Sciweavers

EMNLP
2009
13 years 2 months ago
It's Not You, it's Me: Detecting Flirting and its Misperception in Speed-Dates
Automatically detecting human social intentions from spoken conversation is an important task for dialogue understanding. Since the social intentions of the speaker may differ fro...
Rajesh Ranganath, Dan Jurafsky, Dan McFarland
EMNLP
2009
13 years 2 months ago
Real-Word Spelling Correction using Google Web 1T 3-grams
We present a method for detecting and correcting multiple real-word spelling errors using the Google Web 1T 3-gram data set and a normalized and modified version of the Longest Co...
Aminul Islam, Diana Inkpen
EMNLP
2009
13 years 2 months ago
Consensus Training for Consensus Decoding in Machine Translation
We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram count...
Adam Pauls, John DeNero, Dan Klein
EMNLP
2009
13 years 2 months ago
Combining Collocations, Lexical and Encyclopedic Knowledge for Metonymy Resolution
This paper presents a supervised method for resolving metonymies. We enhance a commonly used feature set with features extracted based on collocation information from corpora, gen...
Vivi Nastase, Michael Strube
EMNLP
2009
13 years 2 months ago
Discovery of Term Variation in Japanese Web Search Queries
In this paper we address the problem of identifying a broad range of term variations in Japanese web search queries, where these variations pose a particularly thorny problem due ...
Hisami Suzuki, Xiao Li, Jianfeng Gao
EMNLP
2009
13 years 2 months ago
Large-Scale Verb Entailment Acquisition from the Web
Textual entailment recognition plays a fundamental role in tasks that require indepth natural language understanding. In order to use entailment recognition technologies for real-...
Chikara Hashimoto, Kentaro Torisawa, Kow Kuroda, S...
EMNLP
2009
13 years 2 months ago
Stream-based Randomised Language Models for SMT
Randomised techniques allow very big language models to be represented succinctly. However, being batch-based they are unsuitable for modelling an unbounded stream of language whi...
Abby Levenberg, Miles Osborne
EMNLP
2009
13 years 2 months ago
Person Cross Document Coreference with Name Perplexity Estimates
The Person Cross Document Coreference systems depend on the context for making decisions on the possible coreferences between person name mentions. The amount of context required ...
Octavian Popescu
EMNLP
2009
13 years 2 months ago
Multilingual Spectral Clustering Using Document Similarity Propagation
We present a novel approach for multilingual document clustering using only comparable corpora to achieve cross-lingual semantic interoperability. The method models document colle...
Dani Yogatama, Kumiko Tanaka-Ishii
EMNLP
2009
13 years 2 months ago
Acquiring Translation Equivalences of Multiword Expressions by Normalized Correlation Frequencies
In this paper, we present an algorithm for extracting translations of any given multiword expression from parallel corpora. Given a multiword expression to be translated, the meth...
Ming-Hong Bai, Jia-Ming You, Keh-Jiann Chen, Jason...