A user expresses an information need of finding out the exact date Abraham Lincoln was born. Using the definition of relevance from our course’s information retrieval lectures, select the document that is most relevant to this information need.

Which of the following are true about Open Information Extraction? (Select all that apply.)

You are building a machine reading system for the Catman movie trivia because you need to beat your friends! Instead of paying humans to label 10,000 sentences by hand, you decide to use an existing database (like IMDb, the Internet Movie Database, which contains information about every movie, every actor that has been in a movie, every director of a movie, etc.) to automatically label the training data. Question: How would using “Distant Supervision” technique guess the labels for your training sentences? (Select all that apply)

Story: We are building a smart travel app. A user opens the app and says: “Find me a cheap flight to Tokyo for next Friday.”   Question: Which of the following best represents the Intent and the extracted Slots for this user’s sentence?(Select the best intent & extracted slots for this user’s sentence)

Which open-domain QA method augments a pretrained language model with a differentiable retrieval component and jointly learns retrieval and answering? (Select the open-domain QA method the best match this description)

Explain the difference between extractive and abstractive summarization. State one primary advantage and one primary disadvantage for each approach.(One or two sentences should be sufficient for the explaining the difference, then one advantage and one disadvantage per method.)

Select “True” after you have successfully uploaded your exam to Gradescope.

Exam 4

Two common types of distillation towers are packed and tray type towers.

Heavy ends are the materials in a distillation column that boil at the highest  temperatures and exit the bottom of the tower.