- 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.
- Explain latent dirichlet allocation – where is it typically used ?
- How will you build an auto suggestion feature for a messaging app or google search?
- You are building a natural language search box for a website. How do you accommodate spelling errors?
- What order of Markov assumption does n-grams model make ?
- How is long term dependency maintained while building a language model?
- What is the significance of n-grams in a language model ?
- How do you generate text using a Hidden Markov Model (HMM) ?
- 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 are the different ways of representing documents ?
- What are knowledge graphs? When would you need a knowledge graph over say a database to store information?
- What is the difference between word2Vec and Glove ?
- What is the difference between stemming and lemmatisation?
- 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?
- What are the advantages and disadvantages of using naive bayes for spam detection?
- What are the different independence assumptions in hMM & Naive Bayes ?
- 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 do you train a hMM model in practice ?
- How many parameters are there for an hMM model?
- Where would you not want to remove stop words ?
- Why is smoothing applied in language model ?
- 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?
- What are some knowledge graphs you know. What is different between these ?
- What can you say about the most frequent and most rare words ? Why are they important or not important ?
- What is negative sampling when training the skip-gram model ?
- Given a bigram language model, in what scenarios do we encounter zero probabilities? How Should we handle these situations ?
- How to measure the performance of the language model ?
- What is PMI ?
- How do you design a system that reads a natural language question and retrieves the closest FAQ answer?
- 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 ?
- How do you find the most probable sequence of POS tags from a sequence of text?
- How do you deal with dataset imbalance in a problem like spam filtering ?
- What would you care more about – precision or recall for spam filtering problem?
- How will you build the automatic/smart reply feature on an app like gmail or linkedIn?
- How do you deal with out of vocabulary words during run time when you build a language model ?
- 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 are popular ways of dimensionality reduction in NLP tasks ? Do you think this is even important ?
- What are the advantages and disadvantages of using Rule based approaches in NLP?
- What is the state of the art technique for Machine Translation ?
- What is a language model ? How do you create one ? Why do you need one ?
- What are common tools for speech recognition ? What are the advantages and disadvantages of each?
- What is speaker segmentation in speech recognition ? How do you use it ?
- Why are bigrams or any n-grams important in NLP(task like sentiment classification or spam detection) or important enough to find them explicitly?
- 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?
- You have come up with a Spam classifier. How do you measure accuracy ?
- What are some common tools available for NER ? Named Entity Recognition ?
- What is the difference between translation and transliteration
- What is the difference between paraphrasing and textual entailment ?
- What is shallow parsing
- Which is better to use while extracting features character n-grams or word n-grams? Why?
- You want to find food related topics in twitter – how do you go about it ?
- 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?