Sentences that show Natural Language Processing of English is hard

Let us try to understand why NLP (Natural Language Processing) is considered hard using a few examples:

1. "There was not a single man at the party".

- Does it mean that there were no men at the party? Or

- Does it mean that there was no one at the party? Or

- Here does man refer to the gender "man" or "mankind"?

2. "The chicken is ready to eat."

- Does this mean that the bird (chicken) is ready to feed on some grains? Or

- Does it mean that the meat is cooked well and is ready to be eaten by a human?

3. "Google is a great company" and "Google this word and find its meaning".

- Google is being used as a noun in the first statement and as a verb in the second.
Google (noun) and Google (verb) are homonyms.

4. The man saw a girl with a telescope.

- Did the man use a telescope to see the girl? Or 

- Did the man see a girl who was holding a telescope?

5. Consider saying this to a voice interface like Siri and Alexa:

She felt... less. She felt tamped down. Dim. More faint. Feint. Feigned. Fain.
--Patrick Rothfuss

6. Why we need a bidirectional parsing model for Natural Language Processing?

Sentences where future words tell about the words spoken in the past.

Consider these two sentences:
a. She says, "Teddy bears are my favorite toy."
b. She says, "Teddy Roosevelt was the 26th President of the United States."

On a high level what a unidirectional LSTM model will see:
She says, "Teddy."

On the other hand, a bidirectional LSTM will be able to see the information further down the road as well. See the illustration below:

Forward LSTM will see: "She says, 'Teddy'."

Backward LSTM will see: "was the the 26th President of the United States."

7. Word Sense Disambiguation

As an example of the contextual effect between words, consider the word "by", which has several meanings, for example: 

# the book by Chesterton (agentive - Chesterton was the author of the book); 

# the cup by the stove (locative - the stove is where the cup is); and 

# submit by Friday (temporal - Friday is the time of the submitting). 

Observe below that the meaning of the italicized word helps us interpret the meaning of by.

a. The lost children were found by the searchers (agentive) 

b. The lost children were found by the mountain (locative) 

c. The lost children were found by the afternoon (temporal)

8. Pronoun Resolution

Consider three possible following sentences, and try to determine what was sold, caught, and found (one case is ambiguous).

a. The thieves stole the paintings. They were subsequently sold.
b. The thieves stole the paintings. They were subsequently caught.
c. The thieves stole the paintings. They were subsequently found.

Answering this question involves finding the antecedent of the pronoun they, either thieves or paintings. 

Computational techniques for tackling this problem include: 

Anaphora resolution - identifying what a pronoun or noun phrase refers to. And:

Semantic role labeling - identifying how a noun phrase relates to the verb (as agent, patient, instrument, and so on).

Tags: Natural Language Processing,