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...
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...
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...
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...
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 ...
Textual entailment recognition plays a fundamental role in tasks that require indepth natural language understanding. In order to use entailment recognition technologies for real-...
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...
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 ...
We present a novel approach for multilingual document clustering using only comparable corpora to achieve cross-lingual semantic interoperability. The method models document colle...
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...