Multi-turn conversation understanding is a major challenge for building intelligent dialogue
systems. This work focuses on retrieval-based response matching for multi-turn conversation …

This paper describes the SemEval 2018 Shared Task on Hypernym Discovery. We put
forward this task as a complementary benchmark for modeling hypernymy, a problem which …

In this paper, we explore the possibility to apply natural language processing in visual model-
to-model (M2M) transformations. Therefore, we present our research results on information …

Answering questions from university admission exams (Gaokao in Chinese) is a challenging
AI task since it requires effective representation to capture complicated semantic relations …

Chinese pinyin input method engine (IME) lets user conveniently input Chinese into a
computer by typing pinyin through the common keyboard. In addition to offering high …

Representation learning is the foundation of machine reading comprehension. In state-of-
the-art models, deep learning methods broadly use word and character level …

The hypernymy relation is the one occurring between an instance term and its general term
(eg,“lion” and “animal”,“Italy” and “country”). This paper we addresses Hypernym Discovery …

Hypernymy plays a fundamental role in many AI tasks like taxonomy learning, ontology
learning, etc. This has motivated the development of many automatic identification methods …

Featured Application The main application of the developed solution lies in the area of
systems design, where model-to-model transformations are being utilized to their full extent …

Training a machine learning model such as a neural network, which can automatically
extract a hypernym from unstructured data, is disclosed. A preliminary candidate list of …