Challenge: Existing task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation.
Approach: They propose a dual dynamic memory network for multi-turn dialog generation . the model dynamically expands the dialog memory turn by turn and keeps track of dialog history .
Outcome: The proposed model outperforms baseline models on three benchmark datasets on human evaluation and automatic evaluation.

Similar Papers

Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems (P18-1)

Copied to clipboard

Challenge: End-to-end task-oriented dialog systems often suffer from the challenge of incorporating knowledge bases.
Approach: They propose a novel yet simple end-to-end differentiable model called memory-tosequence to address this issue.
Outcome: The proposed model can be trained faster and achieve state-of-the-art performance on three different task-oriented dialog datasets.
Multi-Level Memory for Task Oriented Dialogs (N19-1)

Copied to clipboard

Challenge: Recent task oriented dialog systems use memory architectures to incorporate external knowledge in their dialogs.
Approach: They propose a novel multi-level memory architecture that separates dialog context and knowledge base results . they use cells for each query and their corresponding results to address queries .
Outcome: The proposed architecture outperforms current state-of-the-art models on three publicly available data sets.
A Working Memory Model for Task-oriented Dialog Response Generation (P19-1)

Copied to clipboard

Challenge: Existing models to integrate external Knowledge Base information, one form of world knowledge, confound dialog history with KB tuples and store them into one memory.
Approach: They propose a working memory model that interacts with two long-term memories to generate dialog responses.
Outcome: The proposed model outperforms the state-of-the-art models on two task-oriented dialog datasets.
Task-Oriented Conversation Generation Using Heterogeneous Memory Networks (D19-1)

Copied to clipboard

Challenge: Existing memory networks do not perform well when leveraging heterogeneous information from different sources.
Approach: They propose to use user utterances, dialogue history and background knowledge tuples to integrate external knowledge into a neural dialogue model.
Outcome: The proposed model outperforms the state-of-the-art data-driven task-oriented dialogue models on real-world datasets.
Dialog Generation Using Multi-Turn Reasoning Neural Networks (N18-1)

Copied to clipboard

Challenge: Existing methods for dialog generation are limited and short at generalization.
Approach: They propose a generalizable dialog generation approach that adapts multi-turn reasoning to generate responses by taking current conversation session context as a document and current query as 'question' they separate the single memory used for document comprehension into different groups for speaker-specific topic and opinion embedding.
Outcome: Experiments on Japanese 10-sentence (5-round) conversation modeling show that multi-turn reasoning can produce more diverse and acceptable responses than state-of-the-art single-turn and non-reasoning baselines.
Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog (2020.acl-main)

Copied to clipboard

Challenge: Recent studies show remarkable success in end-to-end task-oriented dialog systems . however, most models rely on large training data, which is difficult to scalable for new domains with limited labeled data.
Approach: They propose a shared-private network which exploits the relevance between the target domain and each domain.
Outcome: The proposed model outperforms existing methods on multi-domain dialogue by 13.9% on average.
GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems (2020.emnlp-main)

Copied to clipboard

Challenge: End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs.
Approach: They propose a recurrent cell architecture which exploits the structural information in dialogue history . they propose recursive cell architecture to allow representation learning on graphs .
Outcome: The proposed model improves on two different datasets on task-oriented dialogues.
End-to-End Learning of Task-Oriented Dialogs (N18-4)

Copied to clipboard

Challenge: Dissertation addresses the limitations of conventional task-oriented dialog systems . conventions of such systems include a complex pipeline and dialog state tracking .
Approach: They propose a neural network based dialog system that can robustly track dialog state . they propose offline training and online interactive learning methods to improve efficiency .
Outcome: The proposed system can track dialog state, interface with knowledge bases, and integrate structured query results into system responses to successfully complete task-oriented dialog.
Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory (2021.findings-acl)

Copied to clipboard

Challenge: Recent years have seen a rapid growth of interest in building task-oriented dialogue systems.
Approach: They propose a retrieve-and-memorize framework to deal with unbalanced distribution of system actions in dialogue datasets.
Outcome: The proposed framework achieves competitive performance among state-of-the-art models on a large-scale task-oriented dialogue dataset.
Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue (2021.emnlp-main)

Copied to clipboard

Challenge: Recent years has witnessed the remarkable success in end-to-end task-oriented dialog system, especially when incorporating external knowledge information.
Approach: They propose a mechanism to model deterministic entity knowledge by using an intention reasoning network to obtain intention-aware representations of conceptual tokens.
Outcome: The proposed mechanism captures concept shifts and generates accurate responses on two representative multi-domain dialog datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations