Benjamin Van Durme

HLP Lab and collaborators at CMCL, ACL, and CogSci

Posted on Updated on

The summer conference season is coming up and HLP Lab, friends, and collaborators will be presenting their work at CMCL (Baltimore, joint with ACL), ACL (Baltimore), CogSci (Quebec City), and IWOLP (Geneva). I wanted to take this opportunity to give an update on some of the projects we’ll have a chance to present at these venues. I’ll start with three semi-randomly selected papers. Read the rest of this entry »

How good is the web as an approximation of language experience?

Posted on Updated on

Benjamin Van Durme and Austin Frank (who still doesn’t have a webpage) have been doing some neat comparisons of web-based estimate of language experience vs. traditional data sources. This work is part of a project funded by the University of Rochester’s Provost Award for Multidisciplinary Research. Since I really like the results, I am gonna use some lazy time to blog about my favorites.

We found that web-based probability estimates can be used to investigate probability-sensitive human behavior. We used databases of word naming, picture naming, and lexical decision tasks, as well as a database of word durations derived from the Switchboard corpus of spontaneous speech. Comparing Google Web 1T 5-gram counts vs. CELEX (spoken and written), BNC (spoken and written), and Switchboard counts, we estimated word frequencies and compared models using these different frequency estimates against the different types of probability sensitive language behaviors mentioned above (word naming RTs, etc.).

I find this encouraging, as web data, unlike traditionally used data sources, is cheap and readily available for many languages, thereby facilitating cross-linguistics work on probability-sensitive human language processing. Additionally, we found at least preliminary evidence that simple principal component analysis over the various frequency estimates leads to better correlation against human language behavior.

CELEX (written), Google Ngram, and their 1st principal component fitted against probability-sensitive human language behavior

Read the rest of this entry »