Эмпирикалық нәтижелер

We describe a new sentence realization framework for text-to-text applications. This framework uses IDL-expressions as a representation formalism, and a gener- ation mechanism based on algorithms for intersecting IDL-expressions with …...

This paper discusses the use of factoriza- tion techniques in distributional semantic models. We focus on a method for re- distributing the weight of latent variables, which has previously been …...

AbstractWe develop a formal hierarchy of the expressive capacity of RNN architectures. The hierarchy is based on two formal properties: space complexity, which measures the RNN’s memory, and rational recurrence, …...

AbstractGenerating a concise summary from a large collection of arguments on a given topic is an intriguing yet understudied problem. We propose to represent such summaries as a small set …...

AbstractCross-domain NER is a practical yet challenging problem since the data scarcity in the real-world scenario. A common practice is first to learn a NER model in a rich-resource general …...

AbstractThe ability to generalize compositionally is key to understanding the potentially infinite number of sentences that can be constructed in a human language from only a finite number of words. …...

AbstractUnsupervised out-of-domain (OOD) detection is a task aimed at discriminating whether given samples are from the in-domain or not, without the categorical labels of in-domain instances. Unlike supervised OOD, as …...

AbstractParaphrase detection is useful in many natural language understanding applications. Current works typically formulate this problem as a sentence pair binary classification task. However, this setup is not a good …...