Sciweavers

ACL
2001
13 years 11 months ago
Underspecified Beta Reduction
For ambiguous sentences, traditional semantics construction produces large numbers of higher-order formulas, which must then be -reduced individually. Underspecified versions can ...
Manuel Bodirsky, Katrin Erk, Alexander Koller, Joa...
ACL
2003
13 years 11 months ago
Generating Parallel Multilingual LFG-TAG Grammars from a MetaGrammar
We introduce a MetaGrammar, which allows us to automatically generate, from a single and compact MetaGrammar hierarchy, parallel Lexical Functional Grammars (LFG) and Tree-Adjoini...
Lionel Clément, Alexandra Kinyon
ACL
2001
13 years 11 months ago
What is the Minimal Set of Fragments that Achieves Maximal Parse Accuracy?
We aim at finding the minimal set of fragments which achieves maximal parse accuracy in Data Oriented Parsing. Experiments with the Penn Wall Street Journal treebank show that cou...
Rens Bod
ACL
2003
13 years 11 months ago
Closing the Gap: Learning-Based Information Extraction Rivaling Knowledge-Engineering Methods
In this paper, we present a learning approach to the scenario template task of information extraction, where information filling one template could come from multiple sentences. ...
Hai Leong Chieu, Hwee Tou Ng, Yoong Keok Lee
ACL
2001
13 years 11 months ago
Low-cost, High-Performance Translation Retrieval: Dumber is Better
In this paper, we compare the relative effects of segment order, segmentation and segment contiguity on the retrieval performance of a translation memory system. We take a selecti...
Timothy Baldwin
ACL
2003
13 years 11 months ago
A Probability Model to Improve Word Alignment
Word alignment plays a crucial role in statistical machine translation. Word-aligned corpora have been found to be an excellent source of translation-related knowledge. We present...
Colin Cherry, Dekang Lin
ACL
2001
13 years 11 months ago
Improvement of a Whole Sentence Maximum Entropy Language Model Using Grammatical Features
In this paper, we propose adding long-term grammatical information in a Whole Sentence Maximun Entropy Language Model (WSME) in order to improve the performance of the model. The ...
Fredy A. Amaya, José-Miguel Benedí
ACL
2003
13 years 11 months ago
Uncertainty Reduction in Collaborative Bootstrapping: Measure and Algorithm
This paper proposes the use of uncertainty reduction in machine learning methods such as co-training and bilingual bootstrapping, which are referred to, in a general term, as ‘c...
Yunbo Cao, Hang Li, Li Lian
ACL
2001
13 years 11 months ago
Extracting Paraphrases from a Parallel Corpus
While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases. We present ...
Regina Barzilay, Kathleen McKeown
ACL
2003
13 years 11 months ago
Integrating Discourse Markers into a Pipelined Natural Language Generation Architecture
Pipelined Natural Language Generation (NLG) systems have grown increasingly complex as architectural modules were added to support language functionalities such as referring expre...
Charles B. Callaway