Information-Enhanced Hierarchical Self-Attention Network for Multiturn Dialog Generation

Wang, Jiamin; Sun, Xiao; Chen, Qian; Wang, Meng

doi:10.1109/tcss.2022.3172699

Cited by 8 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TA-Seq2Seq [14] focuses on transforming the conversation topic to assist in response prediction. Combining multiple levels of dialogue context can achieve better context modeling and also yields notable effectiveness in response generation tasks, such as HiSA-GDS, HSAN, IEHSA, HDID and HHKS [15,[24][25][26][27]. For example, HiSA-GDS utilizes the word-level and sentence-level history successively to interact with responses.…”

Section: His2res Methodsmentioning

confidence: 99%

An Adaptive Contextual Relation Model for Improving Response Generation

Wang,

Tian,

Yuan

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Context modeling has always been the groundwork for the dialogue response generation task, yet it presents challenges due to the loose context relations among open-domain dialogue sentences. Introducing simulated dialogue futures has been proposed as a solution to mitigate the problem of low history–response relevance. However, these approaches simply assume that the history and future of a dialogue have the same effect on response generation. In reality, the coherence between dialogue sentences varies, and thus, history and the future are not uniformly helpful in response prediction. Consequently, determining and leveraging the relevance between history–response and response–future to aid in response prediction emerges as a pivotal concern. This paper addresses this concern by initially establishing three context relations of response and its context (history and future), reflecting the relevance between the response and preceding and following sentences. Subsequently, we annotate response contextual relation labels on a large-scale dataset, DailyDialog (DD). Leveraging these relation labels, we propose a response generation model that adaptively integrates contributions from preceding and succeeding sentences guided by explicit relation labels. This approach mitigates the impact in cases of lower relevance and amplifies contributions in cases of higher relevance, thus improving the capability of context modeling. Experimental results on public dataset DD demonstrate that our response generation model significantly enhances coherence by 3.02% in long sequences (4-gram) and augments bi-gram diversity by 17.67%, surpassing the performance of previous models.

show abstract

Section: His2res Methodsmentioning

confidence: 99%

An Adaptive Contextual Relation Model for Improving Response Generation

Wang,

Tian,

Yuan

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In trajectory modeling, transitions between sets of different locations are characterized. If semantic information is available, supervised techniques such as graph neural networks [11] or SVM [12] can be used. In the context-independent case, unsupervised techniques such as clustering [13] or frequent item mining [14] approaches can be used for this purpose.…”

Section: Work Related To Probability Model-based Processing Of Locati...mentioning

confidence: 99%

Particle filtering supported probability density estimation of mobility patterns

Darányi,

Ruppert,

Abonyi

2024

Heliyon

View full text Add to dashboard Cite

“…[28] reads the word embedding sequence through a sliding convolutional unit and uses max-pooling to obtain the sentence-level history representation, interacting the word and sentence-level representation with candidate responses to select high probability responses. [29] propose a multi-level transformer-based model that divides multiple words/sentences into local units of fixed size for sequences of words/sentences respectively, and uses RNN to encode units at two levels, to enhance the ability to capture relevant context. In addition to the above hierarchy division methods, the use of knowledge labels can also help predict knowledge [2].…”

Section: Semantic Unit Granularitymentioning

confidence: 99%

Enhancing Document Information Selection Through Multi-Granularity Responses for Dialogue Generation

Wang,

Qiao,

Xing

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

Document information selection is an essential part of document-grounded dialogue tasks, and more accurate information selection results can provide more appropriate dialogue responses. Existing works have achieved excellent results by employing multi-granularity of dialogue history information, indicating the effectiveness of multi-level historical information. However, these works often focus on exploring the hierarchical information of dialogue history, while neglecting the multi-granularity utilization in response, important information that holds an impact on the decoding process. Therefore, this paper proposes a model for document information selection based on multi-granularity responses. By integrating the document selection results at the response word level and semantic unit level, the model enhances its capability in knowledge selection and produces better responses. For the division at the semantic unit level of the response, we propose two semantic unit division methods, static and dynamic. Experiments on two public datasets show that our models combining static or dynamic semantic unit levels significantly outperform baseline models.

show abstract

Information-Enhanced Hierarchical Self-Attention Network for Multiturn Dialog Generation

Cited by 8 publications

References 27 publications

An Adaptive Contextual Relation Model for Improving Response Generation

An Adaptive Contextual Relation Model for Improving Response Generation

Particle filtering supported probability density estimation of mobility patterns

Enhancing Document Information Selection Through Multi-Granularity Responses for Dialogue Generation

Contact Info

Product

Resources

About