Explorations in the distributional and semantic similarity of words

A straightforward computation of the list of the words (the `tail words' of the list) that are distributionally most similar to a given word (the `head word' of the list) leads to the question: How semantically similar to the head word are the tail words; that is: how similar are their meanings to its meaning? And can we do better? The experiment was done on nearly 18,000 most frequent nouns in a Finnish newsgroup corpus. These nouns are considered to be distributionally similar to the extent that they occur in the same direct dependency relations with the same nouns, adjectives and verbs. The extent of the similarity of their computational representations is quantified with the information radius. The semantic classification of head-tail pairs is intuitive; some tail words seem to be semantically similar to the head word, some do not. Each such pair is also associated with a number of further distributional variables. Individually, their overlap for the semantic classes is large, but the trained classification-tree models have some success in using combinations to predict the semantic class. The training data consists of a random sample of 400 head-tail pairs with the tail word ranked among the 20 distributionally most similar to the head word, excluding names. The models are then tested on a random sample of another 100 such pairs. The best success rates range from 70% to 92% of the test pairs, where a success means that the model predicted my intuitive semantic class of the pair. This seems somewhat promising when distributional similarity is used to capture semantically similar words. This analysis also includes a general discussion of several different similarity formulas, arranged in three groups: those that apply to sets with graded membership, those that apply to the members of a vector space, and those that apply to probability mass functions.

Practical Proposals for Specifying k-Nearest Neighbours Weights Matrices

In this article we introduce and evaluate testing procedures for specifying the number k of nearest neighbours in the weights matrix of spatial econometric models. The spatial J-test is used for specification search. Two testing procedures are suggested: an increasing neighbours testing procedure and a decreasing neighbours testing procedure. Simulations show that the increasing neighbours testing procedures can be used in large samples to determine k. The decreasing neighbours testing procedure is found to have low power, and is not recommended for use in practice. An empirical example involving house price data is provided to show how to use the testing procedures with real data.

Evaluating the regional and distributional impacts of forestry cost-share payments.

XVIII IUFRO World Congress, Ljubljana 1986.

Local air pollution and global climate change taxes: a distributional analysis

25 p.

Ocean distribution of the American shad (Alosa sapidissima) along the Pacific coast of North America

We examined the incidental catches of American shad (Alosa sapidissima) taken during research cruises and in commercial and recreational landings along the Pacific coast of North America during over 30 years of sampling. Shad, an introduced species, was mainly found over the shallow continental shelf, and largest catches and highest frequency of occurrences were found north of central Oregon, along the coasts of Washington and Vancouver Island, and in California around San Francisco Bay. Migrations to the north off Washington and Vancouver were seen during spring to fall, but we found no evidence for large-scale seasonal migrations to the south during the fall or winter. The average weight of shad increased in deeper water. Sizes were also larger in early years of the study. Most were caught over a wide range of sea surface temperatures (11–17°C) and bottom temperatures (6.4–8.0°C). Abundance of shad on the continental shelf north of 44°N was highly correlated with counts of shad at Bonneville Dam on the Columbia River in the same year. Counts were negatively related to average weights and also negatively correlated with the survival of hatchery coho salmon (Oncorhynchus kisutch), indicating that survival of shad is favored by warm ocean conditions. Examining the catch during research cruises and commercial and recreational landings, we concluded that American shad along the Pacific coast have adapted to the prevailing environmental conditions and undertake only moderate seasonal migrations compared with the long seasonal migrations of shad along the Atlantic coast of North America. We suggest that the large spawning populations in the Columbia River and San Francisco Bay areas explain most of the distributional features along the Pacific coast.

A new distributional record of Zozymodes cavipes (Dana, 1852) (Crustacea; Decapoda) from the coastal waters of Pakistan

One male and one female of Zozymodes cavipes (Dana, 1852) have revently been collected from the rocky shores near Karachi; the species is widely distributed in the Indo-Pacific region. It is, however, being reported for the first time from the pakistani coast of the northern Arabian Sea and thus fills the gap in the known distribution of the species. The pakistani material is housed in the Marine Reference Collection Centre, University of Karachi. The specimens are briefly descibed below. Only restricted synonym is given.