Akira Shimazu

The State of the Art in Agent Communication Languages

Abstract. Like societies of humans, there is a need for agents in a multi-agent system to rely on one another, enlist the support of peers in order to solve complex tasks. Agents will be able to cooperate only through a meaningful communication language that can bear correctly their mental states and convey precisely the content of their messages. In search for the ideal agent communication language (ACL), several initiatives like the pioneering work of the Knowledge Sharing Effort and the Foundation for Intelligent Physical Agents (FIPA) are paving the way for a platform where all agents would be able to interact regardless of their implementation environment. ACL is a new field of study that could gain from a survey in expanding its application areas. For this purpose, we examine in this paper the state of the art in ACL design and suggest some principles for building a generalized ACL framework. We then evaluate some existing ACL models, and present the current issues in ACL research, and new perspectives.

Probabilistic sentence reduction using support vector machines

This paper investigates a novel application of support vector machines (SVMs) for sentence reduction. We also propose a new probabilistic sentence reduction method based on support vector machine learning. Experimental results show that the proposed methods outperform earlier methods in term of sentence reduction performance.

Example-based sentence reduction using the hidden markov model

Sentence reduction is the removal of redundant words or phrases from an input sentence by creating a new sentence in which the gist of the original meaning of the sentence remains unchanged. All previous methods required a syntax parser before sentences could be reduced; hence it was difficult to apply them to a language with no reliable parser. In this article we propose two new sentence-reduction algorithms that do not use syntactic parsing for the input sentence. The first algorithm, based on the template-translation learning algorithm, one of example-based machine-translation methods, works quite well in reducing sentences, but its computational complexity can be exponential in certain cases. The second algorithm, an extension of the template--translation algorithm via innovative employment of the Hidden Markov model, which uses the set of template rules learned from examples, can overcome this computation problem. Experiments show that the proposed algorithms achieve acceptable results in comparison to sentence reduction done by humans.

Towards translation of legal sentences into logical forms

This paper proposes a framework for translating legal sentences into logical forms in which we can check for inconsistency, and describes the implementation and experiment of the first experimental system. Our logical formalization conforms to Davidsonian Style, which is suitable for languages allowing expressions with zero-pronouns such as Japanese. We examine our system with actual data of legal documents. As a result, the system was 78% of accurate in terms of deriving predicates with bound variables. We discuss our plan for further development of the system from the viewpoint of the following two aspects: (1) improvement of accuracy (2) formalization of output necessary for logical processing.

Combining classifiers for word sense disambiguation based on Dempster-Shafer theory and OWA operators

In this paper, we discuss a framework for weighted combination of classifiers for word sense disambiguation (WSD). This framework is essentially based on Dempster-Shafer theory of evidence [G. Shafer, A Mathematical Theory of Evidence, Princeton University Press, Princeton, 1976] and ordered weighted averaging (OWA) operators [R.R. Yager, On ordered weighted averaging aggregation operators in multicriteria decision making, IEEE Transactions on Systems, Man, and Cybernetics 18 (1988) 183-190] We first determine various kinds of features which could provide complementarily linguistic information for the context, and then combine these sources of information based on Dempsters rule of combination and OWA operators for identifying the meaning of a polysemous word. We experimentally design a set of individual classifiers, each of which corresponds to a distinct representation type of context considered in the WSD literature, and then the discussed combination strategies are tested and compared on English lexical samples of Senseval-2 and Senseval-3.

Construction of Deliberation Structure in E‐Mail Communication

We propose a model, called a deliberation structure model, that represents streams of relevant messages in email communication. The deliberation structure model treats e‐mail messages that include several topics and uses tree structure, called deliberation trees, that are based on Clarks contribution trees to represent message structure. Deliberation trees are useful to visualize the message structure. A method for constructing the deliberation structure is showed.

Semantic Parsing with Structured SVM Ensemble Classification Models

We present a learning framework for structured support vector models in which boosting and bagging methods are used to construct ensemble models. We also propose a selection method which is based on a switching model among a set of outputs of individual classifiers when dealing with natural language parsing problems. The switching model uses subtrees mined from the corpus and a boosting-based algorithm to select the most appropriate output. The application of the proposed framework on the domain of semantic parsing shows advantages in comparison with the original large margin methods.

A Two-Phase Framework for Learning Logical Structures of Paragraphs in Legal Articles

Analyzing logical structures of texts is important to understanding natural language, especially in the legal domain, where legal texts have their own specific characteristics. Recognizing logical structures in legal texts does not only help people in understanding legal documents, but also in supporting other tasks in legal text processing. In this article, we present a new task, learning logical structures of paragraphs in legal articles, which is studied in research on Legal Engineering. The goals of this task are recognizing logical parts of law sentences in a paragraph, and then grouping related logical parts into some logical structures of formulas, which describe logical relations between logical parts. We present a two-phase framework to learn logical structures of paragraphs in legal articles. In the first phase, we model the problem of recognizing logical parts in law sentences as a multi-layer sequence learning problem, and present a CRF-based model to recognize them. In the second phase, we propose a graph-based method to group logical parts into logical structures. We consider the problem of finding a subset of complete subgraphs in a weighted-edge complete graph, where each node corresponds to a logical part, and a complete subgraph corresponds to a logical structure. We also present an integer linear programming formulation for this optimization problem. Our models achieve 74.37% in recognizing logical parts, 80.08% in recognizing logical structures, and 58.36% in the whole task on the Japanese National Pension Law corpus. Our work provides promising results for further research on this interesting task.

RRE Task: The Task of Recognition of Requisite Part and Effectuation Part in Law Sentences

Analyzing the logical structure of a sentence is important for understanding natural language. In this paper, we present a task of Recognition of Requisite Part and Effectuation Part in Law Sentences, or RRE task for short, which is studied in research on Legal Engineering. The goal of this task is to recognize the structure of a law sentence. We investigate the RRE task regarding both the linguistic features and problem modeling aspects. We also propose solutions and present experimental results in a Japanese legal text domain. We got 88.58% with a supervised learning model and 88.84% with a semi-supervised learning model in the Fβ=1 score on the Japanese National Pension Law corpus.

A Tree-to-String Phrase-based Model for Statistical Machine Translation

Though phrase-based SMT has achieved high translation quality, it still lacks of generalization ability to capture word order differences between languages. In this paper we describe a general method for tree-to-string phrase-based SMT. We study how syntactic transformation is incorporated into phrase-based SMT and its effectiveness. We design syntactic transformation models using unlexicalized form of synchronous context-free grammars. These models can be learned from source-parsed bitext. Our system can naturally make use of both constituent and non-constituent phrasal translations in the decoding phase. We considered various levels of syntactic analysis ranging from chunking to full parsing. Our experimental results of English-Japanese and English-Vietnamese translation showed a significant improvement over two baseline phrase-based SMT systems.