Computer Science – Computation and Language
Scientific paper
1997-08-19
Computer Science
Computation and Language
71 pages (single-spaced)
Scientific paper
This thesis presents two similarity-based approaches to sparse data problems. The first approach is to build soft, hierarchical clusters: soft, because each event belongs to each cluster with some probability; hierarchical, because cluster centroids are iteratively split to model finer distinctions. Our second approach is a nearest-neighbor approach: instead of calculating a centroid for each class, as in the hierarchical clustering approach, we in essence build a cluster around each word. We compare several such nearest-neighbor approaches on a word sense disambiguation task and find that as a whole, their performance is far superior to that of standard methods. In another set of experiments, we show that using estimation techniques based on the nearest-neighbor model enables us to achieve perplexity reductions of more than 20 percent over standard techniques in the prediction of low-frequency events, and statistically significant speech recognition error-rate reduction.
No associations
LandOfFree
Similarity-Based Approaches to Natural Language Processing does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Similarity-Based Approaches to Natural Language Processing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Similarity-Based Approaches to Natural Language Processing will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-183218