Re: Just to further make people think ...
For example, anther sentence: “The city councilmen refused the demonstrators a permit because they [feared/advocated] violence.” If the word “feared” is selected, then “they” refers to the city council. If “advocated” is selected, then “they” presumably refers to the demonstrators.
Thus some patterns are lexical noise and should be somehow either deleted or ignored. The Microsoft team did that using a new method based on the semantic similarity between the pronoun and its antecedent candidates, which I patented as surrounding paragraphs's patterns. As the result Microsoft has significantly improved the MT-DNN approach to NLU, and finally surpassed the estimate for human performance on the overall average score on GLUE (87.6 vs. 87.1) on June 6, 2019.
As for Joy... You never know what programmers can invent drinking a beer, this is the reason quality control exists.