Sciweavers

ACL
2010
13 years 5 months ago
Contextualizing Semantic Representations Using Syntactically Enriched Vector Models
We present a syntactically enriched vector model that supports the computation of contextualized semantic representations in a quasi compositional fashion. It employs a systematic...
Stefan Thater, Hagen Fürstenau, Manfred Pinka...
ACL
2010
13 years 5 months ago
Understanding the Semantic Structure of Noun Phrase Queries
Determining the semantic intent of web queries not only involves identifying their semantic class, which is a primary focus of previous works, but also understanding their semanti...
Xiao Li
ACL
2010
13 years 5 months ago
Bridging SMT and TM with Translation Recommendation
We propose a translation recommendation framework to integrate Statistical Machine Translation (SMT) output with Translation Memory (TM) systems. The framework recommends SMT outp...
Yifan He, Yanjun Ma, Josef van Genabith, Andy Way
ACL
2010
13 years 5 months ago
A Study of Information Retrieval Weighting Schemes for Sentiment Analysis
Most sentiment analysis approaches use as baseline a support vector machines (SVM) classifier with binary unigram weights. In this paper, we explore whether more sophisticated fea...
Georgios Paltoglou, Mike Thelwall
ACL
2010
13 years 5 months ago
Improved Unsupervised POS Induction through Prototype Discovery
We present a novel fully unsupervised algorithm for POS induction from plain text, motivated by the cognitive notion of prototypes. The algorithm first identifies landmark cluster...
Omri Abend, Roi Reichart, Ari Rappoport
ACL
2010
13 years 5 months ago
On Jointly Recognizing and Aligning Bilingual Named Entities
We observe that (1) how a given named entity (NE) is translated (i.e., either semantically or phonetically) depends greatly on its associated entity type, and (2) entities within ...
Yufeng Chen, Chengqing Zong, Keh-Yih Su
ACL
2010
13 years 5 months ago
The Importance of Rule Restrictions in CCG
Combinatory Categorial Grammar (CCG) is generally construed as a fully lexicalized formalism, where all grammars use one and the same universal set of rules, and crosslinguistic v...
Marco Kuhlmann, Alexander Koller, Giorgio Satta
ACL
2010
13 years 5 months ago
Rebanking CCGbank for Improved NP Interpretation
Once released, treebanks tend to remain unchanged despite any shortcomings in their depth of linguistic analysis or coverage of specific phenomena. Instead, separate resources are...
Matthew Honnibal, James R. Curran, Johan Bos
ACL
2010
13 years 5 months ago
Extraction and Approximation of Numerical Attributes from the Web
We present a novel framework for automated extraction and approximation of numerical object attributes such as height and weight from the Web. Given an object-attribute pair, we d...
Dmitry Davidov, Ari Rappoport
ACL
2010
13 years 5 months ago
Conditional Random Fields for Word Hyphenation
Finding allowable places in words to insert hyphens is an important practical problem. The algorithm that is used most often nowadays has remained essentially unchanged for 25 yea...
Nikolaos Trogkanis, Charles Elkan