[2018 ACL Long] 对话系统

[NLG - E2E - knowledge guide generation]

1. Knowledge Diffusion for Neural Dialogue Generation ( ‎Cited by 3 )

Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, Dawei Yin

End-to-end neural dialogue generation has shown promising results recently, but it does not employ knowledge to guide the generation and hence tends to generate short, general, and meaningless responses. In this paper, we propose a neural knowledge diffusion (NKD) model to introduce knowledge into dialogue generation. This method can not only match the relevant facts for the input utterance but diffuse them to similar entities. With the help of facts matching and entity diffusion, the neural dialogue generation is augmented with the ability of convergent and divergent thinking over the knowledge base. Our empirical study on a real-world dataset prove that our model is capable of generating meaningful, diverse and natural responses for both factoid-questions (事实性问题) and knowledge grounded chi-chats. The experiment results also show that our model outperforms competitive baseline models significantly.

[Task - Framework - Seq2Seq - ]

2. Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures ( ‎Cited by 9)

Wenqiang Lei, Xisen Jin, Min-Yen Kan, Zhaochun Ren, Xiangnan He, Dawei Yin

Existing solutions to task-oriented dialogue systems follow pipeline designs which introduces architectural complexity and fragility. We propose a novel, holistic (整体的), extendable framework based on a single sequence-to-sequence (seq2seq) model which can be optimized with supervised or reinforcement learning. A key contribution is that we design text spans named belief spans to track dialogue believes, allowing task-oriented dialogue systems to be modeled in a seq2seq way. Based on this, we propose a simplistic Two Stage CopyNet instantiation which emonstrates good scalability: significantly reducing model complexity in terms of number of parameters and training time by a magnitude. It significantly outperforms state-of-the-art pipeline-based methods on large datasets and retains a satisfactory entity match rate on out-of-vocabulary (OOV) cases where pipeline-designed competitors totally fail.

[Task - Framework - RL]

3. Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning ( ‎Cited by 3) 

Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the language complexity of human interlocutors(参加谈话的人) and the biases in its design may tend to degrade the agent. To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning. We incorporate into the dialogue agent a model of the environment, referred to as the world model, to mimic real user response and generate simulated experience. During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience. The effectiveness of our approach is demonstrated on a movie-ticket booking task in both simulated and human-in-the-loop settings.

[Task - E2E - Framework - multimodel info - RL]

4. Sentiment Adaptive End-to-End Dialog Systems ( ‎Cited by 2 )

Weiyan Shi, Zhou Yu

End-to-end learning framework is useful for building dialog systems for its simplicity in training and efficiency in model updating. However, current end-to-end approaches only consider user semantic inputs in learning and under-utilize other user information. Therefore, we propose to include user sentiment obtained through multimodal information (acoustic, dialogic and textual), in the end-to-end learning framework to make systems more user-adaptive and effective. We incorporated user sentiment information in both supervised and reinforcement learning settings. In both settings, adding sentiment information reduced the dialog length and improved the task success rate on a bus information search task. This work is the first attempt to incorporate multimodal user information in the adaptive end-to-end dialog system training framework and attained state-of-the-art performance.

[CC - add profile info] 

5. Personalizing Dialogue Agents: I have a dog, do you have pets too? (Cited by 31)

Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, Jason Weston

Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating (迷人的). In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i)condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown our model is trained to engage(紧密结合) its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.

[NLG - encoder-decoder model - unsup discrete sent representation learning]

6. Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation ( Cited by 8)

Tiancheng Zhao, Kyusong Lee, Maxine Eskenazi

The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. Yet it is limited because it cannot output interpretable actions as in traditional systems, which hinders(阻碍) humans from understanding its generation process. We present an unsupervised discrete sentence representation learning method that can integrate with any existing encoder-decoder dialog models for interpretable response generation. Building upon variational autoencoders (VAEs), we present two novel models, DI-VAE and DI-VST that improve VAEs and can discover interpretable semantics via either auto encoding or context predicting. Our methods have been validated on real-world dialog datasets to discover semantic representations and enhance encoder-decoder models with interpretable generation.

[Task - E2E - Framework]

7. Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems ( Cited by 8)

Andrea Madotto, Chien-Sheng Wu, Pascale Fung

End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases. In this paper, we propose a novel yet simple end-to-end differentiable model called memory-to-sequence (Mem2Seq) to address this issue. Mem2Seq is the first neural generative model that combines the multi-hop attention over memories with the idea of pointer network. We empirically show how Mem2Seq controls each generation step, and how its multi-hop attention mechanism helps in learning correlations between memories. In addition, our model is quite general without complicated task-specific designs. As a result, we show that Mem2Seq can be trained faster and attain the state-of-the-art performance on three different task-oriented dialog datasets.

[Query Generation]

8. DialSQL: Dialogue Based Structured Query Generation ( Cited by 4)

Izzeddin Gur, Semih Yavuz, Yu Su, Xifeng Yan

The recent advance in deep learning and semantic parsing has significantly improved the translation accuracy of natural language questions to structured queries. However, further improvement of the existing approaches turns out to be quite challenging. Rather than solely relying on algorithmic innovations, in this work, we introduce DialSQL, a dialogue-based structured query generation framework that leverages human intelligence to boost the performance of existing algorithms via user interaction. DialSQL is capable of identifying potential errors in a generated SQL query and asking users for validation via simple multi-choice questions. User feedback is then leveraged to revise the query. We design a generic simulator to bootstrap synthetic training dialogues and evaluate the performance of DialSQL on the WikiSQL dataset. Using SQLNet as a black box query generation tool, DialSQL improves its performance from 61.3% to 69.0% using only 2.4 validation questions per dialogue.

[Dialogue state tracking] 

9. Global-Locally Self-Attentive Encoder for Dialogue State Tracking (Cited by 0)

Victor Zhong, Caiming Xiong, Richard Socher

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to shares parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states. GLAD obtains 88.3% joint goal accuracy and 96.4% request accuracy on the WoZ state tracking task, outperforming prior work by 3.9% and 4.8%. On the DSTC2 task, our model obtains 74.7% joint goal accuracy and 97.3% request accuracy, outperforming prior work by 1.3% and 0.8%

[E2E - Framework - PtrNet]

10.  An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking. ( Cited by 2 )

Puyang Xu, Qi Hu.

We highlight a practical yet rarely discussed problem in dialogue state tracking (DST), namely handling unknown slot values. Previous approaches generally assume predefined candidate lists and thus are not designed to output unknown values, especially when the spoken language understanding (SLU) module is absent as in many end-to-end (E2E) systems. We describe in this paper an E2E architecture based on the pointer network (PtrNet) that can effectively extract unknown slot values while still obtains state-of-the-art accuracy on the standard DSTC2 benchmark. We also provide extensive empirical evidence to show that tracking unknown values can be challenging and our approach can bring significant improvement with the help of an effective feature dropout technique.