Image captioning task has become a highly competitive research area with application of convolutional and recurrent neural networks, especially with the advent of long short-term memory (LSTM) architecture. However, its primary focus has been a factual description of the images, mostly objects and their actions. While such focus has demonstrated competence, describing the images with non-factua...

In this research, we deployed an automated fact-checking system (ClaimBuster) on the 2016 presidential primary debates and assessed its performance compared to professional news organizations. In real-time, ClaimBuster scored the statements made by candidates on check-worthiness, the likelihood that the statement contained an important factual claim. Its discrimination compared to professional ...

When reasoning about the facts of a case, we typically use stories to link the known events into coherent wholes. One way to establish coherence is to appeal to past examples, real or fictitious. These examples can be chosen and critiqued using the case-based reasoning (CBR) techniques from the AI and Law literature. In this paper, we apply these techniques to factual stories, assessing a story...

Aims and objectives: To examine the relationship between observed delirium in ICU and patients' recall of factual events up to two years after discharge. Background: People, the environment, and procedures are frequently cited memories of actual events encountered in ICU. These are often perceived as stressors to the patients and the presence of several such stressors has been associated with t...

In this paper, we present our team TUT/NII results at DUC 2005 and additional experiments on improving multi-document summarization. Summarization systems have typically focused on the factual aspect of information needs. Subjectivity analysis is another essential aspect for better understanding of information needs. Our approach is based on sentence extraction, weighted by sentence type annota...

Social media communities (e.g. Wikipedia, Flickr, Live Q&A) give rise to distinct types of content, foremost among which are relational content (discussion, chat) and factual content (answering questions, problem-solving). Both users and researchers are increasingly interested in developing strategies that can rapidly distinguish these types of content. While many text-based and structural stra...

aces in the audience on the 25th of January! "How to win a house job" is not a subject to which there is a short answer, but rather one in which the importance lies ln the summation of a lot of minor points plus a few more major and more definite ?nes, so I shall give a general factual background and then some more detailed advice. The factual background I decided to obtain from a questionnaire...