are available online for free. (https://machinelearningmastery.com)

This is an advanced course on natural language processing. Automatically processing natural language inputs and producing language outputs is a key component of Artificial General Intelligence. The ambiguities and noise inherent in human communication render traditional symbolic AI techniques ineffective for representing and analysing language data. Recently statistical techniques based on neural networks have achieved a number of remarkable successes in natural language processing leading to a great deal of commercial and academic interest in the field

This is an applied course focusing on recent advances in analysing and generating speech and text using recurrent neural networks. We introduce the mathematical definitions of the relevant machine learning models and derive their associated optimisation algorithms. The course covers a range of applications of neural networks in NLP including analysing latent dimensions in text, transcribing speech to text, translating between languages, and answering questions.

These topics are organised into three high level themes forming a progression from understanding the use of neural networks for sequential language modelling, to understanding their use as conditional language models for transduction tasks, and finally to approaches employing these techniques in combination with other mechanisms for advanced applications. Throughout the course the practical implementation of such models on CPU and GPU hardware is also discussed.

GitHub Link: https://github.com/oxford-cs-deepnlp-2017/lectures

Lecture 1a – Introduction [Phil Blunsom]
This lecture introduces the course and motivates why it is interesting to study language processing using Deep Learning techniques.

Lecture 1b – Deep Neural Networks [Wang Ling]
This lecture revises basic machine learning concepts that students should know before embarking on this course.

Lecture 2a – Word Level Semantics [Ed Grefenstette]
Words are the core meaning bearing units in language. Representing and learning the meanings of words is a fundamental task in NLP and in this lecture the concept of a word embedding is introduced as a practical and scalable solution.

Lecture 2b – Overview of the Practicals [Chris Dyer]
This lecture motivates the practical segment of the course.

Lecture 3 – Language Modelling and RNNs Part 1 [Phil Blunsom]
Language modelling is important task of great practical use in many NLP applications. This lecture introduces language modelling, including traditional n-gram based approaches and more contemporary neural approaches. In particular the popular Recurrent Neural Network (RNN)

Lecture 4 – Language Modelling and RNNs Part 2 [Phil Blunsom]
This lecture continues on from the previous one and considers some of the issues involved in producing an effective implementation of an RNN language model. The vanishing and exploding gradient problem is described and architectural solutions, such as Long Short Term Memory (LSTM), are introduced.

Lecture 5 – Text Classification [Karl Moritz Hermann]
This lecture discusses text classification, beginning with basic classifiers, such as Naive Bayes, and progressing through to RNNs and Convolution Networks.

Lecture 6 – Deep NLP on Nvidia GPUs [Jeremy Appleyard]
This lecture introduces Graphical Processing Units (GPUs) as an alternative to CPUs for executing Deep Learning algorithms. The strengths and weaknesses of GPUs are discussed as well as the importance of understanding how memory bandwidth and computation impact throughput for RNNs.

Lecture 7 – Conditional Language Models [Chris Dyer]
In this lecture we extend the concept of language modelling to incorporate prior information. By conditioning an RNN language model on an input representation we can generate contextually relevant language. This very general idea can be applied to transduce sequences into new sequences for tasks such as translation and summarisation, or images into captions describing their content.

Lecture 8 – Generating Language with Attention [Chris Dyer]
This lecture introduces one of the most important and influencial mechanisms employed in Deep Neural Networks: Attention. Attention augments recurrent networks with the ability to condition on specific parts of the input and is key to achieving high performance in tasks such as Machine Translation and Image Captioning.

Lecture 9 – Speech Recognition (ASR) [Andrew Senior]
Automatic Speech Recognition (ASR) is the task of transducing raw audio signals of spoken language into text transcriptions. This talk covers the history of ASR models, from Gaussian Mixtures to attention augmented RNNs, the basic linguistics of speech, and the various input and output representations frequently employed.

Lecture 10 – Text to Speech (TTS) [Andrew Senior]
This lecture introduces algorithms for converting written language into spoken language (Text to Speech). TTS is the inverse process to ASR, but there are some important differences in the models applied. Here we review traditional TTS models, and then cover more recent neural approaches such as DeepMind’s WaveNet model.

Lecture 11 – Question Answering [Karl Moritz Hermann]

Lecture 12 – Memory [Ed Grefenstette]

Lecture 13 – Linguistic Knowledge in Neural Networks

Source:  Zafarullah Mahmood

The post Oxford Course on Deep Learning for Natural Language Processing appeared first on New World : Artificial Intelligence.

Natural language processing (NLP) deals with the key artificial intelligence technology of understanding complex human language communication. Natural language processing (NLP) is one of the most important technologies of the information age. Understanding complex language utterances is also a crucial part of artificial intelligence. Applications of NLP are everywhere because people communicate most everything in language: web search, advertisement, emails, customer service, language translation, radiology reports, etc. There is a large variety of underlying tasks and machine learning models powering NLP applications. Recently, deep learning approaches have obtained very high performance across many different NLP tasks. These models can often be trained with a single end-to-end model and do not require traditional, task-specific feature engineering.

Ekaterina Kochmar is a research associate at the Computer Laboratory of the University of Cambridge. She works on Automated Language Teaching and Assessment (ALTA) with Professor Ted Briscoe. She has recently completed my Ph.D. at the Natural Language and Information Processing Group, Computer Laboratory. Her research focuses on compositional distributional semantics and the use of machine learning methods in educational NLP. In particular, She investigates the methods of automated error detection and correction, and explore how compositional distributional semantics can be used to detect and correct errors in lexical choice. She is also interested in vocabulary acquisition and in how NLP and ML techniques can help learners of a language acquire and expand their vocabulary in order to read and write in a foreign language.

In 2011, She gained an MPhil Degree in Advanced Computer Science from the University of Cambridge. Her research focused on non-native author profiling and native language identification in texts written by non-native speakers of English. In particular, She investigated how to automatically detect the native language of an anonymous writer using idiosyncrasies and errors in their writing.

She is a member of St John’s College since 2010 and a scholar of the College since 2011. Her studies have been funded by the Cambridge Trusts and Cambridge Assessment.

Before coming to Cambridge, She finished a Master’s Degree in Computational Linguistics at the University of Tuebingen. Her MA project focused on ensemble-based learning and its application to morphological analysis of German. This project was done under the supervision of Professor Erhard Hinrichs and Dr. Dale Gerdemann.

She gained her Diploma in Applied Linguistics from Saint Petersburg State University, where she was supervised by Assistant Professor Irina V. Azarova.

The post Introduction to Natural Language Processing: Ekaterina Kochmar appeared first on New World : Artificial Intelligence.