The scope of PKAW is not limited to traditional knowledge acquisition approaches such as human (expert) centric
ones, but also covers diverse areas closely related to knowledge acquisition such as
knowledge engineering, knowledge management, machine learning, data mining, etc.
We need to choose appropriate techniques for knowledge acquisition, depending on its
type and the task addressed. In fact, the scope changes over time so that it can cover
novel, newly emerged techniques and application areas in which knowledge acquisition
plays an important role. Especially, now, we live in the era of the third wave of AI, in
which the availability of high-performance computing and massive electronic data
generated from various sensors and texts on the Web make it possible to devise novel
data-driven methodologies such as Deep Learning and its variants. These advanced
technologies could help us acquire tacit knowledge that has been difficult to learn by
human-centric approaches, while they also remind us of the importance of the
understandability of knowledge, leading to a new field of Explainable AI.
Within this context, we invited submissions in the above broad fields and finally
selected 9 regular papers and 7 short papers from 38 submitted papers. All papers were
peer-reviewed by three reviewers. These papers demonstrate advanced research work
from the practical viewpoint and make contributions in technical and theoretical aspects
to the fields of intelligent systems/agents, natural language processing, and applications
of machine learning techniques including Deep Learning to real world problems.