This paper describes our ongoing research project on text simplification for congenitally deaf people. Text simplification we are aiming at is the task of offering a deaf reader a syntactic and lexical paraphrase of a given text for assisting her/him to understand what it means.

The use of paraphrases as a potential way to improve question answering, machine translation or automatic text summarization systems has long attracted the interest of researchers in natural language processing. However, manually entering reformulations into a system is a tedious and time-consuming process, if not an endless one. In this paper, we introduce a learning machinery aimed at acquiring reformulations automatically. Our system uses the Web as a linguistic resource and takes advantage of the results of an existing question answering system. Starting with one single prototypical argument tuple of a given semantic relation, our system first searches for potential alternative formulations of the relation, then finds new potential argument tuples, and iterates this process to progressively validate the candidate formulations. This learning process combines an acquisition stage, whose goal is to retrieve new evidences from Web pages, and a validation stage, whose role is to filter out noise and discard invalid paraphrases. After justifying the use of the Web as a linguistic resource, we describe our system, and report on primary results on a series of test semantic relations.

This paper describes a statistical approach to tile interpretation of metonymy. A metonymy is received as an input, then its possible interp retations are ranked by al)t)lying ~ statistical measure. The method has been tested experimentally. It; correctly interpreted 53 out of 75 metonymies in Jat)anese. 1

In this paper, we present a nearly unsupervised learning methodology for automatically extracting paraphrases from the Web. Starting with one single linguistic expression of a semantic relationship, our learning algorithm repeatedly samples the Web, in order to build a corpus of potential new examples of the same relationship. Sampling steps alternate with validation steps, during which implausible paraphrases are filtered out using an EM-based unsupervised clustering procedure. This learning machinery is built on top of an existing question-answering (QA) system and the learnt paraphrases will eventually be used to improve its recall. We focus here on the learning aspect of this system and report preliminary results.

This paper describes an approach to using semantic representations for learning information extraction (IE) rules by a type-oriented inductive logic programming (ILP) system. NLP components of a machine trauslation system are used to automatically generate semantic representations of text corpus that can be given directly to an ILP system. The latest experimental results show high precision and recall of the learned rules.

This paper describes a nealy unsupervised learning method for converting or paraphrasing Japanese noun phrases to verb phrases without changing their semantic contents. We focus on the paraphrasing of the noun phrases in the form of “A no B ” where “A” and “B ” are noun phrases and “no ” is a postposition. Noun phrases in this form can express various relationships between “A ” and “B. ” In the past, semantic analyses of the noun phrases were performed by choosing up a relation from a relatively small set of pre-defined semantic relations. However, some researchers pointed out that “no ” can denote a broad range of relationships that can be expressed only by introducing various verbs. For instance, the noun phrase “restaurant no beer ” can be paraphrased to the relative clause “the beer that someone drinks at a restaurant. ” The relationship between “restaurant ” and “beer” cannot be expressed without introducing the verb “drink. ” We sought to perform this type of paraphrasing without manually tailored dictionaries and thesauri. Instead, we use the semantic case frames and word classifications obtained by an unsupervised statistical learning method. 1

This paper proposes a probabilistic model for associative anaphora resolution in Japanese. Associative anaphora is a type of bridging anaphora, in which the anaphor and its antecedent are not coreferent. Our model regards associative anaphora as a kind of zero anaphora and resolves it in the same manner as zero anaphora resolution using automatically acquired lexical knowledge. Experimental results show that our model resolves associative anaphora with good performance and the performance is improved by resolving it simultaneously with zero anaphora. 1

This paper describes our ongoing research project on text simplification for congenitally deaf people. Text simplification we are aiming at is the task of offering a deaf reader a syntactic and lexical paraphrase of a given text for assisting her/him to understand what it means.

This paper proposes a wide-range anaphora resolution system toward text understanding. This system resolves zero, direct and indirect anaphors in Japanese texts by integrating two sorts of linguistic resources: a hand-annotated corpus with various relations and automatically constructed case frames. The corpus has relevance tags which consist of predicate-argument relations, relations between nouns and coreferences, and is utilized for learning parameters of the system and testing it. The case frames are indispensable knowledge both for detecting zero/indirect anaphors and estimating appropriate antecedents. Our preliminary experiments showed promising results.

This paper describes our preliminary attempt to automatically recognize zero adnominals, a subgroup of zero pronouns, in Japanese discourse. Based on the corpus study, we define and classify what we call “argument-taking nouns (ATNs), ” i.e., nouns that can appear with zero adnominals. We propose an ATN recognition algorithm that consists of lexicon-based heuristics, drawn from the observations of our analysis. We finally present the result of the algorithm evaluation and discuss future directions. 1