- What order of Markov assumption does n-grams model make ?
- Can you find the antonyms of a word given a large enough corpus? For ex. Black => white or rich => poor etc. If yes then how, otherwise justify your answer.
- What is the difference between word2Vec and Glove ?
- What are common tools for speech recognition ? What are the advantages and disadvantages of each?
- What are some common tools available for NER ? Named Entity Recognition ?
- What are knowledge graphs? When would you need a knowledge graph over say a database to store information?
- What can you say about the most frequent and most rare words ? Why are they important or not important ?
- How many parameters are there for an hMM model?
- What are the different independence assumptions in hMM & Naive Bayes ?
- How do you deal with out of vocabulary words during run time when you build a language model ?
- What is the significance of n-grams in a language model ?
- What is the difference between stemming and lemmatisation?
- Explain latent dirichlet allocation – where is it typically used ?
- Suppose you build word vectors (embeddings) with each word vector having dimensions as the vocabulary size(V) and feature values as pPMI between corresponding words: What are the problems with this approach and how can you resolve them ?
- What are the advantages and disadvantages of using naive bayes for spam detection?
- Why is smoothing applied in language model ?
- What is a language model ? How do you create one ? Why do you need one ?
- What is speaker segmentation in speech recognition ? How do you use it ?
- What would you care more about – precision or recall for spam filtering problem?
- Where would you not want to remove stop words ?
- How do you find the most probable sequence of POS tags from a sequence of text?
- What are the advantages and disadvantages of using Rule based approaches in NLP?
- How do you design a system that reads a natural language question and retrieves the closest FAQ answer?
- You are trying to cluster documents using a Bag of Words method. Typically words like if, of, is and so on are not great features. How do you make sure you are leveraging the more informative words better during the feature Engineering?
- What are the different ways of representing documents ?
- What is the difference between paraphrasing and textual entailment ?
- You want to find food related topics in twitter – how do you go about it ?
- What is the state of the art technique for Machine Translation ?
- What are popular ways of dimensionality reduction in NLP tasks ? Do you think this is even important ?
- What is shallow parsing
- How do you train a hMM model in practice ?
- How can you increase the recall of a search query (on search engine or e-commerce site) result without changing the algorithm ?
- You are given some documents and asked to find prevalent topics in the documents – how do you go about it ?
- What will happen if you do not convert all characters to a single case (either lower or upper) during the pre-processing step of an NLP algorithm?
- Which is better to use while extracting features character n-grams or word n-grams? Why?
- Why are bigrams or any n-grams important in NLP(task like sentiment classification or spam detection) or important enough to find them explicitly?
- What is the difference between translation and transliteration
- What are some knowledge graphs you know. What is different between these ?
- Say you’ve generated a language model using Bag of Words (BoW) with 1-hot encoding , and your training set has lot of sentences with the word “good” but none with the word “great”. Suppose I see sentence “Have a great day” p(great)=0.0 using this language model. How can you solve this problem leveraging the fact that good and great are similar words?
- How is long term dependency maintained while building a language model?
- What is negative sampling when training the skip-gram model ?
- You are building a natural language search box for a website. How do you accommodate spelling errors?
- Given a bigram language model, in what scenarios do we encounter zero probabilities? How Should we handle these situations ?
- Given the following two sentences, how do you determine if Teddy is a person or not? “Teddy bears are on sale!” and “Teddy Roosevelt was a great President!”
- What is PMI ?
- How do you generate text using a Hidden Markov Model (HMM) ?
- How to measure the performance of the language model ?
- How do you deal with dataset imbalance in a problem like spam filtering ?
- How will you build the automatic/smart reply feature on an app like gmail or linkedIn?
- If you don’t have a stop-word dictionary or are working on a new language, what approach would you take to remove stop words?
- Suppose you are modeling text with a HMM, What is the complexity of finding most the probable sequence of tags or states from a sequence of text using brute force algorithm?
- You have come up with a Spam classifier. How do you measure accuracy ?
- How will you build an auto suggestion feature for a messaging app or google search?