Winograd schemas as a window into reading comprehension

In one of my earlier posts on the limits of Artificial Intelligence, I reported on the difficulty AI has figuring out what “it” means. As measured by so-called Winograd schemas like the one below, even the most sophisticated AI performs at levels not much better than chance:

SENTENCE 1: “The city council refused the demonstrators a permit because they feared violence.”

QUESTION: Who feared violence?

A. The city council B. The demonstrators

SENTENCE 2: “The city council refused the demonstrators a permit because they advocated violence.”

QUESTION: Who advocated violence?

A. The city council B. The demonstrators

The problem is that even state of the art AI lacks worldly knowledge–including background knowledge about city councils and demonstrators and their typical concerns and plausible goals. Who might fear violence and feel a responsibility to prevent it? Who might advocate violence?

Of course, even the occasional human has been known to have deficits in background knowledge, and those deficits have increasingly been implicated in problems with reading comprehension. In general, if you lack the knowledge that a text takes for granted, you’ll struggle to make sense of anything the text asserts that’s based on that knowledge.

For example, if you don’t know about the functions of antimicrobial agents, or what bacterial resistance and immunosuppression entail, you’ll struggle to make sense of this paragraph (even if you happen to know words like “pathogenic” and “concomitant”):

The emergence of pathogenic bacteria resistant to most, if not all, currently available antimicrobial agents has become a critical problem in modern medicine, particularly because of the concomitant increase in immunosuppressed patients. 

https://aac.asm.org/content/45/3/649.short

Given that a big part of reading comprehension is figuring out what pronouns (“it”, “they”, etc.) and other anaphora (“this”, “that”) refer to, I’m wondering how often breakdowns in reading comprehension boil down to failures at Winograd-like schemas. Indeed, given complaints about students’ background knowledge, specifically, in broad areas like history and civics (see Natalie Wexler on The Knowledge Gap; sorry, it’s not just the Holocaust and Civil Rights about which today’s students are woefully ignorant), it’s not implausible that some of today’s students would misunderstand simple three-word sentences like “they feared violence” and “they advocated violence” when they occur in contexts that, absent background knowledge, render them stupefyingly ambiguous.

One thought on “Winograd schemas as a window into reading comprehension

  1. I love this!

    I always teach anaphora in my composition classes — and I always find that my students stumble over anaphora, including anaphora in very short sentences.

    Like

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s