Snow, Rion and Jurafsky, Daniel and Ng, Andrew Y. (2004) Learning syntactic patterns for automatic hypernym discovery. In: Advances in Neural Information Processing Systems (NIPS 2004), December 13-18, 2004,, Vancouver, British Columbia.
We present a new algorithm for learning hypernym (is-a) relations from text, a key problem in machine learning for natural language understanding. This method generalizes earlier work that relied on hand-built lexico-syntactic patterns by introducing a general-purpose formalization of the pattern space based on syntactic dependency paths. We learn these paths automatically by taking hypernym/hyponym word pairs from WordNet, finding sentences containing these words in a large parsed corpus, and automatically extracting these paths. These paths are then used as features in a high-dimensional representation of noun relationships. We use a logistic regression classifier based on these features for the task of corpus-based hypernym pair identification. Our classifier is shown to outperform previous pattern-based methods for identifying hypernym pairs (using WordNet as a gold standard), and is shown to outperform those methods as well as WordNet on an independent test set.
|Item Type:||Conference or Workshop Item (Paper)|
|Additional Information:||This is a draft version from the NIPS preproceedings; the final version will be published by April 2005.|
|Subjects:||Computer Science > Data Mining|
Computer Science > Semistructured Data
|Related URLs:||Project Homepage||http://www-nlp.stanford.edu/|
|Deposited By:||Import Account|
|Deposited On:||20 Nov 2004 16:00|
|Last Modified:||23 Dec 2008 09:47|
Repository Staff Only: item control page