Latent Intention Dialogue Models

By Tsung-Hsien Wen, Yishu Miao, Phil Blunsom, Susannah Young. 2017

148 citations recorded by the source corpus.

Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructing deterministic models for learning dialogue sentences that fail to capture natural conversational variability. In this paper, we propose a Latent Intention Dialogue Model (LIDM) that employs a discrete latent variable to learn underlying dialogue intentions in the framework of neural variational inference. In a goal-oriented dialogue scenario, these latent intentions can be interpreted as actions guiding the generation of machine responses, which can be further refined autonomously by reinforcement learning. The experimental evaluation of LIDM shows that the model out-performs published benchmarks for both corpus-based and human evaluation, demonstrating the effectiveness of discrete latent variable models for learning goal-oriented dialogues.

Subfields: Artificial Intelligence, Natural Language Processing, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Generative Models

Citations in the corpus

A Simple Language Model for Task-Oriented Dialogue (2020, background): “These components include understanding user intent via intent detection [26], tracking the constraints imposed by the user via dialogue state tracking [20, 32, 41, 34, 53, 59, 64, 8, 19], determining system actions via dialogue policy [51], and using dedicated response generation components [49].”
Incremental Learning from Scratch for Task-Oriented Dialogue Systems (2019, methodology): “In the existing work, this approach was used to generate diverse machine responses in both open domain dialogue systems (Zhao et al., 2017; Serban et al., 2016) and task-oriented dialogue systems (Wen et al., 2017).”
End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient (2017, background): “Usually these algorithms adopt an encoder-decoder architecture, some having an additional belief tracker [26] or latent intent variable [25].”
Mixture Models for Diverse Machine Translation: Tricks of the Trade (2019, background): “Besides machine translation, there is work on latent variables for dialogue generation (Serban et al., 2017; Cao & Clark, 2017; Wen et al., 2017) and image captioning (Wang et al., 2017; Dai et al., 2017).”
Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning (2019, unknown): “Deep learning has been applied to task-oriented dialog in many recent studies [4, 22, 25, 13, 11, 23, 1].”
Decoupling Strategy and Generation in Negotiation Dialogues (2018, background): “Another line of work tackles this problem by introducing latent stochastic variables to model the dialogue state (Wen et al., 2017b; Zhao et al., 2017; Cao and Clark, 2017).”
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention (2019, background): “(iii) dialog act prediction (Wen et al., 2017), which is applied to classify the system action.”
Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models (2019, methodology): “Experimental results on CamRest676 and MultiWOZ suggest that ARDM outperforms or on-par with the current state-of-the-art methods that use manual annotation information, such as belief states and dialog acts.”
An Overview of Natural Language State Representation for Reinforcement Learning (2020, methodology): “Wen et al. (2017a) modeled the dialogue state vector as a concatenation of user input (encoded by a BiLSTM), a belief vector (probability distributions over domain speciﬁc slot-value pairs, extracted by RNN-CNN belief trackers) and the degree of matching in a knowledge base.”
Hierarchical Text Generation and Planning for Strategic Dialogue (2017, methodology): “We use simple pattern matching for several such errors, and found that the F ULL M ODEL performed slightly better (15 errors vs. 19).”
MOSS: End-to-End Dialog System Framework with Modular Supervision (2019, methodology): “Though both NDM and LIDM (Wen et al. 2017b; 2017a) have policy network components, they are single layer MLPs functioning as the glue that binds the system modules together.”
Modeling Multi-Action Policy for Task-Oriented Dialogues (2019, methodology): “Recent work (Wen et al., 2017; Liu and Lane, 2018) also used SL as pre-training for RL to mitigate the sample inefficiency of RL approaches and to reduce the number of interactions.”
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing (2019, unknown): “…been applied in many NLP tasks, including language modeling (Bowman et al., 2015; Miao et al., 2016), dialog response generation (Zhao et al., 2017; Wen et al., 2017), semi-supervised text classiﬁ-cation (Xu et al., 2017), controllable text generation (Hu et al., 2017), and text compression (Miao…”
Mixture Content Selection for Diverse Sequence Generation (2019, background): “…such as language modeling (Bowman et al., 2016), machine translation (Zhang et al., 2016; Su et al., 2018; Deng et al., 2018; Shankar and Sarawagi, 2019), and conversation modeling (Serban et al., 2017; Wen et al., 2017; Zhao et al., 2017; Park et al., 2018; Wen and Luong, 2018; Gu et al., 2019).”
Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures (2018, methodology): “…the Sequicity framework, called Two Stage CopyNet ( TSCP ), which has fewer number of parameters and trains faster than state-of-the-art baselines (Wen et al., 2017b, 2016a, 2017a); (3) We demonstrate that TSCP signiﬁcantly outperforms state-of-the-art baselines on two large-scale datasets,…”
Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models (2019, background): “Prior work has shown that learning with latent variables leads to benefits like diverse response decoding (Serban et al., 2017b; Zhao et al., 2017; Cao and Clark, 2017), interpretable decision-making (Wen et al., 2017; Zhao et al., 2018) and zero-shot domain transfer (Zhao and Eskenazi, 2018).”
Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems (2018, background): “, 2017; Mnih and Gregor, 2014), dialogue system (Wen et al., 2017; Serban et al., 2017).”
Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue (2019, methodology): “Both experiments were carried out on the CamRest676 dataset.”