Michael Paul

The NiCT-ATR statistical machine translation system for the iwslt 2006 evaluation (2008)

Ruiqiang Zhang, Hirofumi Yamamoto, Michael Paul, Hideo Okuma, Keiji Yasuda, Yves Lepage, ...

This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2006 evaluation compaign. We participated in all four language pair translation tasks (CE, JE, AE and...

Exploiting Variant Corpora for Machine Translation (2008)

Michael Paul, Eiichiro Sumita

This paper proposes the usage of variant corpora, i.e., parallel text corpora that are equal in meaning but use different ways to express content, in order to improve corpus-based machine...

Exploiting Variant Corpora for Machine Translation (2008)

Michael Paul, Eiichiro Sumita

This paper proposes the usage of variant corpora, i.e., parallel text corpora that are equal in meaning but use different ways to express content, in order to improve corpus-based machine...

Nobody is Perfect: ATR’s Hybrid Approach to Spoken Language Translation (2005)

Michael Paul, Takao Doi, Youngsook Hwang, Kenji Imamura, Hideo Okuma, Eiichiro Sumita

This paper describes ATR’s hybrid approach to spoken language translation and it’s application to the IWSLT 2005 translation task. Multiple corpus-based translation engines are used to translate...

A CorpusCentered Approach to Spoken Language Translation (2003)

Eiichiro Sumita, Yasuhiro Akiba, Takao Doi, Andrew Finch, Kenji Imamura, Michael Paul, ...

This paper reports the latest performance of components and features of a project named Corpus-Centered Computation (cS), which targets a trans-lation technology suitable for spoken language...

Solutions to problems inherent in spoken-language translation: The atr-matrix approach (1999)

Eiichiro Sumita, Setsuo Yamada, Kazuhide Yamamoto, Michael Paul, Hideki Kashioka, Kai Ishikawa, ...

ATR has built a multi-language speech trans-lation system called ATR-MATRIX. It con-sists of a spoken-language translation sub-system, which is the focus of this paper, to-gether with a highly...

Corpus-based anaphora resolution towards antecedent preference (1999)

Michael Paul, Kazuhide Yamamoto, Eiichiro Sumita

In this paper we propose a corpus-based approach to anaphora resolution combin-ing a machine learning method and sta-tistical information. First, a decision tree trained on an annotated corpus...

Solutions to problems inherent in spoken-language translation: The atr-matrix approach (1999)

Eiichiro Sumita, Setsuo Yamada, Kazuhide Yamamoto, Michael Paul, Hideki Kashioka, Kai Ishikawa, ...

ATR has built a multi-language speech translation system called ATR-MATRIX. It consists of a spoken-language translation subsystem, which is the focus of this paper, together with a highly accurate...

Corpus-based anaphora resolution towards antecedent preference (1999)

Michael Paul, Kazuhide Yamamoto, Eiichiro Sumita

In this paper we propose a corpus-based approach to anaphora resolution combining a machine learning method and statistical information. First, a decision tree trained on an annotated corpus...

Basel II: Führen die neuen Anforderungen an die Kreditinstitute zu einer Benachteiligung des Mittelstands?

Werner Müller, Helmut Krämer-Eis, Gregor Taistra, Gerhard Hofmann, Thomas Heidorn, Stephan Paul, ...

In der Öffentlichkeit wurden Befürchtungen geäußert, dass Basel II den Mittelstand benachteilige, indem die Kreditverfügbarkeit für die Unternehmen eingeschränkt und ihre Zinskosten steigen...