Affect conveys important implicit information in human communication. Having
the capability to correctly express affect during human-machine conversations
is one of the major milestones in artificial intelligence. In recent years,
extensive research on open-domain neural conversational models has been
conducted. However, embedding affect into such models is still under explored.
In this paper, we propose an end-to-end affect-rich open-domain neural
conversational model that produces responses not only appropriate in syntax and
semantics, but also with rich affect. Our model extends the Seq2Seq model and
adopts VAD (Valence, Arousal and Dominance) affective notations to embed each
word with affects. In addition, our model considers the effect of negators and
intensifiers via a novel affective attention mechanism, which biases attention
towards affect-rich words in input sentences. Lastly, we train our model with
an affect-incorporated objective function to encourage the generation of
affect-rich words in the output responses. Evaluations based on both perplexity
and human evaluations show that our model outperforms the state-of-the-art
baseline model of comparable size in producing natural and affect-rich
responses.

本文提出了一种端到端情感丰富的神经对话模型，采用 VAD 注意机制将情感嵌入到每个单词中，并通过采用情感注意机制考虑了否定语和强化语的影响。最后，采用具有情感的目标函数训练模型，以产生具有情感丰富性的输出响应，得到人类的联合评估与基于困惑度的评估都优于同等规模的基线模型。

一种带有偏置注意力和加权交叉熵损失的情感丰富的神经对话模型

An Affect-Rich Neural Conversational Model with Biased Attention and  Weighted Cross-Entropy Loss

In this paper, we present a hybrid model that combines a neural
conversational model and a rule-based graph dialogue system that assists users
in scheduling reminders through a chat conversation. The graph based system has
high precision and provides a grammatically accurate response but has a low
recall. The neural conversation model can cater to a variety of requests, as it
generates the responses word by word as opposed to using canned responses. The
hybrid system shows significant improvements over the existing baseline system
of rule based approach and caters to complex queries with a domain-restricted
neural model. Restricting the conversation topic and combination of graph based
retrieval system with a neural generative model makes the final system robust
enough for a real world application.

该研究提出了一个混合模型，结合了神经会话模型和基于规则的图形对话系统，通过聊天对话协助用户安排提醒，该系统相较于基于规则的基准系统表现出显著的改进，并结合了神经生成模型，使其足够稳健以应对实际应用场景。

生产就绪的聊天机器人：生成或提取

Production Ready Chatbots: Generate if not Retrieve

Recent neural models of dialogue generation offer great promise for
generating responses for conversational agents, but tend to be shortsighted,
predicting utterances one at a time while ignoring their influence on future
outcomes. Modeling the future direction of a dialogue is crucial to generating
coherent, interesting dialogues, a need which led traditional NLP models of
dialogue to draw on reinforcement learning. In this paper, we show how to
integrate these goals, applying deep reinforcement learning to model future
reward in chatbot dialogue. The model simulates dialogues between two virtual
agents, using policy gradient methods to reward sequences that display three
useful conversational properties: informativity (non-repetitive turns),
coherence, and ease of answering (related to forward-looking function). We
evaluate our model on diversity, length as well as with human judges, showing
that the proposed algorithm generates more interactive responses and manages to
foster a more sustained conversation in dialogue simulation. This work marks a
first step towards learning a neural conversational model based on the
long-term success of dialogues.

本研究基于强化学习，建立一个可生成更多交互式回复、更长且不重复的对话、更容易回答问题的聊天机器人的神经对话模型。