What are the major open problems in natural language understanding?

原文链接： https://www.quora.com/What-are-the-major-open-problems-in-natural-language-understanding

I will classify the problems in Natural Language Processing into 3 categories :
 

1. Easy or mostly solved

• Spam detection
• Part of Speech Tagging -  Example
  INPUT:
  Profits soared at Boeing Co., easily topping forecasts on Wall Street, as
  their CEO Alan Mulally announced first quarter results.
  OUTPUT:
  Profits/N soared/V at/P Boeing/N Co./N ,/, easily/ADV topping/V forecasts/
  N on/P Wall/N Street/N ,/, as/P their/POSS CEO/N Alan/N Mulally/
  N announced/V first/ADJ quarter/N results/N ./.
  KEY: N = Noun, V = Verb, P = Preposition, Adv = Adverb

• Named Entity Recognition - Example

      INPUT:
      Profits soared at Boeing Co., easily topping forecasts on Wall Street, as
      their CEO Alan Mulally announced first quarter results.
      OUTPUT:
      Profits/NA soared/NA at/NA Boeing/SC Co./CC ,/NA easily/NA topping/
      NA forecasts/NA on/NA Wall/SL Street/CL ,/NA as/NA their/NA CEO/NA
      Alan/SP Mulally/CP announced/NA first/NA quarter/NA results/NA ./NA
      KEY: NA = No entity, SC = Start Company, CC = Continue Company, SL = Start Location, CL = Continue Location
 

2. Intermediate or making good progress

• Sentiment analysis- Example:

      Best roast chicken in San Francisco! -- Positive
      The waiter ignored us for 20 minutes. -- Negative

• Coreference resolution - Example: "Carter told Mubarak he shouldn't run again." To solve whether "he" is related to "Carter" or "Mubarak".
• Word sense disambiguation - Example :

      I need new batteries for my mouse. - "mouse" is ambiguous here.

• Parsing - the basic problem of parsing sentences.
• Machine Translation - translating sentences from one language to another, best example would be Google translate.
• Information Translation - to take a text as input and represent it in a structured form like a database entries.

 

3. Hard or still need lot of work

• Text Summarization - to take input as text document(s) and try to condense them into a summary.
• Machine dialog system - Example:

      User - I need a flight from New York to London, arriving at 10 pm ?
      System - What day are you leaving?
      User - Tomorrow.
     
      System detects the missing information in your sentences.