Sciweavers

EMNLP
2009
13 years 2 months ago
A Syntactified Direct Translation Model with Linear-time Decoding
Recent syntactic extensions of statistical translation models work with a synchronous context-free or tree-substitution grammar extracted from an automatically parsed parallel cor...
Hany Hassan, Khalil Sima'an, Andy Way
EMNLP
2009
13 years 2 months ago
Semi-supervised Speech Act Recognition in Emails and Forums
In this paper, we present a semi-supervised method for automatic speech act recognition in email and forums. The major challenge of this task is due to lack of labeled data in the...
Minwoo Jeong, Chin-Yew Lin, Gary Geunbae Lee
EMNLP
2009
13 years 2 months ago
Segmenting Email Message Text into Zones
In the early days of email, widely-used conventions for indicating quoted reply content and email signatures made it easy to segment email messages into their functional parts. To...
Andrew Lampert, Robert Dale, Cécile Paris
EMNLP
2009
13 years 2 months ago
Web-Scale Distributional Similarity and Entity Set Expansion
Computing the pairwise semantic similarity between all words on the Web is a computationally challenging task. Parallelization and optimizations are necessary. We propose a highly...
Patrick Pantel, Eric Crestan, Arkady Borkovsky, An...
EMNLP
2009
13 years 2 months ago
Projecting Parameters for Multilingual Word Sense Disambiguation
We report in this paper a way of doing Word Sense Disambiguation (WSD) that has its origin in multilingual MT and that is cognizant of the fact that parallel corpora, wordnets and...
Mitesh M. Khapra, Sapan Shah, Piyush Kedia, Pushpa...
EMNLP
2009
13 years 2 months ago
Automatically Evaluating Content Selection in Summarization without Human Models
We present a fully automatic method for content selection evaluation in summarization that does not require the creation of human model summaries. Our work capitalizes on the assu...
Annie Louis, Ani Nenkova
EMNLP
2009
13 years 2 months ago
Improved Statistical Machine Translation Using Monolingually-Derived Paraphrases
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
Yuval Marton, Chris Callison-Burch, Philip Resnik
EMNLP
2009
13 years 2 months ago
Semi-Supervised Learning for Semantic Relation Classification using Stratified Sampling Strategy
This paper presents a new approach to selecting the initial seed set using stratified sampling strategy in bootstrapping-based semi-supervised learning for semantic relation class...
Longhua Qian, Guodong Zhou, Fang Kong, Qiaoming Zh...
EMNLP
2009
13 years 2 months ago
Polylingual Topic Models
Topic models are a useful tool for analyzing large text collections, but have previously been applied in only monolingual, or at most bilingual, contexts. Meanwhile, massive colle...
David M. Mimno, Hanna M. Wallach, Jason Naradowsky...
EMNLP
2009
13 years 2 months ago
Supervised and Unsupervised Methods in Employing Discourse Relations for Improving Opinion Polarity Classification
This work investigates design choices in modeling a discourse scheme for improving opinion polarity classification. For this, two diverse global inference paradigms are used: a su...
Swapna Somasundaran, Galileo Namata, Janyce Wiebe,...