In this paper we deal with several kinds of anaphora in unrestricted texts. These kinds of anaphora are pronominal references, surfacecount anaphora and one-anaphora. In order to solve these anaphors we work on the output of a part-of-speech tagger, on which we automatically apply a partial parsing from the formalism: Slot Unification Grammar, which has been implemented in Prolog. We only use t...

This paper describes a grammar formalism and a deterministic parser developed for text normalisation in the rVoice text-to-speech (TTS) system. The rules are formulated using regular expressions and converted into a non-deterministic finite-state transducer (FST). At runtime, search is guided by parsing preferences which the user may associate with regular operators; the best solution is determ...

We propose a method to alleviate the problem of referential granularity for Japanese zero pronoun resolution. We use dictionary definition sentences to extract ‘representative’ arguments of predicative definition words; e.g. ‘arrest’ is likely to take police as the subject and criminal as its object. These representative arguments are far more informative than ‘person’ that is provided by other...

This study develops a connection between human parsing preferences and feature selection rankings in a multilingual dependency parser. The results reveal that feature weights reflect the typological characteristics of three languages. Accounting for these differences leads to greater precision in modeling garden path data.

In this paper we discuss the psycholinguistic relevance of a “surfastic” TAG-based theory of syntax (Abeill 91, Abeill nd al. 00a). We show that widely accepted parsing preferences can be elegantly formulated on LTAG derivation trees. We sketch a processing model which allows to predict Garden-Path phenomena and sheds a new light on some psycholinguistic results concerning the existence of Wh t...

A statistical corpus-based approach for acquiring selectional preferences of verbs is proposed. By parsing through text corpora, we obtain examples of context nouns that are considered to be the selectional preferences of a given verb. The approach is to generalize initial noun classes to the most appropriate levels on a semantic hierarchy. We present an iterative algorithm for generalization b...

In this chapter we explore the possibility that within Optimality Theory, a single syntactic grammar directly yields not only competence theoretic results on the grammatical distributions of elements, but also performance theoretic results on relative preferences when processing sentences with various syntactic ambiguities. Whereas the competence theory applies the grammar at the level of an en...

To contribute to a better understanding of L2 sentence processing, the present study examines how second language (L2) learners parse temporary ambiguous sentences containing relative clauses. Results are reported from both off-line and on-line experiments with three groups of advanced learners of Greek, with Spanish, German or Russian as native language (L1), as well as results from correspond...

Human parsing has great application prospects in the field of computer vision, but there are still many problems. In existing algorithms, problems small-scale target location and problem background occlusion have not been fully resolved, which will lead to wrong segmentation or incomplete segmentation. Compared with practice feature concatenation, using correlation between two factors can make ...