Sciweavers

ACL
2007
13 years 9 months ago
Formalism-Independent Parser Evaluation with CCG and DepBank
A key question facing the parsing community is how to compare parsers which use different grammar formalisms and produce different output. Evaluating a parser on the same resource...
Stephen Clark, James R. Curran
ACL
2008
13 years 9 months ago
Mining Wikipedia Revision Histories for Improving Sentence Compression
A well-recognized limitation of research on supervised sentence compression is the dearth of available training data. We propose a new and bountiful resource for such training dat...
Elif Yamangil, Rani Nelken
ACL
2007
13 years 9 months ago
Forest-to-String Statistical Translation Rules
In this paper, we propose forest-to-string rules to enhance the expressive power of tree-to-string translation models. A forestto-string rule is capable of capturing nonsyntactic ...
Yang Liu, Yun Huang, Qun Liu, Shouxun Lin
ACL
2008
13 years 9 months ago
Intrinsic vs. Extrinsic Evaluation Measures for Referring Expression Generation
In this paper we present research in which we apply (i) the kind of intrinsic evaluation metrics that are characteristic of current comparative HLT evaluation, and (ii) extrinsic,...
Anja Belz, Albert Gatt
ACL
2007
13 years 9 months ago
A discriminative language model with pseudo-negative samples
In this paper, we propose a novel discriminative language model, which can be applied quite generally. Compared to the well known N-gram language models, discriminative language m...
Daisuke Okanohara, Jun-ichi Tsujii
ACL
2008
13 years 9 months ago
Robust Extraction of Named Entity Including Unfamiliar Word
This paper proposes a novel method to extract named entities including unfamiliar words which do not occur or occur few times in a training corpus using a large unannotated corpus...
Masatoshi Tsuchiya, Shinya Hida, Seiichi Nakagawa
ACL
2007
13 years 9 months ago
Conditional Modality Fusion for Coreference Resolution
Non-verbal modalities such as gesture can improve processing of spontaneous spoken language. For example, similar hand gestures tend to predict semantic similarity, so features th...
Jacob Eisenstein, Randall Davis
ACL
2008
13 years 9 months ago
Exploiting N-best Hypotheses for SMT Self-Enhancement
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
Boxing Chen, Min Zhang, AiTi Aw, Haizhou Li
ACL
2008
13 years 9 months ago
Extracting a Representation from Text for Semantic Analysis
We present a novel fine-grained semantic representation of text and an approach to constructing it. This representation is largely extractable by today's technologies and fac...
Rodney D. Nielsen, Wayne Ward, James H. Martin, Ma...
ACL
2008
13 years 9 months ago
Event Matching Using the Transitive Closure of Dependency Relations
This paper describes a novel event-matching strategy using features obtained from the transitive closure of dependency relations. The method yields a model capable of matching eve...
Daniel M. Bikel, Vittorio Castelli