- Abstract:
-
Previous work demonstrated that web counts can be used to approximate bigram counts, thus suggesting that web-based frequencies should be useful for a wide variety of NLP tasks. However, only a limited number of tasks have so far been tested using web-scale data sets. The present paper overcomes this limitation by systematically investigating the performance of web-based models for several NLP tasks, covering both syntax and semantics, both generation and analysis, and a wider range of n-grams and parts of speech than have been previously explored. For the majority of our tasks, we find that simple, unsupervised models perform better when n-gram counts are obtained from the web rather than from a large corpus. In some cases, performance can be improved further by using backoff or interpolation techniques that combine web counts and corpus counts. However, unsupervised web-based models generally fail to outperform supervised state-of-the-art models trained on smaller corpora. We argue that web-based models should therefore be used as a baseline for, rather than an alternative to, standard supervised models.
- Links To Paper
- 1st Link
- Bibtex format
- @Article{EDI-INF-RR-0469,
- author = {
Mirella Lapata
and Frank Keller
},
- title = {Web-based Models for Natural Language Processing},
- journal = {ACM Transactions on Speech and Language Processing},
- publisher = {ACM},
- year = 2005,
- volume = {# 2(1)},
- doi = {10.1145/1075389.1075392},
- url = {http://homepages.inf.ed.ac.uk/mlap/Papers/tslp05.html},
- }
|
