Traditional approaches to word sense disambiguation (WSD) rest on the assumption that there exists a single, unambiguous communicative intention underlying every word in a documen...
Constituent parsing is typically modeled by a chart-based algorithm under probabilistic context-free grammars or by a transition-based algorithm with rich features. Previous model...
A joint-space model for cross-lingual distributed representations generalizes language-invariant semantic features. In this paper, we present a matrix cofactorization framework fo...
Traditional learning to rank methods learn ranking models from training data in a batch and offline learning mode, which suffers from some critical limitations, e.g., poor scalab...
Jialei Wang, Ji Wan, Yongdong Zhang, Steven C. H. ...
Deception detection has been formulated as a supervised binary classification problem on single documents. However, in daily life, millions of fraud cases involve detailed conver...
Dian Yu, Yulia Tyshchuk, Heng Ji, William A. Walla...
This paper is the first to examine the effect of prosodic features on coreference resolution in spoken discourse. We test features from different prosodic levels and investigate ...
In this paper, we propose a flexible principle-based approach (PBA) for reader-emotion classification and writing assistance. PBA is a highly automated process that learns emoti...
An event chronicle provides people with an easy and fast access to learn the past. In this paper, we propose the first novel approach to automatically generate a topically releva...
Tao Ge, Wenzhe Pei, Heng Ji, Sujian Li, Baobao Cha...
We characterize a class of indirect answers to yes/no questions, alternative answers, where information is given that is not directly asked about, but which might nonetheless addr...
Jon Scott Stevens, Anton Benz, Sebastian Reuß...
Rumours on social media exhibit complex temporal patterns. This paper develops a model of rumour prevalence using a point process, namely a log-Gaussian Cox process, to infer an u...