Since scripts were proposed in the 1970’s as an inferencing mechanism for AI and natural language processing programs, there have been few attempts to build a database of scripts. This paper describes a database and lexicon of scripts that has been added to the ThoughtTreasure commonsense platform. The database provides the following information about scripts: sequence of events, roles, props, ...

Social scientists who do not have specialized natural language processing training often use a unigram bag-of-words (BOW) representation when analyzing text corpora. We offer a new phrase-based method, NPFST, for enriching a unigram BOW. NPFST uses a partof-speech tagger and a finite state transducer to extract multiword phrases to be added to a unigram BOW. We compare NPFST to both ngram and p...

While a word in isolation has a high potential of expressing various senses, in certain phrases this potential is restricted up to the point that one and only one sense is possible. A phrase is called sense stable if the senses of all the words compounding it do not change their sense irrespective of the context which could be added to its left or to its right. By comparing sense stable phrases...

This paper reports our work to improve a bigram language model for Japanese TV broadcast news speech recognition. First, frequent word strings were grouped into phrases in order that the phrases were added to the lexicon as new units of recognition. The test set perplexity was improved when frequent function word strings were used as additional recognition units. The speech recognition performa...

Translation capability of a Phrase-Based Statistical Machine Translation (PBSMT) system mostly depends on parallel data and phrases that are not present in the training data are not correctly translated. This paper describes a method that efficiently expands the existing knowledge of a PBSMT system without adding more parallel data but using external morphological resources. A set of new phrase...

We discuss a restricted natural language understanding system and a proposed extension to it, which is a corpus of phrases. The Controlled English to Logic Translation (CELT) system allows users to make statements in a domain-independent, restricted English grammar that have a clear formal semantics and that are amenable to machine processing. CELT needs a large amount of linguistic and semanti...

When developing Japanese text-to-speech (TTS) systems, algorithms to accurately predict accent types of each constituent phrase is essential for better output speech quality. In our previous studies on the accent type estimation, a CRF-based method was realized. Although this method outperformed the conventional rule-based method, the estimation accuracy of particular phrases such as those incl...

0 1 5 Frequency [GHz] 6 2 3 4 Abstract The validity of lumped element microwave class-F amplifier circuit design has been demonstrated experimentally. By means of the proposed class-F amplifier design method, more than 4th-order higher harmonic frequencies can be taken into account in class-F microwave amplifier design using only lumped element components. In this approach, miniaturization of c...

The emerging service-dominant logic requires cooperation between several partners in a value-added network or value chain. Information asymmetry and information gaps may lead to uncovered and unused knowledge. This paper addresses how this problem can be solved by suggesting an approach based on contingency theory. The core idea consists of supporting and improving value-added partnerships by e...