When will my computer understand me?
From the post:
It’s not hard to tell the difference between the “charge” of a battery and criminal “charges.” But for computers, distinguishing between the various meanings of a word is difficult.
For more than 50 years, linguists and computer scientists have tried to get computers to understand human language by programming semantics as software. Driven initially by efforts to translate Russian scientific texts during the Cold War (and more recently by the value of information retrieval and data analysis tools), these efforts have met with mixed success. IBM’s Jeopardy-winning Watson system and Google Translate are high profile, successful applications of language technologies, but the humorous answers and mistranslations they sometimes produce are evidence of the continuing difficulty of the problem.
Our ability to easily distinguish between multiple word meanings is rooted in a lifetime of experience. Using the context in which a word is used, an intrinsic understanding of syntax and logic, and a sense of the speaker’s intention, we intuit what another person is telling us.
“In the past, people have tried to hand-code all of this knowledge,” explained Katrin Erk, a professor of linguistics at The University of Texas at Austin focusing on lexical semantics. “I think it’s fair to say that this hasn’t been successful. There are just too many little things that humans know.”
Other efforts have tried to use dictionary meanings to train computers to better understand language, but these attempts have also faced obstacles. Dictionaries have their own sense distinctions, which are crystal clear to the dictionary-maker but murky to the dictionary reader. Moreover, no two dictionaries provide the same set of meanings — frustrating, right?
Watching annotators struggle to make sense of conflicting definitions led Erk to try a different tactic. Instead of hard-coding human logic or deciphering dictionaries, why not mine a vast body of texts (which are a reflection of human knowledge) and use the implicit connections between the words to create a weighted map of relationships — a dictionary without a dictionary?
“An intuition for me was that you could visualize the different meanings of a word as points in space,” she said. “You could think of them as sometimes far apart, like a battery charge and criminal charges, and sometimes close together, like criminal charges and accusations (“the newspaper published charges…”). The meaning of a word in a particular context is a point in this space. Then we don’t have to say how many senses a word has. Instead we say: ‘This use of the word is close to this usage in another sentence, but far away from the third use.’”
Before you jump to the post looking for the code, Erk is working with a 10,000 dimension space to analyze her data.
The most recent paper: Montague Meets Markov: Deep Semantics with Probabilistic Logical Form (2013)
Abstract:
We combine logical and distributional representations of natural language meaning by transforming distributional similarity judgments into weighted inference rules using Markov Logic Networks (MLNs). We show that this framework supports both judging sentence similarity and recognizing textual entailment by appropriately adapting the MLN implementation of logical connectives. We also show that distributional phrase similarity, used as textual inference rules created on the fly, improves its performance.