Abstract | However, syntax-based methods can only use discrete contextual information, which may suffer from data sparsity . |
Abstract | Lexical semantic clue verifies whether a candidate term is related to the target product, and contextual semantic clue serves as a soft pattern miner to find candidates, which exploits semantics of each word in context so as to alleviate the data sparsity problem. |
Experiments | As for SGW-TSVM, the features they used for the TSVM suffer from the data sparsity problem for infrequent terms. |
Introduction | Therefore, such a representation often suffers from the data sparsity problem (Turian et al., 2010). |
Introduction | This enables our method to be less sensitive to lexicon change, so that the data sparsity problem can be alleviated . |
Related Work | As discussed in the first section, syntactic patterns often suffer from data sparsity . |
Related Work | Thus, the data sparsity problem can be alleviated. |
The Proposed Method | To alleviate the data sparsity problem, EB is first trained on a very large corpus3 (denoted by C), and then fine-tuned on the target review corpus R. Particularly, for phrasal product features, a statistic-based method in (Zhu et al., 2009) is used to detect noun phrases in R. Then, an Unfolding Recursive Autoencoder (Socher et al., 2011) is trained on C to obtain embedding vectors for noun phrases. |
Compositional distributional semantics | Estimating tensors of this size runs into data sparseness issues already for less common transitive verbs. |
Compositional distributional semantics | Besides losing the comparability of the semantic contribution of a word across syntactic contexts, we also worsen the data sparseness issues. |
Evaluation | Evidently, the separately-trained subject and object matrices of plf, being less affected by data sparseness than the 3-way tensors of If, are better able to capture how verbs interact with their arguments. |
The practical lexical function model | We expect a reasonably large corpus to feature many occurrences of a verb with a variety of subjects and a variety of objects (but not necessarily a variety of subjects with each of the objects as required by Grefenstette et al.’s training), allowing us to avoid the data sparseness issue. |
Abstract | This leads to a severe data sparsity problem even for moderately long sentences. |
Abstract | Assume for this section is large (we address the data sparsity issue in §3.4). |
Abstract | We now address the data sparsity problem, in particular that ’D(a:) can be very small, and therefore estimating d for each POS sequence separately can be problematic.3 |
Abstract | Traditional models of distributional semantics suffer from computational issues such as data sparsity for individual lex-emes and complexities of modeling semantic composition when dealing with structures larger than single lexical items. |
Abstract | The framework subsumes issues such as differential compositional as well as non-compositional behavior of phrasal con-situents, and circumvents some problems of data sparsity by design. |
Introduction | Such a framework for distributional models avoids the issue of data sparsity in learning of representations for larger linguistic structures. |