Summary form only given. The project Natural Language Understanding and Action Control started in 2001 as 5-year research project of a Grant-in-Aid for Creative Scientific Research supported by the Ministry of Education, Culture, Sports, Science and Technology, and Japan Society for the Promotion of Science. The research objectives are summarized as follows: to explore the relation between language understanding and actions; to build a human friendly machine interface; to develop a new interdisciplinary research area. During the period 2001-2004, many interesting research results have been obtained. Following are some main accomplishments: 1) basic research - analysis of spoken language, space understanding, and the relation between language and action from the point of linguistics, cognitive science, and cognitive linguistics, respectively; 2) spoken language understanding and dialogue management - resolution of anaphora and ellipsis, object identification, handling vagueness, discourse management, morphological analysis for spoken language, real time speech recognition, robust speech recognition in noisy environment, handling ill-formed expressions (e.g. fillers, repetitions and repair expressions), speech synthesis; 3) robotics and computer graphics -constructing a life-like 3-dimensional software agent capable of performing many actions in a vitual world, and a hardware service robot, sign language understanding, a robot capable of communicating with a human through non-verbal expressions (e.g. nodding and gazing); 4) prototype system development - animated agent system that understands spoken language commands and performs actions in a virtual space, a service robot to help a human, a guidance robot, sign language understanding system, hardware robot capable of performing non-verbal expressions. Note that the results obtained from our research on software agent should be naturally applicable to hardware robots. This progress report collects only the research results obtained in 2004. Progress reports period 2001-2003 are available by consulting URL address as shown [http://www.cl.cs.titech.ac.jp/sinpro/]. I have introduced this project more precisely as invited speech and consider why language understanding is one of key technologies for designing an intelligent CW.

This paper explores the effectiveness of index terms more complex than the single words used in conventional information retrieval systems. Retrieval is done in two phases: in the first, a conventional retrieval method (the Okapi system) is used; in the second, complex index terms such as syntactic relations and single words with part-of-speech information are introduced to rerank the results of the first phase. We evaluated the effectiveness of the different types of index terms through experiments using the TREC-7 test collection and 50 queries. The retrieval effectiveness was improved for 32 out of 50 queries. Based on this investigation, we then introduce a method to select effective index terms by using a decision tree. Further experiments with the same test collection showed that retrieval effectiveness was improved in 25 of the 50 queries.

In Japanese constructions of the form [N1 no Adj N2], the adjective Adj modifies either N1 or N2. Determing the semantic dependencies of adjective in such phrase is an important task for machine translation. This paper describes a method for determining the adjective dependency in such constructions using decision lists, and inducing decision lists from training contexts with correct semantic dependencies and without. Based on evaluation, our method is able to determine adjective dependency with an precision of about 94%. We further analyze rules in the induced decision lists and examine effective features to determine the semantic dependencies of adjectives.

Bracketed corpora are a very useful resource for natural language processing, but hard to build efficiently, leading to quantitative insufficiency for practical use. Disparities in morphological information, such as word segmentation and part-of-speech tag sets, are also troublesome. An application specific to a particular corpus often cannot be applied to another corpus. In this paper, we sketch out a method to build a corpus that has a fixed syntactic structure but varying morphological annotation based on the different tag set schemes utilized. Our system uses a two layered grammar, one layer of which is made up of replaceable tag-set-dependent rules while the other has no such tag set dependency. The input sentences of our system are bracketed corresponding to structural information of corpus. The parser can work using any tag set and grammar, and using the same input bracketing, we obtain corpus that shares partial syntactic structure.

Automatic query expansion has been known to be the most important method in overcoming the word mismatch problem in information retrieval. Thesauri have long been used by many researchers as a tool for query expansion. However only one type of thesaurus has generally been used. In this paper we analyze the characteristics of different thesaurus types and propose a method to combine them for query expansion. Experiments using the TREC collection proved the effectiveness of our method over those using one type of thesaurus.

A continuous speech recognition system 'niNja' (Natural language INterface in JApanese), is presented. Efficient search algorithms are proposed to get high accuracy and to reduce the required computations. First, an LR parsing algorithm with context-dependent phone models is proposed. Second, scores of the same phone models in different hypotheses at the phone-level are represented by the single score of the best hypotheses. The system is tested for the task with a 113 word vocabulary, with a word perplexity of 4.1. It produces a sentence accuracy of 97.3% for the 10 open speakers' 110 sentences and the error reduction is as much as 77% compared with using context independent phone models.>

In promoting the ETSS project a program simulator based on an idea of partial interpretation has been constructed, and its principle and design are described in the paper. This new approach has been introduced to provide the simulator with such features as high speed and high accuracy in simulation and simplification in implementation. The essence of the idea of partial interpretation is using direct execution of instructions by hardware and simulation of them by an interpreter in combination, wherewith the hardware interrupt mechanism intermediates the two phases of the whole simulation. An interruption takes place when executing a "privileged" instruction, which triggers the simulation of the instruction. The other type of instructions are normally rendered to direct execution by hardware. The simulation method for devices operating in parallel is also described with respect to the timing control and scheduling. A program simulator of this type provides a powerful tool for debugging "supervisor " programs and opens a new approach to system expansion.