paper-with-me

Papers

Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue

2020-02-18 · ICLR 2020 1 · Byeongchang Kim, Jaewoo Ahn, Gunhee Kim

Knowledge-grounded dialogue is a task of generating an informative response based on both discourse context and external knowledge. As we focus on better modeling the knowledge selection in the multi-turn knowledge-grounded dialogue, we propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge; as a result, it 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. Our experimental results show that the proposed model improves the knowledge selection accuracy and subsequently the performance of utterance generation. We achieve the new state-of-the-art performance on Wizard of Wikipedia (Dinan et al., 2019) as one of the most large-scale and challenging benchmarks. We further validate the effectiveness of our model over existing conversation methods in another knowledge-based dialogue Holl-E dataset (Moghe et al., 2018).

📄 PDF Abstract BibTeX arXiv:2002.07510

Code (3)

bckim92/sequential-knowledge-transformer 공식 구현 tf
chuanmeng/dukenet pytorch
zhangbo-nlp/TransIKG pytorch

Tasks

Diversity

Methods 이 논문이 사용한 방법론

Wizard Computer vision is an interesting tool for animal behavior monitoring, mainly because it limits animal handling and it can be used to record various traits using only one sensor.…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation

2021-11-01 · EMNLP 2021 11 · Haolan Zhan, Lei Shen, Hongshen Chen, Hainan Zhang

Knowledge-grounded dialogue generation has achieved promising performance with the engagement of external knowledge sources. Typical approaches towards this task usually perform relatively independent two sub-tasks, i.e.…

Dialogue GenerationDiversityResponse Generation

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

2020-11-01 · EMNLP 2020 11 · Xiuyi Chen, Fandong Meng, Peng Li, Feilong Chen 외

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 …

DecoderDialogue GenerationKnowledge Distillation

Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition

2021-06-01 · NAACL 2021 4 · Haolan Zhan, Hainan Zhang, Hongshen Chen, Zhuoye Ding 외

Knowledge data are massive and widespread in the real-world, which can serve as good external sources to enrich conversations. However, in knowledge-grounded conversations, current models still lack the fine-grained cont…

Response Generation

GKS: Graph-based Knowledge Selector for Task-oriented Dialog System

2021-12-07 · Jen-Chieh Yang, Jia-Yan Wu, Sung-Ping Chang, Ya-Chieh Huang

In previous research, knowledge-selection tasks mostly rely on language model-based methods or knowledge ranking. However, while approaches that rely on the language models take all knowledge as sequential input, knowled…

Decision MakingGraph AttentionLanguage ModelingLanguage Modelling

Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling

2022-04-27 · Yizhe Yang, Heyan Huang, Yang Gao, Jiawei Li and

The knowledge-grounded dialogue task aims to generate responses that convey information from given knowledge documents. However, it is a challenge for the current sequence-based model to acquire knowledge from complex do…

Dialogue GenerationResponse GenerationText Generation