• Corpus ID: 231855322

Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog

  title={Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog},
  author={David Thulke and Nico Daheim and Christian Dugast and Hermann Ney},
This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), “Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access”. The goal of the task is to generate responses to user turns in a task-oriented dialog that require knowledge from unstructured documents. The task is divided into three subtasks: detection, selection and generation. In order to be compute efficient, we formulate the selection problem in terms… 

Tables from this paper

Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

This paper summarizes the entries to both subtasks of the first DialDoc shared task which focuses on the agent response prediction task in goal-oriented document-grounded dialogs and uses a cascaded model which grounds the response prediction on the predicted span instead of the full document.

Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling

This paper proposes an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv, and con-ducted comprehensive experiments on conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation to demonstrate the effectiveness of the proposed method.

End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management

This article proposes a TOD system with semi-structured knowledge management, SeKnow, which extends the belief state to manage knowledge with both structured and unstructured contents, and introduces two implementations of SeKnow based on a non-pretrained sequence-to-sequence model and a pretrained language model.

Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Model

This paper summarizes the submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) “Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations” and explores different approaches to make the models more robust to this type of input and to adapt the generated responses to the style of spoken conversations.

OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience

A unified model OPERA (Open-book End-to-end Task-oriented Dialog) which can appropriately access explicit and implicit external knowledge to tackle the defined task is proposed.

AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog

We introduce AARGH, an end-to-end task-oriented dialog system combining retrieval and generative approaches in a single model, aiming at improving dialog management and lexical diversity of outputs.

Joint Retrieval and Generation Training for Grounded Text Generation

This work proposes a framework that alleviates data constraint by jointly training a grounded generator and document retriever on the language model signal, and demonstrates that both generator and retriever can take advantage of this joint training and work synergistically to produce more informative and relevant text in both prose and dialogue generation.

External Knowledge Document Retrieval Strategy Based on Intention-guided and Meta-learning for Task-oriented Dialogues

This paper has introduced the entity-aware dialogue intention information and proposed a two-stage training method for the intention-guided knowledge document retrieval model, which can effectively enhance the retrieval accuracy of the Bi-encoder retrieval model in the task-based dialogue system.

Learning Dense Entity-Aware Dialogue Intentions with Rewritten Utterance for External Knowledge Documents Retrieval

This paper proposes an intention-guided two-stage training approach, which leverages rewritten utterances that explicitly convey entity-aware user intentions and can improve the performance of existing Bi-Encoder retrievers such as DPR (Deep Passage Retriever).

Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model

This work presents a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes’ theorem, and shows that the model is more factual in terms of automatic factuality metrics than the base-line model.



Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access

An augmented version of MultiWOZ 2.1 is introduced, which includes new out-of-API-coverage turns and responses grounded on external knowledge sources, and defines three sub-tasks: knowledge-seeking turn detection, knowledge selection, and knowledge-grounded response generation, which can be modeled individually or jointly.

REALM: Retrieval-Augmented Language Model Pre-Training

The effectiveness of Retrieval-Augmented Language Model pre-training (REALM) is demonstrated by fine-tuning on the challenging task of Open-domain Question Answering (Open-QA) and is found to outperform all previous methods by a significant margin, while also providing qualitative benefits such as interpretability and modularity.

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

A general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -- models which combine pre-trained parametric and non-parametric memory for language generation, and finds that RAG models generate more specific, diverse and factual language than a state-of-the-art parametric-only seq2seq baseline.

Wizard of Wikipedia: Knowledge-Powered Conversational agents

The best performing dialogue models are able to conduct knowledgeable discussions on open-domain topics as evaluated by automatic metrics and human evaluations, while a new benchmark allows for measuring further improvements in this important research direction.

Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue

The proposed sequential latent variable model can keep track of the prior and posterior distribution over knowledge and can not only reduce the ambiguity caused from the diversity in knowledge selection of conversation but also better leverage the response information for proper choice of knowledge.

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

This systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks and achieves state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more.

Towards Exploiting Background Knowledge for Building Conversation Systems

This work creates a new dataset containing movie chats wherein each response is explicitly generated by copying and/or modifying sentences from unstructured background knowledge such as plots, comments and reviews about the movie.

MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling

The Multi-Domain Wizard-of-Oz dataset (MultiWOZ), a fully-labeled collection of human-human written conversations spanning over multiple domains and topics is introduced, at a size of 10k dialogues, at least one order of magnitude larger than all previous annotated task-oriented corpora.

Dense Passage Retrieval for Open-Domain Question Answering

This work shows that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework.

Language Models are Unsupervised Multitask Learners

It is demonstrated that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText, suggesting a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations.