Sciweavers

ACL
2012
12 years 1 months ago
Learning Better Rule Extraction with Translation Span Alignment
This paper presents an unsupervised approach to learning translation span alignments from parallel data that improves syntactic rule extraction by deleting spurious word alignment...
Jingbo Zhu, Tong Xiao, Chunliang Zhang
ACL
2012
12 years 1 months ago
Subgroup Detector: A System for Detecting Subgroups in Online Discussions
We present Subgroup Detector, a system for analyzing threaded discussions and identifying the attitude of discussants towards one another and towards the discussion topic. The sys...
Amjad Abu-Jbara, Dragomir R. Radev
COLING
2010
13 years 6 months ago
Enhancing Morphological Alignment for Translating Highly Inflected Languages
We propose an unsupervised approach utilizing only raw corpora to enhance morphological alignment involving highly inflected languages. Our method focuses on closed-class morpheme...
Minh-Thang Luong, Min-Yen Kan
EMNLP
2009
13 years 9 months ago
Unsupervised Semantic Parsing
We present the first unsupervised approach to the problem of learning a semantic parser, using Markov logic. Our USP system transforms dependency trees into quasi-logical forms, r...
Hoifung Poon, Pedro Domingos
NAACL
2010
13 years 9 months ago
Unsupervised Modeling of Twitter Conversations
We propose the first unsupervised approach to the problem of modeling dialogue acts in an open domain. Trained on a corpus of noisy Twitter conversations, our method discovers dia...
Alan Ritter, Colin Cherry, Bill Dolan
ACL
2008
14 years 27 days ago
An Unsupervised Approach to Biography Production Using Wikipedia
We describe an unsupervised approach to multi-document sentence-extraction based summarization for the task of producing biographies. We utilize Wikipedia to automatically constru...
Fadi Biadsy, Julia Hirschberg, Elena Filatova
CIKM
2008
Springer
14 years 1 months ago
Using tag semantic network for keyphrase extraction in blogs
Folksonomies provide a comfortable way to search and browse the blogosphere. As the tags in the blogosphere are sparse, ambiguous and too general, this paper proposes both a super...
Lizhen Qu, Christof Müller, Iryna Gurevych
ICMCS
2007
IEEE
96views Multimedia» more  ICMCS 2007»
14 years 5 months ago
Role Recognition in Broadcast News using Bernoulli Distributions
This work presents an approach for the recognition of the roles played by speakers participating in radio broadcast news (e.g. anchorman or guest). The approach includes two main ...
Alessandro Vinciarelli