Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation

Abstract

Knowledge selection plays an important role in knowledge-grounded dialogue, which is a challenging task to generate more informative responses by leveraging external knowledge. Recently, latent variable models have been proposed to deal with the diversity of knowledge selection by using both prior and posterior distributions over knowledge and achieve promising performance. However, these models suffer from a huge gap between prior and posterior knowledge selection. Firstly, the prior selection module may not learn to select knowledge properly because of lacking the necessary posterior information. Secondly, latent variable models suffer from the exposure bias that dialogue generation is based on the knowledge selected from the posterior distribution at training but from the prior distribution at inference. Here, we deal with these issues on two aspects: (1) We enhance the prior selection module with the necessary posterior information obtained from the specially designed Posterior Information Prediction Module (PIPM); (2) We propose a Knowledge Distillation Based Training Strategy (KDBTS) to train the decoder with the knowledge selected from the prior distribution, removing the exposure bias of knowledge selection. Experimental results on two knowledge-grounded dialogue datasets show that both PIPM and KDBTS achieve performance improvement over the state-of-theart latent variable model and their combination shows further improvement.

Unsupervised Knowledge Selection for Dialogue Generation

“…Automatic Evaluation. We automatically evaluate knowledge selection with accuracy (Acc), response generation with perplexity (PPL), unigram F1 (R-1) and bigram F1 (R-2), which are commonly used in this task (Dinan et al, 2019;Kim et al, 2020a;Chen et al, 2020b). We also remove all the punctuation and (a, an, the) to compute the R-1 and R-2 scores as (Kim et al, 2020a) do.…”

“…Knowledge Distillation: We further alleviate the noisy labeling problem of distance supervision via Knowledge Distillation (KD) as shown in Figure 1 (b). Following (Tian et al, 2020;Chen et al, 2020b), the teacher takes the context and response as input and generates the distribution of knowledge selection as soft target. Compared with the student, i.e., the standard knowledge selection module described in Section 2.4, teacher has the gold response as an additional input.…”

“…It is a sport or leisure activity in which a player rolls a bowling ball towards a target. Kim et al, 2020a;Chen et al, 2020b;. In this paper, we focus on knowledge selection in the unsupervised setting where there is no gold knowledge label.…”

CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System

“…In addition to the works to enrich the contents of open-domain conversations by controllable generation (Lin et al, 2020;Madotto et al, 2020b), the knowledge grounded dialogue task aims to offer more informative conversation by leveraging an external knowledge source (Dinan et al, 2018;. Relevant knowledge selection is the key to improving the whole system, and very recently, latent variable models have been attracting more attention for this purpose (Lian et al, 2019;Liu et al, 2019b;Kim et al, 2020;Chen et al, 2020;Xu et al, 2021).…”

Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation

“…Recently, there is increasing interest in visionlanguage tasks, such as image caption Anderson et al, 2016Anderson et al, , 2018Cornia et al, 2020) and visual question answering (Ren et al, 2015a;Gao et al, 2015;Lu et al, 2016;Anderson et al, 2018). In the real world, our conversations (Chen et al, 2020b(Chen et al, , 2019 usually have multiple turns. As an extension of conventional single-turn visual question answering, Das et al (2017) introduce a multi-turn visual question answering task named visual dialogue, which aims to Q1: how many people ?…”