We propose a method of revising lead sentences in a news broadcast. Unlike many other methods proposed so far, this method does not use the coreference relation of noun phrases (NPs) but rather, insertion and substitution of the phrases modifying the same head chunk in lead and other sentences. The method borrows an idea from the sentence fusion methods and is more general than those using NP coreferencing as ours includes them. We show in experiments the method was able to find semantically appropriate revisions thus demonstrating its basic feasibility. We also show that that parsing errors mainly degraded the sentential completeness such as grammaticality and redundancy.

HIDEKITANAKA t,TADASHI KUMANOtt,NORIYOSHI URATANItt and TERUMASA EHARAttWe are developing a Japanese-to-English Translation Aid system for news translators.The system consists of a voluminous bilingual news database whose sentences are properly aligned across languages beforehand,and a similar expression search engine.A user can find past translation examples of input Japanese with the system. Similar expression search engines like the one in this paper have usually employed an AND retrieval technique that uses keywords in the input expression,to measure the similarity between the input and the target by the number of shared keywords. In many cases of applying such search engines to our database,however,a number of spurious search results have been produced as a consequence:the sentences have been quite long(88.9 Japanese characters on average)and a single sentence has often contained identical keywords many times.In this paper,we propose adding two constraints to the AND retrieval technique:the order and positions(deviations)of keywords.We enhance AND retrieval allowing it to be able to reflect some syntactic similarity by this inexpensive modification.We will show, through a set of experiments,that the proposed method significantly improves the level of user satisfaction in search results in a statistical sense,with only a 1.3-fold increase in the search time.

This paper describes a method to control prosodic features using phonetic and prosodic symbols as input of attention-based sequenceto-sequence (seq2seq) acoustic modeling (AM) for neural text-to-speech (TTS). The method involves inserting a sequence of prosodic symbols between phonetic symbols that are then used to reproduce prosodic acoustic features, i.e. accents, pauses, accent breaks, and sentence endings, in several seq2seq AM methods. The proposed phonetic and prosodic labels have simple descriptions and a low production cost. By contrast, the labels of conventional statistical parametric speech synthesis methods are complicated, and the cost of time alignments such as aligning the boundaries of phonemes is high. The proposed method does not need the boundary positions of phonemes. We propose an automatic conversion method for conventional labels and show how to automatically reproduce pitch accents and phonemes. The results of objective and subjective evaluations show the effectiveness of our method.

No abstract

SUMMARYMachine translation technology is currently incapable of producing translations of the high quality required for purposes such as broadcast news. Such translations still require skilled human translators. We have developed a translation aid system to support translators in such tasks. The system retrieves news articles by answering user queries, and shows the entire article together with the corresponding translated article. The system does not require manual alignment of each sentence with its translation when storing articles in a database. Thus, it is capable of handling flexible translations. Moreover, the system helps users learn not just the translations for queried expressions, but also the facts described in the articles, which can aid in producing good translations. The results of a user inquiry demonstrated the validity of the system.