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 aswould like toandcan’tare 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.

This paper reports the improvements we made to our previously proposed hidden Markov model (HMM) based summarization method for multi-domain contact center dialogues. Since the method relied on Viterbi decoding for selecting utterances to include in a summary, it had the inability to control compression rates. We enhance our method by using the forward-backward algorithm together with integer linear programming (ILP) to enable the control of compression rates, realizing summaries that contain as many domain-related utterances and as many important words as possible within a predefined character length. Using call transcripts as input, we verify the effectiveness of our enhancement.

This paper describes a client-server speech translation platform designed for use at mobile terminals. Because terminals and servers are connected via a 3G public mobile phone networks, speech translation services are available at various places with thin client. This platform realizes hands-free communication and robustness for real use of speech translation in noisy environments. A microphone array and new noise suppression technique improves speech recognition performance, and a corpus-based approach enables wide coverage, robustness and portability to new languages and domains. The experimental result for evaluating the communicability of speakers of different languages shows that task completion rates using the speech translation system of 85% and 75% are achieved for Japanese- English and Japanese-Chinese, respectively. The system also has the ability to convey approximately one item of information per 2 utterances (one turn) on average for both Japanese-English and Japanese-Chinese in a task-oriented dialogue.

This paper investigates issues in preparing corpora for developing speech-to-speech translation (S2ST). It is impractical to create a broad-coverage parallel corpus only from dialog speech. An alternative approach is to have bilingual experts write conversational-style texts in the target domain, with translations. There is, however, a risk of losing fidelity to the actual utterances. This paper focuses on balancing a tradeoff between these two kinds of corpora through the analysis of two newly developed corpora in the travel domain: a bilingual parallel corpus with 420 K utterances and a collection of in-domain dialogs using actual S2ST systems. We found that the first corpus is effective for covering utterances in the second corpus if complimented with a small number of utterances taken from monolingual dialogs. We also found that characteristics of in-domain utterances become closer to those of the first corpus when more restrictive conditions and instructions to speakers are given. These results suggest the possibility of a bootstrap-style of development of corpora and S2ST systems, where an initial S2ST system is developed with parallel texts, and is then gradually improved with in-domain utterances collected by the system as restrictions are relaxed

In this paper, we describe the ATR multilingual speech-to-speech translation (S2ST) system, which is mainly focused on translation between English and Asian languages (Japanese and Chinese). There are three main modules of our S2ST system: large-vocabulary continuous speech recognition, machine text-to-text (T2T) translation, and text-to-speech synthesis. All of them are multilingual and are designed using state-of-the-art technologies developed at ATR. A corpus-based statistical machine learning framework forms the basis of our system design. We use a parallel multilingual database consisting of over 600 000 sentences that cover a broad range of travel-related conversations. Recent evaluation of the overall system showed that speech-to-speech translation quality is high, being at the level of a person having a Test of English for International Communication (TOEIC) score of 750 out of the perfect score of 990.

In this paper, a mis-recognized utterance detection and modification scheme is proposed to recover speech recognition errors in speech translation. In a speech recognition stage, mis-recognition is frequently observed. The most of mis-recognitions result from mis-match of acoustic models and out-of-vocabulary (OOV) words. To cope with both acoustic model mis-match and OOVs, we adopt a hierarchical language model to identify them. A hierarchical language model can generate both hypotheses with and without OOVs (or acoustic mis-matched words). Likelihood difference of these hypotheses is used as utterance confidence measure. To confirm the possibility of this scheme, as a first experiment, we have conducted speech recognition experiments and mis-recognized utterance detection. Experiment results showed 99% detection rate for utterances with OOVs. This rate is considerably higher than 94% of a conventional detection method using a-posteriori probability. The rate of 80%, which is comparable to a conventional method were obtained for the utterances without OOVs. These results support the possibility of the proposed error detection and modification scheme.

We intended to demonstrate the effect of using N-best speech recognition hypotheses for improving speech translation performance. A log-linear model, which integrated features from speech recognition and statistical machine translation, was used to rescore the translation candidates. Model parameters were estimated by optimizing an objectively measurable but subjectively relevant translation quality metric. Experimental results have shown that the proposed N-best approach improved translation quality over the conventional single-best approach. The improvements were confirmed consistently by several automatic translation evaluation metrics. 1.

This paper describes a natural language generation system developed for a spoken language translation system. Our system employs Feature‐structure‐based Tree Adjoining Grammar (FTAG) for generation knowledge representation. Each elementary tree of our grammar is paired with a semantic feature structure which is consistent with semantics defined in Head‐driven Phrase Structure Grammar. Feature structures attached to nodes of elementary trees are unrestricted. Thus our formalism allows HPSG style phrase structure description as well as TAG style description. The advantage of our generation knowledge representation is the ability of incorporating HPSG style “core” grammar and TAG style case‐based grammar. The system generates a syntactic tree by combining elementary trees so as to satisfy an input semantic structure. The generation algorithm is an application of a semantic head‐driven generation. To carry out an adjoining operation. an elementary tree with an adjunction node is dynamically split at the adjunction node during generation.