Sciweavers

ANLP
2000
96views more  ANLP 2000»
13 years 5 months ago
Efficient parsing strategies for syntactic analysis of closed captions
We present an efficientmulti-levelchart parser that was designed forsyntacticanalysisofclosedcaptions (subtitles) in a real-time Machine Translation (MT) system. In order to achie...
Krzysztof Czuba
ANLP
2000
60views more  ANLP 2000»
13 years 5 months ago
The Effectiveness of Corpus-Induced Dependency Grammars for Post-processing Speech
Mary P. Harper, Christopher M. White, Wen Wang, Mi...
ANLP
2000
107views more  ANLP 2000»
13 years 5 months ago
Multilingual Coreference Resolution
In this paper we present a new, multilingual data-driven method for coreference resolution as implemented in the SWIZZLE system. The results obtained after training this system on...
Sanda M. Harabagiu, Steven J. Maiorano
ANLP
2000
96views more  ANLP 2000»
13 years 5 months ago
Experiments with Corpus-based LFG Specialization
Sophisticated grammar formalisms, such as LFG, allow concisely capturing complex linguistic phenomena. The powerful operators provided by such formalisms can however introduce spu...
Nicola Cancedda, Christer Samuelsson
ANLP
2000
112views more  ANLP 2000»
13 years 5 months ago
Message Classification in the Call Center
Customer care in technical domains is increasingly based on e-mail communication, allowing for the reproduction of approved solutions. Identifying the customer's problem is o...
Stephan Busemann, Sven Schmeier, Roman Georg Arens
ANLP
2000
85views more  ANLP 2000»
13 years 5 months ago
Improving Testsuites via Instrumentation
This paper explores the usefulness of a technique from software engineering, namely code instrumentation, for the development of large-scale natural language grammars. Information...
Norbert Bröker
ANLP
2000
92views more  ANLP 2000»
13 years 5 months ago
TnT -- A Statistical Part-of-Speech Tagger
Trigrams'n'Tags (TnT) is an efficient statistical part-of-speech tagger. Contrary to claims found elsewhere in the literature, we argue that a tagger based on Markov mod...
Thorsten Brants
ANLP
2000
86views more  ANLP 2000»
13 years 5 months ago
A Finite State and Data-Oriented Method for Grapheme to Phoneme Conversion
A finite-state method, based on leftmost longestmatch replacement, is presented for segmenting words into graphemes, and for converting graphemes into phonemes. A small set of han...
Gosse Bouma