Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

Gu, Jia-Chen; Ling, Zhen-Hua; Liu, Quan

doi:10.1145/3357384.3358140

Cited by 65 publications

(78 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early studies focus on the single-turn dialogue with the user input regarded as the query [11,34,35], and recently move to the multi-turn dialogue where the dialogue history and the user input are both taken into account. Representative methods include the Dual LSTM [19], the deep learning-to-respond architecture [40], the multi-view matching model [51], the sequential matching network [37], the deep attention matching network [52], the multi-representation fusion network [31], the interaction-over-interaction matching network [32], and the interaction matching network [7]. Knowledge is crucial to the dialogue in the real world.…”

Section: Related Workmentioning

confidence: 99%

Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems

Hua

Zhao

Tao

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Recently, knowledge-grounded conversations in the open domain gain great attention from researchers. Existing works on retrievalbased dialogue systems have paid tremendous efforts to utilize neural networks to build a matching model, where all of the context and knowledge contents are used to match the response candidate with various representation methods. Actually, different parts of the context and knowledge are differentially important for recognizing the proper response candidate, as many utterances are useless due to the topic shift. Those excessive useless information in the context and knowledge can influence the matching process and leads to inferior performance. To address this problem, we propose a multi-turn Response Selection Model that can Detect the relevant parts of the Context and Knowledge collection (RSM-DCK). Our model first uses the recent context as a query to pre-select relevant parts of the context and knowledge collection at the word-level and utterance-level semantics. Further, the response candidate interacts with the selected context and knowledge collection respectively. In the end, the fused representation of the context and response candidate is utilized to post-select the relevant parts of the knowledge collection for matching with more confidence. We test our proposed model on two benchmark datasets. Evaluation results indicate that our model achieves better performance than the existing methods, and can effectively detect the relevant context and knowledge for response selection.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems

Hua

Zhao

Tao

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

show abstract

“…In this paper, we build our baseline model based on IMN (Gu et al, 2019). After the context and response embeddings are obtained in the IMN model, the context-level persona fusion architecture shown in Figure 1(a) is applied to integrate persona information.…”

Section: Imn-based Persona Fusionmentioning

confidence: 99%

Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots

Gu¹,

Ling²,

Zhu³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

This paper proposes a dually interactive matching network (DIM) for presenting the personalities of dialogue agents in retrievalbased chatbots. This model develops from the interactive matching network (IMN) which models the matching degree between a context composed of multiple utterances and a response candidate. Compared with previous persona fusion approaches which enhance the representation of a context by calculating its similarity with a given persona, the DIM model adopts a dual matching architecture, which performs interactive matching between responses and contexts and between responses and personas respectively for ranking response candidates. Experimental results on PERSONA-CHAT dataset show that the DIM model outperforms its baseline model, i.e., IMN with persona fusion, by a margin of 14.5% and outperforms the current state-of-the-art model by a margin of 27.7% in terms of top-1 accuracy hits@1.

show abstract

“…Building a conversational agent with intelligence has received significant attention with the emergence of personal assistants such as Apple Siri, Google Now and Microsoft Cortana. One approach is to building retrieval-based chatbots, which aims to select a potential response from a set of candidates given the conversation context (Lowe et al, 2015;Wu et al, 2017;Zhou et al, 2018b;Gu et al, 2019a;Gu et al, 2020a). (Zhou et al, 2018a).…”

Section: Introductionmentioning

confidence: 99%

Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots

Gu¹,

Ling²,

Liu³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

The challenges of building knowledgegrounded retrieval-based chatbots lie in how to ground a conversation on its background knowledge and how to match response candidates with both context and knowledge simultaneously. This paper proposes a method named Filtering before Iteratively REferring (FIRE) for this task. In this method, a context filter and a knowledge filter are first built, which derive knowledge-aware context representations and context-aware knowledge representations respectively by global and bidirectional attention. Besides, the entries irrelevant to the conversation are discarded by the knowledge filter. After that, iteratively referring is performed between context and response representations as well as between knowledge and response representations, in order to collect deep matching features for scoring response candidates. Experimental results show that FIRE outperforms previous methods by margins larger than 2.8% and 4.1% on the PERSONA-CHAT dataset with original and revised personas respectively, and margins larger than 3.1% on the CMU DoG dataset in terms of top-1 accuracy. We also show that FIRE is more interpretable by visualizing the knowledge grounding process.

show abstract

Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

Cited by 65 publications

References 13 publications

Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems

Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems

Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots

Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots

Contact Info

Product

Resources

About