Our experiments on verb classification have offered a class-based approach to alleviate data sparsity problem in parsing.

Dependency relation (DR): Our way to overcome data sparsity is to break lexicalized frames into lexicalized slots (a.k.a.

to data sparsity .

When the information about a verb type is not available or sufficient for us to draw firm conclusions about its usage, the information about the class to which the verb type belongs can compensate for it, addressing the pervasive problem of data sparsity in a wide range of NLP tasks, such as automatic extraction of subcategorization frames (Korhonen, 2002), semantic role labeling (Swier and Stevenson, 2004; Gildea and Juraf-sky, 2002), natural language generation for machine translation (Habash et al., 2003), and deriving predominant verb senses from unlabeled data (Lapata and Brew, 2004).

Trying to overcome the problem of data sparsity , Schulte im Walde (2000) explores the additional use of selectional preference features by augmenting each syntactic slot with the concept to which its head noun belongs in an ontology (e.g.

Although the problem of data sparsity is alleviated to certain extent (3), these features do not generally improve classification performance (Schulte im Walde, 2000; J oanis, 2002).

Conventional statistical machine translation (SMT) systems do not perform well on measure word generation due to data sparseness and the potential long distance dependency between measure words and their corresponding head words.

Compared with the baseline, the Mo-ME method takes advantage of a large size monolingual training corpus and reduces the data sparseness problem.

One problem is data sparseness with respect to collocations be-

However, as we will show below, existing SMT systems do not deal well with the measure word generation in general due to data sparseness and long distance dependencies between measure words and their corresponding head words.

To alleviate the data sparseness problem, we only kept patterns appearing more than 10 times in the corpus for extracting paraphrase patterns.

In other words, it seriously suffers from data sparseness .

which is mainly because the data sparseness problem is more serious when extracting long patterns.

However, we find that using only the MLE based probabilities can suffer from data sparseness .

In statistical language modeling, one technique to reduce the problematic effects of data sparsity is to partition the vocabulary into equivalence classes.

We conclude that even despite the large amounts of data used to train the large word-based model in our second experiment, class-based language models are still an effective tool to ease the effects of data sparsity .

Class-based n—gram models are intended to help overcome this data sparsity problem by grouping words into equivalence classes rather than treating them as distinct words and thus reducing the number of parameters of the model (Brown et al., 1990).