Sciweavers

ACL
2010
13 years 10 months ago
Untangling the Cross-Lingual Link Structure of Wikipedia
Wikipedia articles in different languages are connected by interwiki links that are increasingly being recognized as a valuable source of cross-lingual information. Unfortunately,...
Gerard de Melo, Gerhard Weikum
ACL
2010
13 years 10 months ago
Open-Domain Semantic Role Labeling by Modeling Word Spans
Most supervised language processing systems show a significant drop-off in performance when they are tested on text that comes from a domain significantly different from the domai...
Fei Huang, Alexander Yates
ACL
2010
13 years 10 months ago
Creating Robust Supervised Classifiers via Web-Scale N-Gram Data
In this paper, we systematically assess the value of using web-scale N-gram data in state-of-the-art supervised NLP classifiers. We compare classifiers that include or exclude fea...
Shane Bergsma, Emily Pitler, Dekang Lin
ACL
2010
13 years 10 months ago
Bitext Dependency Parsing with Bilingual Subtree Constraints
This paper proposes a dependency parsing method that uses bilingual constraints to improve the accuracy of parsing bilingual texts (bitexts). In our method, a targetside tree frag...
Wenliang Chen, Jun'ichi Kazama, Kentaro Torisawa
ACL
2010
13 years 10 months ago
Wikipedia as Sense Inventory to Improve Diversity in Web Search Results
Is it possible to use sense inventories to improve Web search results diversity for one word queries? To answer this question, we focus on two broad-coverage lexical resources of ...
Celina Santamaría, Julio Gonzalo, Javier Ar...
ACL
2010
13 years 10 months ago
Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities
Quantifying the semantic relevance between questions and their candidate answers is essential to answer detection in social media corpora. In this paper, a deep belief network is ...
Baoxun Wang, Xiaolong Wang, Chengjie Sun, Bingquan...
ACL
2010
13 years 10 months ago
Topic Models for Word Sense Disambiguation and Token-Based Idiom Detection
This paper presents a probabilistic model for sense disambiguation which chooses the best sense based on the conditional probability of sense paraphrases given a context. We use a...
Linlin Li, Benjamin Roth, Caroline Sporleder
ACL
2010
13 years 10 months ago
Entity-Based Local Coherence Modelling Using Topological Fields
One goal of natural language generation is to produce coherent text that presents information in a logical order. In this paper, we show that topological fields, which model high-...
Jackie Chi Kit Cheung, Gerald Penn
ACL
2010
13 years 10 months ago
Efficient Staggered Decoding for Sequence Labeling
The Viterbi algorithm is the conventional decoding algorithm most widely adopted for sequence labeling. Viterbi decoding is, however, prohibitively slow when the label set is larg...
Nobuhiro Kaji, Yasuhiro Fujiwara, Naoki Yoshinaga,...
ACL
2010
13 years 10 months ago
Joint Syntactic and Semantic Parsing of Chinese
This paper explores joint syntactic and semantic parsing of Chinese to further improve the performance of both syntactic and semantic parsing, in particular the performance of sem...
Junhui Li, Guodong Zhou, Hwee Tou Ng