Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System

By Rui Yan, Yiping Song, Hua Wu. 2016

349 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Simple and Effective Retrieve-Edit-Rerank Text Generation (2020, background): “Candidate ranking has served as a core part in some retrieval-based models (Ji et al., 2014; Yan et al., 2016), but these models do not edit the retrieved candidates.”
A Retrieve-and-Edit Framework for Predicting Structured Outputs (2018, background): “One drawback to this approach is that designing a task-specific retriever is time-consuming, and a generic retriever may not perform well on tasks where x is structured or complex [40].”
What Makes Good In-Context Examples for GPT-3? (2021, background): “, 2020), dialogue generation (Yan et al., 2016; Cai et al., 2018; Song et al., 2016; Pandey et al., 2018; Weston et al., 2018; Wu et al., 2019), text summarization (Cao et al.”
Neural Approaches to Conversational AI (2018, neutral): “, generating new sentences word-byword), a more conservative solution to mitigating blandness is to replace generation-based models with retrieval-based models for response generation (Jafarpour et al., 2010; Lu and Li, 2014; Inaba and Takahashi, 2016; Al-Rfou et al., 2016; Yan et al., 2016), in whi”
Natural Language Inference by Tree-Based Convolution and Heuristic Matching (2015, background): “In some scenarios like sentence pair re-ranking (Yan et al., 2016), it is not feasible to pre-calculate the vector representations of sentences, so the matching complexity is of O ( n ) .”
Challenges in Building Intelligent Open-domain Dialog Systems (2019, methodology): “[163] reformulated input query X , and combined matching scores computed based on the reformulated and original queries, and retrieved queries and responses, respectively.”
From Eliza to XiaoIce: challenges and opportunities with social chatbots (2018, methodology): “generated by two approaches: retrieval-based (Lu and Li, 2013; Li et al., 2016; Yan et al., 2016) or generation-based (Vinyals and Le, 2015; Sordoni”
Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems (2016, neutral): “[7] and [28] use both shallow hand-crafted features and deep neural networks for matching.”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, background): “[97] selected the previous utterances in different strategies and combined them with current messages to form a reformulated context.”
Learning to Control the Specificity in Neural Response Generation (2018, methodology): “Retrieval-based conversational models search the most suitable response from candidate responses using different schemas (Kearns, 2000; Wang et al., 2013; Yan et al., 2016).”
Response Generation by Context-aware Prototype Editing (2018, methodology): “retrieval-based methods (Ji et al., 2014; Yan et al., 2016) and generation methods (Li et al.”
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation (2019, neutral): “…related to the recent work on applying retrieval mechanisms to augment text generation, such as image captioning (Kuznetsova et al., 2013; Mason and Charniak, 2014), dialogue generation (Song et al., 2016; Yan et al., 2016; Wu et al., 2018) and style transfer (Lin et al., 2017; Li et al., 2018).”
Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation (2020, background): “, 2017) and jointly trained neural models (Yan et al., 2016; Mitra et al., 2017).”
A Deep Look into Neural Ranking Models for Information Retrieval (2019, methodology): “Specifically, experiments have been conducted over neural ranking models based on collections such as Ubuntu Dialog Corpus (UDC) [75, 77, 78], Sina Weibo dataset [74, 26, 79, 80], MSDialog [81, 30, 82] and the ”campaign” NTCIR STC [83].”
Modeling Multi-turn Conversation with Deep Utterance Aggregation (2018, methodology): “15) concatenated all previous utterances and last utterance as the context representation and then computed the matching degree score based on the context representation to encode candidate response. Yan et al. (2016) selected the previous utterances in different strategies and combined them with la”
Natural Language Processing Advancements By Deep Learning: A Survey (2020, methodology): “In [174], various features and multiple data inputs have been incorporated to be ingested using a deep learning framework.”
Sequential Attention-based Network for Noetic End-to-End Response Selection (2019, methodology): “Ensembling the ensemble Models Ubuntu E-commerce R@1 R@2 R@5 R@1 R@2 R@5 TF-IDF (Lowe et al. 2015) 0.410 0.545 0.708 0.159 0.256 0.477 RNN (Lowe et al. 2015) 0.403 0.547 0.819 0.325 0.463 0.775 CNN (Kadlec, Schmid, and Kleindienst 2015) 0.549 0.684 0.896 0.328 0.515 0.792 LSTM (Kadlec, Schmid, and K”
A Literature Survey of Recent Advances in Chatbots (2021, background): “Some of these keywords were also mentioned in relevant works of literature: “con-versational entities” appears in [25]; “conversational agents” appears in [26,27], and in [28]; “conversation system” appears in the title of [29,30].”
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations (2019, neutral): “The recent advances of conversational agents have attracted research in various aspects of conversational information access [3, 6, 40, 49].”
ConveRT: Efficient and Accurate Conversational Representations from Transformers (2019, background): “Response selection is also directly applicable to retrieval-based dialog systems, a popular and elegant approach to framing dialog (Yan et al., 2016; Wu et al., 2017; Weston et al., 2018; Boussaha et al., 2019; Gunasekara et al., 2019; Henderson et al., 2019b)1.”