Learn More
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which(More)
Discriminatively trained undirected graphical models have had wide empirical success, and there has been increasing interest in toolkits that ease their application to complex relational data. The power in relational models is in their repeated structure and tied parameters; at issue is how to define these structures in a powerful and flexible way. Rather(More)
Cross-document coreference, the task of grouping all the mentions of each entity in a document collection, arises in information extraction and automated knowledge base construction. For large collections, it is clearly impractical to consider all possible groupings of mentions into distinct entities. To solve the problem we propose two ideas: (a) a(More)
Cross-document coreference resolution is the task of grouping the entity mentions in a collection of documents into sets that each represent a distinct entity. It is central to knowledge base construction and also useful for joint inference with other NLP components. Obtaining large, organic labeled datasets for training and testing cross-document(More)
Spontaneous, conversational speech in probable dementia of Alzheimer type (DAT) participants and healthy older controls was analysed using eight linguistic measures. These were evaluated for their usefulness in discriminating between healthy and demented individuals. The measures were; noun rate, pronoun rate, verb rate, adjective rate, Clause-like Semantic(More)
Recent research on entity linking (EL) has introduced a plethora of promising techniques, ranging from deep neural networks to joint inference. But despite numerous papers there is surprisingly little understanding of the state of the art in EL. We attack this confusion by analyzing differences between several versions of the EL problem and presenting a(More)
Methods that measure compatibility between mention pairs are currently the dominant approach to coreference. However, they suffer from a number of drawbacks including difficulties scaling to large numbers of mentions and limited representational power. As the severity of these drawbacks continue to progress with the growing demand for more data, the need to(More)
Matrix factorization approaches to relation extraction provide several attractive features: they support distant supervision, handle open schemas, and leverage unlabeled data. Unfortunately, these methods share a shortcoming with all other distantly supervised approaches: they cannot learn to extract target relations without existing data in the knowledge(More)
and Care of the Elderly. 2 Abstract This paper describes a technique for quantifying the degree of speech deficits in probable dementia of Alzheimer's type (DAT). The technique involves interviewing individuals with DAT and transcribing their speech. From these transcripts five measurements which reflect the physical characteristics of this speech can be(More)
Discriminatively trained undirected graphical models have garnered tremendous interest and empirical success in natural language processing, computer vision, bioinformatics and many other areas [16, 1, 11]. Some of these models use simple structure (e.g. linear-chains, grids, fully-connected affinity graphs), but there has been increasing interest in more(More)