This paper proposes a new computational method for comprehending attributional metaphors. The proposed method generates deeper interpretations of metaphors than other methods through the process of figurative mapping that transfers affectively similar features of the source concept onto the target concept. Any features are placed on a common two-dimensional space revealed in the domain of psychology, and similarity of two features is calculated as a distance between them in the space. A computational model of metaphor comprehension based on the method has been implemented in a computer program called PROMIME (PROtotype system of Metaphor Interpreter with MEtaphorical mapping). Comparison between the PROMIME system's output and human interpretation shows that the performance of the proposed method is satisfactory.

View full abstract

This paper presents a new formalization of probabilistic GLR (PGLR) language modeling for statistical parsing.Our model inherits its essential features from Briscoe and Carroll's generalized probabilistic LR model (Briscoe and Carroll 1993), which takes context of parse derivation into account by assigning a probability to each LR parsing action according to its left and right context. Briscoe and Carroll's model, however, has a drawback in that it is not formalized in any probabilistically well-founded way, which may degrade its parsing performance. Our formulation overcomes this drawback with a few significant refinements, while maintaining all the advantages of Briscoe and Carroll's modeling. In this paper, we discuss the formal and qualitative aspects of our PGLR model, illustrating the qualitative differences between Briscoe and Carroll's model and our model, and their expected impact on parsing performance.

View full abstract

This paper proposes a new class-based method for estimating the strength of association for word co-occurrences. To deal with sparseness of data we first use a conceptual dictionary to find upper classes of the words in the co-occurrence relation. We then use t-scores to determine a pair of classes to be used in the estimation. The strength of association for the word co-occurrence is calculated using the classes thus obtained. We have applied our method to determining dependency relations in Japanese and prepositional phrase attachment in English. The experimental results show that our method is sound, effective and useful in resolving different types of ambiguities.

View full abstract

When a parser processes a long sentence, it produces a lot of the parsing results because of the ambiguity. The number of parsing results and the processing time increase in proportion to the ambiguity. Stochastic approaches are widely used to reduce ambiguity in recent years. They add preference information learned by some stochastic methods to grammatical constraints. However, it is not desirable from a viewpoint of modularity of knowledge. In this paper, we separate preference information and grammatical constraints. When the parser processes a sentence, these information are integrated and used. We use probabilistic dependency relation as the source information for the reduction of ambiguity. In order to use this information, we modify the Chart parsing algorithm. Then, we can use stochastic information and grammatical constraints in an integrated manner, and also make the Chart parser efficient. The result of the experiment shows that the number of edges in the Chart decreases to one forth, and the processing time to one seventh.

View full abstract

In this paper, we propose a new framework of statistical language modeling integrating syntactic statistics and lexical statistics. Our model consists of two submodels, the syntactic model and lexical model. The syntactic model reflects syntactic statistics, such as structural preferences, whereas the lexical model reflects lexical statistics, such as the occurrence of each word and word collocations. One of the characteristics of our model is that it learns both types of statistics separately, although many previous models learn them simultaneously. Learning each submodel separately enables us to use a different language source for different submodels, and to make understanding of each submodel's behavior much easier. We conducteda preliminary experiment, where our model was applied to the disambiguation of dependency structures of Japanese sentences. The syntactic model achieved 73.38%in Bunsetu phrase accuracy, which is 11.70 points above the baseline, and when incorporating the lexical model with the syntactic model, further 10.96 point gain was achieved, to 84.34%. Thus the contribution of lexical statistics for disambiguation is as great as that of syntactic statistics in our framework.

View full abstract

This paper presents a method for inducing a context-sensitive conditional probability context-free grammar from an unlabeled bracketed corpus using local contextual information and describes a natural language parsing model which uses a probabilitybased scoring function of the grammar to rank parses of a sentence. This method uses clustering techniques to group brackets in a corpus into a number of similar bracket groups based on their local contextual information. From the set of these groups, the corpus is automatically labeled with some nonterminal labels, and consequently a grammar with conditional probabilities is acquired. Based on these conditional probabilities, the statistical parsing model provides a framework for finding the most likely parse of a sentence. A number of experiments are made using EDR corpus and Wall Street Journal corpus. The results show that our approach achieves a relatively high accuracy: 88% recall, 72% precision and 0.7 crossing brackets per sentence for sentences shorter than 10 words, and 71% recall, 51% precision and 3.4 crossing brackets for sentences between 10-19 words. This result supports the assumption that local contextual statistics obtained from an unlabeled bracketed corpus are effective for learning a useful grammar and parsing.

View full abstract