In this paper we propose using the distributional differences in the syntactic patterns of near-synonyms to deduce the relevant components of verb meaning. Our method involves determining the distributional differences in syntactic patterns, deducing the semantic features from the syntactic phenomena, and testing the semantic features in new syntactic frames. We determine the distributional dif...

We use the technique of SVM anchoring to demonstrate that lexical features extracted from a training corpus are not necessary to obtain state of the art results on tasks such as Named Entity Recognition and Chunking. While standard models require as many as 100K distinct features, we derive models with as little as 1K features that perform as well or better on different domains. These robust re...

In this paper, we describe an approach to annotate the propositions in the Penn Chinese Treebank. We describe how diathesis alternation patterns can be used to make coarse sense distinctions for Chinese verbs as a necessary step in annotating the predicate-structure of Chinese verbs. We then discuss the representation scheme we use to label the semantic arguments and adjuncts of the predicates....

This study explored lexical-syntactic information - syntactic information that is stored in the lexicon - and its relation to syntactic and lexical impairments in aphasia. We focused on two types of lexical-syntactic information: predicate argument structure (PAS) of verbs (the number and types of arguments the verb selects) and grammatical gender of nouns. The participants were 17 Hebrew-speak...

the present meta-analysis was conducted to provide a quantitative measure of the overall effects of task complexity on chinese efl learners’ language production. based on the strict inclusion criteria, 12 primary studies were synthesized according to key features. eleven of them were meta-analyzed to investigate effects of raising the resource-directing task complexity. results revealed that ...

Good performance on Text Classification (TC) tasks depends on effective and statistically significant features. Typically, the simple bag-of-words representation is widely used because unigram counts are more likely to be significant compared to more compound features. This research explores the idea that the major cause of poor performance of some complex features is sparsity. Syntactic featur...

Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. In this paper, we have experimented with one empirical and two unsupervised statistical machine learning techniques: kmeans and Expectation Maximization (EM), for computing relative importance of the sentences. However,...