EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble
Model on Short-Text Conversation
- URL: http://arxiv.org/abs/2004.14592v1
- Date: Thu, 30 Apr 2020 05:59:12 GMT
- Title: EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble
Model on Short-Text Conversation
- Authors: Jiayi Zhang, Chongyang Tao, Zhenjing Xu, Qiaojing Xie, Wei Chen, Rui
Yan
- Abstract summary: ensembleGAN is an adversarial learning framework for enhancing a retrieval-generation ensemble model in open-domain conversation scenario.
It consists of a language-model-like generator, a ranker generator, and one ranker discriminator.
- Score: 37.80290058812499
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Generating qualitative responses has always been a challenge for
human-computer dialogue systems. Existing dialogue systems generally derive
from either retrieval-based or generative-based approaches, both of which have
their own pros and cons. Despite the natural idea of an ensemble model of the
two, existing ensemble methods only focused on leveraging one approach to
enhance another, we argue however that they can be further mutually enhanced
with a proper training strategy. In this paper, we propose ensembleGAN, an
adversarial learning framework for enhancing a retrieval-generation ensemble
model in open-domain conversation scenario. It consists of a
language-model-like generator, a ranker generator, and one ranker
discriminator. Aiming at generating responses that approximate the ground-truth
and receive high ranking scores from the discriminator, the two generators
learn to generate improved highly relevant responses and competitive unobserved
candidates respectively, while the discriminative ranker is trained to identify
true responses from adversarial ones, thus featuring the merits of both
generator counterparts. The experimental results on a large short-text
conversation data demonstrate the effectiveness of the ensembleGAN by the
amelioration on both human and automatic evaluation metrics.
Related papers
- PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded
Dialogue Systems [59.1250765143521]
Current knowledge-grounded dialogue systems often fail to align the generated responses with human-preferred qualities.
We propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework.
We demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history.
arXiv Detail & Related papers (2023-09-19T08:27:09Z) - Adversarial Conversational Shaping for Intelligent Agents [0.0]
We study the performance of two models able to enhance an intelligent conversational agent through adversarial conversational shaping.
One model is able to assign rewards to both partially and fully generated text sequences.
We discuss performance with different training details : seq2seq [ 36] and transformers [37] in a reinforcement learning framework.
arXiv Detail & Related papers (2023-07-20T12:44:47Z) - Diverse and Faithful Knowledge-Grounded Dialogue Generation via
Sequential Posterior Inference [82.28542500317445]
We present an end-to-end learning framework, termed Sequential Posterior Inference (SPI), capable of selecting knowledge and generating dialogues.
Unlike other methods, SPI does not require the inference network or assume a simple geometry of the posterior distribution.
arXiv Detail & Related papers (2023-06-01T21:23:13Z) - Towards Robust Online Dialogue Response Generation [62.99904593650087]
We argue that this can be caused by a discrepancy between training and real-world testing.
We propose a hierarchical sampling-based method consisting of both utterance-level sampling and semi-utterance-level sampling.
arXiv Detail & Related papers (2022-03-07T06:51:41Z) - Context Matters in Semantically Controlled Language Generation for
Task-oriented Dialogue Systems [6.1478669848771546]
This work combines information about the dialogue history encoded by pre-trained model with a meaning representation of the current system utterance to realize contextual language generation in task-oriented dialogues.
We utilize the pre-trained multi-context ConveRT model for context representation in a model trained from scratch; and leverage the immediate preceding user utterance for context generation in a model adapted from the pre-trained GPT-2.
arXiv Detail & Related papers (2021-11-28T11:48:02Z) - WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation
for Multi-turn Dialogue [17.663449579168297]
We simulate a dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other.
The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses.
Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation.
arXiv Detail & Related papers (2021-08-01T08:00:45Z) - Knowledge-Grounded Dialogue Generation with Pre-trained Language Models [74.09352261943911]
We study knowledge-grounded dialogue generation with pre-trained language models.
We propose equipping response generation defined by a pre-trained language model with a knowledge selection module.
arXiv Detail & Related papers (2020-10-17T16:49:43Z) - Learning an Effective Context-Response Matching Model with
Self-Supervised Tasks for Retrieval-based Dialogues [88.73739515457116]
We introduce four self-supervised tasks including next session prediction, utterance restoration, incoherence detection and consistency discrimination.
We jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner.
Experiment results indicate that the proposed auxiliary self-supervised tasks bring significant improvement for multi-turn response selection.
arXiv Detail & Related papers (2020-09-14T08:44:46Z) - Posterior-GAN: Towards Informative and Coherent Response Generation with
Posterior Generative Adversarial Network [38.576579498740244]
We propose a novel encoder-decoder based generative adversarial learning framework, Posterior Generative Adversarial Network (Posterior-GAN)
Experimental results demonstrate that our method effectively boosts the informativeness and coherence of the generated response on both automatic and human evaluation.
arXiv Detail & Related papers (2020-03-04T11:57:53Z)
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.