Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches.
Most of these approaches account for the context for effective understanding.
DIALOGUE UNDERSTANDING GOAL-ORIENTED DIALOGUE SYSTEMS TEXT GENERATION
DREAM is likely to present significant challenges for existing reading comprehension systems: 84% of answers are non-extractive, 85% of questions require reasoning beyond a single sentence, and 34% of questions also involve commonsense knowledge.
Research into the area of multiparty dialog has grown considerably over recent years.
DIALOGUE UNDERSTANDING DISCOURSE PARSING MACHINE READING COMPREHENSION
This paper presents a deep sequential model for parsing discourse dependency structures of multi-party dialogues.
DIALOGUE UNDERSTANDING DISCOURSE PARSING LINK PREDICTION QUESTION ANSWERING RELATION CLASSIFICATION SENTIMENT ANALYSIS
Finally, we evaluate and analyze baseline neural models on a simple subtask that requires recognition of the created common ground.
DIALOGUE UNDERSTANDING GOAL-ORIENTED DIALOG LANGUAGE ACQUISITION
We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations.
ABSTRACTIVE TEXT SUMMARIZATION DIALOGUE UNDERSTANDING MEETING SUMMARIZATION SENTENCE COMPRESSION WORD EMBEDDINGS
Multi-role dialogue understanding comprises a wide range of diverse tasks such as question answering, act classification, dialogue summarization etc.
DIALOGUE UNDERSTANDING QUESTION ANSWERING REPRESENTATION LEARNING