Sciweavers

EMNLP
2006
14 years 6 days ago
Learning Information Status of Discourse Entities
In this paper we address the issue of automatically assigning information status to discourse entities. Using an annotated corpus of conversational English and exploiting morpho-s...
Malvina Nissim
EMNLP
2006
14 years 6 days ago
Loss Minimization in Parse Reranking
We propose a general method for reranker construction which targets choosing the candidate with the least expected loss, rather than the most probable candidate. Different approac...
Ivan Titov, James Henderson
EMNLP
2006
14 years 6 days ago
Incremental Integer Linear Programming for Non-projective Dependency Parsing
Integer Linear Programming has recently been used for decoding in a number of probabilistic models in order to enforce global constraints. However, in certain applications, such a...
Sebastian Riedel, James Clarke
EMNLP
2006
14 years 6 days ago
Semantic Role Labeling of NomBank: A Maximum Entropy Approach
This paper describes our attempt at NomBank-based automatic Semantic Role Labeling (SRL). NomBank is a project at New York University to annotate the argument structures for commo...
Zheng Ping Jiang, Hwee Tou Ng
EMNLP
2006
14 years 6 days ago
Paraphrase Recognition via Dissimilarity Significance Classification
We propose a supervised, two-phase framework to address the problem of paraphrase recognition (PR). Unlike most PR systems that focus on sentence similarity, our framework detects...
Long Qiu, Min-Yen Kan, Tat-Seng Chua
EMNLP
2006
14 years 6 days ago
Modeling Impression in Probabilistic Transliteration into Chinese
For transliterating foreign words into Chinese, the pronunciation of a source word is spelled out with Kanji characters. Because Kanji comprises ideograms, an individual pronuncia...
LiLi Xu, Atsushi Fujii, Tetsuya Ishikawa
EMNLP
2006
14 years 6 days ago
Graph-based Word Clustering using a Web Search Engine
Word clustering is important for automatic thesaurus construction, text classification, and word sense disambiguation. Recently, several studies have reported using the web as a c...
Yutaka Matsuo, Takeshi Sakaki, Koki Uchiyama, Mits...
EMNLP
2006
14 years 6 days ago
Lexicon Acquisition for Dialectal Arabic Using Transductive Learning
We investigate the problem of learning a part-of-speech (POS) lexicon for a resource-poor language, dialectal Arabic. Developing a high-quality lexicon is often the first step tow...
Kevin Duh, Katrin Kirchhoff
EMNLP
2006
14 years 6 days ago
Boosting Unsupervised Relation Extraction by Using NER
Web extraction systems attempt to use the immense amount of unlabeled text in the Web in order to create large lists of entities and relations. Unlike traditional IE methods, the ...
Ronen Feldman, Benjamin Rosenfeld