Every time I fire a conversational designer, the performance of the
dialog system goes down
- URL: http://arxiv.org/abs/2109.13029v1
- Date: Mon, 27 Sep 2021 13:05:31 GMT
- Title: Every time I fire a conversational designer, the performance of the
dialog system goes down
- Authors: Giancarlo A. Xompero, Michele Mastromattei, Samir Salman, Cristina
Giannone, Andrea Favalli, Raniero Romagnoli, Fabio Massimo Zanzotto
- Abstract summary: We investigate how the use of explicit domain knowledge of conversational designers affects the performance of neural-based dialogue systems.
We propose the Conversational-Logic-Injection-in-Neural-Network system (CLINN) where explicit knowledge is coded in semi-logical rules.
- Score: 0.07696728525672149
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Incorporating explicit domain knowledge into neural-based task-oriented
dialogue systems is an effective way to reduce the need of large sets of
annotated dialogues. In this paper, we investigate how the use of explicit
domain knowledge of conversational designers affects the performance of
neural-based dialogue systems. To support this investigation, we propose the
Conversational-Logic-Injection-in-Neural-Network system (CLINN) where explicit
knowledge is coded in semi-logical rules. By using CLINN, we evaluated
semi-logical rules produced by a team of differently skilled conversational
designers. We experimented with the Restaurant topic of the MultiWOZ dataset.
Results show that external knowledge is extremely important for reducing the
need of annotated examples for conversational systems. In fact, rules from
conversational designers used in CLINN significantly outperform a
state-of-the-art neural-based dialogue system.
Related papers
- PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue
Model [79.64376762489164]
PK-Chat is a Pointer network guided generative dialogue model, incorporating a unified pretrained language model and a pointer network over knowledge graphs.
The words generated by PK-Chat in the dialogue are derived from the prediction of word lists and the direct prediction of the external knowledge graph knowledge.
Based on the PK-Chat, a dialogue system is built for academic scenarios in the case of geosciences.
arXiv Detail & Related papers (2023-04-02T18:23:13Z) - Variational Reasoning over Incomplete Knowledge Graphs for
Conversational Recommendation [48.70062671767362]
We propose the Variational Reasoning over Incomplete KGs Conversational Recommender (VRICR)
Our key idea is to incorporate the large dialogue corpus naturally accompanied with CRSs to enhance the incomplete KGs.
We also denote the dialogue-specific subgraphs of KGs as latent variables with categorical priors for adaptive knowledge graphs.
arXiv Detail & Related papers (2022-12-22T17:02:21Z) - KETOD: Knowledge-Enriched Task-Oriented Dialogue [77.59814785157877]
Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains.
We investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model.
arXiv Detail & Related papers (2022-05-11T16:01:03Z) - Back to the Future: Bidirectional Information Decoupling Network for
Multi-turn Dialogue Modeling [80.51094098799736]
We propose Bidirectional Information Decoupling Network (BiDeN) as a universal dialogue encoder.
BiDeN explicitly incorporates both the past and future contexts and can be generalized to a wide range of dialogue-related tasks.
Experimental results on datasets of different downstream tasks demonstrate the universality and effectiveness of our BiDeN.
arXiv Detail & Related papers (2022-04-18T03:51:46Z) - A Review of Dialogue Systems: From Trained Monkeys to Stochastic Parrots [0.0]
We aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans.
We present a broad overview of methods developed to build dialogue systems over the years.
arXiv Detail & Related papers (2021-11-02T08:07:55Z) - SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and
Machine Teaching [75.87418236410296]
SYNERGY is a hybrid learning framework where a task bot is developed in two steps.
A pre-trained neural dialog model, SOLOIST, is fine-tuned on the simulated dialogs to build a bot for the task.
The fine-tuned neural dialog model is continually refined with a handful of real task-specific dialogs via machine teaching.
arXiv Detail & Related papers (2021-10-21T23:13:04Z) - Graph Based Network with Contextualized Representations of Turns in
Dialogue [0.0]
Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue.
We propose the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues.
arXiv Detail & Related papers (2021-09-09T03:09:08Z) - Recent Advances in Deep Learning-based Dialogue Systems [12.798560005546262]
We mainly focus on the deep learning-based dialogue systems.
This survey is the most comprehensive and upto-date one at present in the area of dialogue systems and dialogue-related tasks.
arXiv Detail & Related papers (2021-05-10T14:07:49Z) - Discovering Dialog Structure Graph for Open-Domain Dialog Generation [51.29286279366361]
We conduct unsupervised discovery of dialog structure from chitchat corpora.
We then leverage it to facilitate dialog generation in downstream systems.
We present a Discrete Variational Auto-Encoder with Graph Neural Network (DVAE-GNN), to discover a unified human-readable dialog structure.
arXiv Detail & Related papers (2020-12-31T10:58:37Z) - Probing Neural Dialog Models for Conversational Understanding [21.76744391202041]
We analyze the internal representations learned by neural open-domain dialog systems.
Our results suggest that standard open-domain dialog systems struggle with answering questions.
We also find that the dyadic, turn-taking nature of dialog is not fully leveraged by these models.
arXiv Detail & Related papers (2020-06-07T17:32:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.