Lillian Lee: Computers not yet able to understand human speech

Jul 24, 2012 by Rebecca Harrison

Perhaps Hal from "2001: A Space Odyssey" may not have been wrong when he said: "I'm sorry, Dave, I'm afraid I can't do that." Machines—even Apple's Siri—cannot yet completely understand our natural language, a Cornell researcher says.

For the second installment of the School of Continuing Education and Summer Sessions lecture series, Cornell's Lillian Lee, professor of , drew 225 faculty, students and guests to Kennedy Hall's Call Auditorium July 18. Lee detailed the progress in (NLP) and machine learning, and the challenges that lie ahead.

"Understanding language is really hard, not just because of understanding the structure of language part ... it also involves understanding things about what human beings want," Lee explained. Scientists are trying to integrate the insight from linguistics into statistical models, but "we are not all the way there yet," Lee said.

What would happen if, in March 2012, you queried, "Is Snooki on stork watch?" into Google, or asked the question to "Watson," the machine that has beaten human champions in . "Google didn't know the answer!" Lee said. "I've argued that we need a probabilistic approach; a data approach. ... How would Watson figure this out? We have a lot of data. We as human beings may notice what answers the first question. Watson doesn't understand 'Snooki and fiancé Jionni LaValle are expecting their first child together' when asked about 'stork watch.'"

NLP seeks to create systems that can use human language as input or output. This includes speech-based interfaces, information retrieval (such as Google), automatic summarization of news, emails and postings, and automatic translation (such as Translate). According to Lee, the thrill of NLP is that it is "interdisciplinary, including fields of computer science, , psychology, communication, probability and statistics, and information theory."

"Why is understanding language so hard?" Lee answers her own question by providing the example: "I saw her duck with a telescope." According to Lee: "[This sentence] could mean a lot of things. If you look at the word 'duck,' it could mean I'm 'ducking' because people are throwing potatoes at me. Or the word duck could be the animal. In both cases, you have to ask who's holding the telescope … seven simple little words, and this sentence could mean a bazillion things."

According to Lee, somewhere between science fiction and new technological advancement there is a dream and a promise of computers that can understand what people are saying. intelligence can be demonstrated by natural language conversation.

Even has not been able to stand up to this test of intelligence. For example, Lee explains that telling her, "We can email you when you're back" generates "We can email you when you're fat."

The moral of Lee's story: "Today, we need to be careful before you hit, or now even say, the word 'send.'"

Explore further: Communication-optimal algorithms for contracting distributed tensors

add to favorites email to friend print save as pdf

Related Stories

Texting affects ability to interpret words

Feb 20, 2012

(Medical Xpress) -- Research designed to understand the effect of text messaging on language found that texting has a negative impact on people's linguistic ability to interpret and accept words.

Pittsburgh symposium answers: What is Watson?

Mar 30, 2011

(AP) -- Six university students attempted to match wits with IBM's "Jeopardy!"-playing computer Wednesday and lost badly in a mock game show. But the competition was hardly the point of a daylong symposium ...

Google adds automatic translation to Gmail

May 20, 2009

Google added automatic translation technology to Gmail on Tuesday, allowing users of its email service to translate messages in another language with a single mouse click.

Recommended for you

User comments : 4

Adjust slider to filter visible comments by rank

Display comments: newest first

Tausch
3 / 5 (2) Jul 24, 2012
Humans are not able to understand human speech.

Do not discourage anyone by revealing how far astray they are from understanding language - any language.
Bob_Kob
5 / 5 (1) Jul 24, 2012
Honestly i had no godamn idea what they meant by the snooki stork watch, took me a couple of reads to realise the context... id say not bad computer recognition, bad language.
Mayday
not rated yet Jul 24, 2012
Computers are obsessed with speed above all else. If a reasonably intelligent person hears a statement and needs to transcribe it, they will almost invariably review their own transcription (or potential transcription) for sense, accuracy, context relevance and social appropriateness. If the transcription fails the tests (we do this in a heart beat), they will ask "we can email you when you get what?" The modern computers' obsession with speed makes this simple, and so human, error correction method impossible. Just ask any computer that you meet.
Aloken
not rated yet Jul 24, 2012
Honestly i had no godamn idea what they meant by the snooki stork watch, took me a couple of reads to realise the context... id say not bad computer recognition, bad language.


Agreed, worry about making computers understand proper human language first. Leave slangs for later or never work on them at all (personally I would hate to receive a reply from a computer that speaks in slangs).