Sciweavers

ACL
1998
14 years 26 days ago
An Alternative LR Algorithm for TAGs
We present a new LR algorithm for treeadjoining grammars. It is an alternative to an existing algorithm that is shown to be incorrect. Furthermore, the new algorithm is much simpl...
Mark-Jan Nederhof
ACL
1998
14 years 26 days ago
Recognition of the Coherence Relation between Te-linked Clauses
This paper describes a method for recognizing coherence relations between clauses which are linked by te in Japanese -- a translational equivalent of English and. We consider that...
Akira Oishi, Yuji Matsumoto
ACL
1998
14 years 26 days ago
Translating a Unification Grammar with Disjunctions into Logical Constraints
This paper proposes a method for generating a logicalconstraint-based internal representation from a unification grammar formalism with disjunctive information. Unification gramma...
Mikio Nakano, Akira Shimazu
ACL
1998
14 years 26 days ago
Improving Statistical Natural Language Translation with Categories and Rules
This paper describes an all level approach on statistical natural language translation (SNLT). Without any predefined knowledge the system learns a statistical translation lexicon...
Franz Josef Och, Hans Weber
ACL
1998
14 years 26 days ago
Hypertext Authoring for Linking Relevant Segments of Related Instruction Manuals
Recently manuals of industrial products become large and often consist of separated volumes. In reading such individual but related manuals, we must consider the relation among se...
Hiroshi Nakagawa, Tatsunori Mori, Nobuyuki Omori, ...
ACL
1998
14 years 26 days ago
Integration of Large-Scale Linguistic Resources in a Natural Language Understanding System
Knowledge acquisition is a serious bottleneck for natural language understanding systems. For this reason, large-scale linguistic resources have been compiled and made available b...
Lewis M. Norton, Deborah A. Dahl, Li Li, Katharine...
ACL
1998
14 years 26 days ago
Japanese OCR Error Correction using Character Shape Similarity and Statistical Language Model
We present a novel OCR error correction method for languages without word delimiters that have a large character set, such as Japanese and Chinese. It consists of a statistical OC...
Masaaki Nagata