Welcome!


The AAAI-16 Workshop on Knowledge Extraction from Text (KET@AAAI 2016) is a continuation of the Knowledge Extraction from Text workshop from NIPS 2013 and WWW 2015.

Text understanding is an old, yet-unsolved, AI problem consisting of a number of nontrivial steps. The critical step in solving the understanding problem is knowledge acquisition from text, i.e. a transition from a non-formalized text, explicitly or implicitly, into a formalized actionable language (i.e. capable of supporting automated reasoning).  Other steps in the text understanding pipeline include linguistic processing, reasoning, text generation, search, question answering etc. These are more or less solved to a degree that would support composition of a text understanding service. However, we know that knowledge acquisition, the key bottleneck, can be done by humans, even though automation of the process is still out of reach in its full breadth.
After failed attempts in the past (due to a lack of both theoretical and technological prerequisites), in recent years the interest in text understanding and knowledge acquisition form text has been growing. There are numerous AI research groups studying various aspects of the problem in the areas of computational linguistics, machine learning, probabilistic & logical reasoning, and semantic web. The commonality among all the newer approaches is the use recent advances in machine learning to deal with representational change on the level of words, sentences, concepts, etc. 


Topics of interest

KET@AAAI-2016 invites submissions on all aspects of text understanding, including approaches related to areas of computational linguistics, 
machine learning, probabilistic & logical reasoning, and the semantic web.
Topic of interest include, but are not limited to:


• cross-lingual, multi-lingual and monolingual alignment between knowledge bases and text;
• joint inference between text interpretation and inference over the content of a knowledge base;
• textual natural language processing and natural language understanding;
• machine reading, reading the web, learning by reading;
• macro reading, micro reading and KR-directed information retrieval;
• supervised, unsupervised, semi-supervised and distantly-supervised learning;
• crowd-sourcing, human computation and conversational learning;
• knowledge base construction and population from text;
• text-based question-answering.