Current neural network-based conversational models lack diversity and generate boring
responses to open-ended utterances. Priors such as persona, emotion, or topic provide …

Responding to online customer reviews has become an essential part of successfully
managing and growing a business both in e-commerce and the hospitality and tourism …

Response generation models trained with cross entropy loss suffer from over-general
responses due to their preference for high-frequent tokens. Focal loss and anti-focal loss are …

Significant progress has been made on the Neural Response Generation (NRG) task.
However, there still exist great challenges on results' diversity. Compared to the End-to-End …

The dialogue data usually consist of the pairs of a query and its response, but no previous
response generators have exploited the responses explicitly in their training while a …

The sequence-to-sequence model is a widely used model for dialogue response
generators, but it tends to generate safe responses for most input queries. Since safe …

This is the application document for the 2019 Amazon Alexa competition. We give an overall
vision of our conversational experience, as well as a sample conversation that we would like …

We create a new, large, high-quality dataset for neural dialog modeling, and explore its
benefits over existing datasets. A dialog agent (chatbot) is a software that communicates …

대화 시스템은 사용자의 입력 발화에 대해 적절하고 의미 있는 응답을 생성하는 시스템으로
seq2seq 구조를 갖는 대화 모델이 주로 연구되고 있다. 그러나 seq2seq 기반 대화 모델은 입력 …

요 약모델은 대화 생성 모델의 지대한 발전을 이끌어 왔지만 고전 대화 생성 모델 Sequence-to-
Sequence, 부터 지금에 이르기까지 일반적인 답변을 생성하여 사용자로 하여금 흥미를 …