Kenji Imamura

Feedback Cleaning of Machine Translation Rules Using Automatic Evaluation

When rules of transfer-based machine translation (MT) are automatically acquired from bilingual corpora, incorrect/redundant rules are generated due to acquisition errors or translation variety in the corpora. As a new countermeasure to this problem, we propose a feedback cleaning method using automatic evaluation of MT quality, which removes incorrect/redundant rules as a way to increase the evaluation score. BLEU is utilized for the automatic evaluation. The hill-climbing algorithm, which involves features of this task, is applied to searching for the optimal combination of rules. Our experiments show that the MT quality improves by 10% in test sentences according to a subjective evaluation. This is considerable improvement over previous methods.

Discriminative Approach to Predicate-Argument Structure Analysis with Zero-Anaphora Resolution

This paper presents a predicate-argument structure analysis that simultaneously conducts zero-anaphora resolution. By adding noun phrases as candidate arguments that are not only in the sentence of the target predicate but also outside of the sentence, our analyzer identifies arguments regardless of whether they appear in the sentence or not. Because we adopt discriminative models based on maximum entropy for argument identification, we can easily add new features. We add language model scores as well as contextual features. We also use contextual information to restrict candidate arguments.

Japanese Dependency Parsing Using Sequential Labeling for Semi-spoken Language

The amount of documents directly published by end users is increasing along with the growth of Web 2.0. Such documents often contain spoken-style expressions, which are difficult to analyze using conventional parsers. This paper presents dependency parsing whose goal is to analyze Japanese semi-spoken expressions. One characteristic of our method is that it can parse self-dependent (independent) segments using sequential labeling.

A corpus-centered approach to spoken language translation

This paper reports the latest performance of components and features of a project named Corpus-Centered Computation (C3), which targets a translation technology suitable for spoken language translation. C3 places corpora at the center of the technology. Translation knowledge is extracted from corpora by both EBMT and SMT methods, translation quality is gauged by referring to corpora, the best translation among multiple-engine outputs is selected based on corpora and the corpora themselves are paraphrased or filtered by automated processes.

Evolution of NTT high-capacity land mobile communication system

The development of a land mobile communication system, MCS-L2 which is Japans second-generation analog cellular system is presented. The system operates in the 800-MHz band, and service commenced in May 1988 by overlaying it on the first-generation system, MCS-L1, sharing the 15-MHz*2 frequency resources. The field trial results are described. Techniques for increasing the frequency spectrum utilization such as radio zone sectorisation, flexible channel assignment and radio channel interleaving further intended to be applied to MCS-L2 are also discussed. Techniques established by MCS-L2 are basic techniques for digital mobile radio systems.<<ETX>>

Using Multiple Edit Distances to Automatically Grade Outputs From Machine Translation Systems

This paper addresses the challenging problem of automatically evaluating output from machine translation (MT) systems that are subsystems of speech-to-speech MT (SSMT) systems. Conventional automatic MT evaluation methods include BLEU, which MT researchers have frequently used. However, BLEU has two drawbacks in SSMT evaluation. First, BLEU assesses errors lightly at the beginning of translations and heavily in the middle, even though its assessments should be independent of position. Second, BLEU lacks tolerance in accepting colloquial sentences with small errors, although such errors do not prevent us from continuing an SSMT-mediated conversation. In this paper, the authors report a new evaluation method called “g Rader based on Edit Distances (RED)” that automatically grades each MT output by using a decision tree (DT). The DT is learned from training data that are encoded by using multiple edit distances, that is, normal edit distance (ED) defined by insertion, deletion, and replacement, as well as its extensions. The use of multiple edit distances allows more tolerance than either ED or BLEU. Each evaluated MT output is assigned a grade by using the DT. RED and BLEU were compared for the task of evaluating MT systems of varying quality on ATRs Basic Travel Expression Corpus (BTEC). Experimental results show that RED significantly outperforms BLEU.

Automatic expansion of equivalent sentence set based on syntactic substitution

In this paper, we propose an automatic quantitative expansion method for a sentence set that contains sentences of the same meaning (called an equivalent sentence set). This task is regarded as paraphrasing. The features of our method are: 1) The paraphrasing rules are dynamically acquired by Hierarchical Phrase Alignment from the equivalent sentence set, and 2) A large equivalent sentence set is generated by substituting source syntactic structures. Our experiments show that 561 sentences on average are correctly generated from 8.48 equivalent sentences.

Supervision and control in cellular systems

The necessity for a novel cellular supervision and control system is described from two points of view. The first view is that increasing service complexity and customer demands are forcing the creation of a supervision and control system that will apply a common database and a unified approach to network management. The other point of view is that a supervision and control system should have improved automatic and remote functions, and should provide the operator with simplified interfaces. The system function structure, which is hierarchical, will permit extensive and sophisticated cellular network operations to effect the required total network operations. The appropriate design objectives are described, and methods for their implementations are discussed.<<ETX>>

Normalizing Complex Functional Expressions in Japanese Predicates: Linguistically-Directed Rule-Based Paraphrasing and Its Application

The growing need for text mining systems, such as opinion mining, requires a deep semantic understanding of the target language. In order to accomplish this, extracting the semantic information of functional expressions plays a crucial role, because functional expressions such as would like to and can’t are key expressions to detecting customers’ needs and wants. However, in Japanese, functional expressions appear in the form of suffixes, and two different types of functional expressions are merged into one predicate: one influences the factual meaning of the predicate while the other is merely used for discourse purposes. This triggers an increase in surface forms, which hinders information extraction systems. In this article, we present a novel normalization technique that paraphrases complex functional expressions into simplified forms that retain only the crucial meaning of the predicate. We construct paraphrasing rules based on linguistic theories in syntax and semantics. The results of experiments indicate that our system achieves a high accuracy of 79.7%, while it reduces the differences in functional expressions by up to 66.7%. The results also show an improvement in the performance of predicate extraction, providing encouraging evidence of the usability of paraphrasing as a means of normalizing different language expressions.

Paraphrasing Japanese Light Verb Constructions: Towards the Normalization of Complex Predicates

We introduce novel paraphrasing rules for Japanese light verb constructions (LVCs) that reduce the differences in the surface forms while retaining several of the crucial syntactic/semantic functions of these light verbs. An analysis of the linguistic properties of light verbs allows us to create paraphrasing patterns that map 151 different light verbs into 10 simple forms. Of these 10 forms, 7 convert complex noun-particle-verb structures into simple predicative forms. By constructing a list of 923 examples for ambiguous light verbs, we show that we can correctly distinguish real LVCs from those in which the light verbs were actually functioning as a main verb. The results of experiments indicate that our paraphrasing rules offer high accuracy. The experiments also reveal that our paraphrasing system works as a normalizer of complex predicates, which improves the recall rate of the predicate extraction task.