IRIS: a Chat-oriented Dialogue System based on the Vector Space Model

By Rafael E. Banchs, Haizhou Li. 2012

223 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

A Diversity-Promoting Objective Function for Neural Conversation Models (2015, background): “…heuristic-driven even where there is a statistical component (Levin et al., 2000; Oh and Rudnicky, 2000; Ratna-parkhi, 2002; Walker et al., 2003; Pieraccini et al., 2009; Young et al., 2010; Wang et al., 2011; Banchs and Li, 2012; Chen et al., 2013; Ameixa et al., 2014; Nio et al., 2014).”
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models (2015, background): “To the best of our knowledge, Banchs et al. (2012) were the ﬁrst to suggest using movie scripts to build dialogue systems.”
Deep Reinforcement Learning for Dialogue Generation (2016, background): “…Processes (MDPs) (Levin et al., 1997; Levin et al., 2000; Walker et al., 2003; Pieraccini et al., 2009), POMDP (Young et al., 2010; Young et al., 2013) models, and models that statistically learn generation rules (Oh and Rudnicky, 2000; Ratnaparkhi, 2002; Banchs and Li, 2012; Nio et al., 2014).”
A Persona-Based Neural Conversation Model (2016, background): “…et al., 2000; Young et al., 2010; Walker et al., 2003; Pieraccini et al., 2009; Wang et al., 2011) or learning generation rules from a minimal set of authored rules or labels (Oh and Rudnicky, 2000; Ratnaparkhi, 2002; Banchs and Li, 2012; Ameixa et al., 2014; Nio et al., 2014; Chen et al., 2013).”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “Banchs and Li (2012) construct an information retrieval system based on movie scripts using the vector space model.”
Strategy and Policy Learning for Non-Task-Oriented Conversational Systems (2016, methodology): “There are a variety of methods to generate responses for non-task-oriented systems, such as machine translation (Ritter et al., 2011), retrieval-based response selection (Banchs and Li, 2012), and sequence-to-sequence recurrent neural network (Vinyals and Le, 2015).”
Survey on evaluation methods for dialogue systems (2019, background): “ 6) to automatically author a dialogue strategy that can be used in conversational systems such as chatbots (Banchs and Li 2012; Charras et al.”
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network (2018, background): “Most modern chatbots are data-driven, either in a fashion of information-retrieval (Ji et al., 2014; Banchs and Li, 2012; Nio et al., 2014; Ameixa et al., 2014) or sequence-generation (Ritter et al., 2011).”
Developing Non-goal Dialog System Based on Examples of Drama Television (2012, methodology): “One way to overcome these problems was proposed by [11] IRIS (Informal Response Interactive System), which uses a vector space model to implement a chat oriented dialog system based on movie scripts [12].”
Towards a Continuous Knowledge Learning Engine for Chatbots (2018, methodology): “Early such systems were mostly built using markup languages such as AIML1, handcrafted conversation generation rules, and/or information retrieval techniques (Banchs and Li, 2012; Ameixa et al., 2014; Lowe et al., 2015; Serban et al., 2015).”
Neural personalized response generation as domain adaptation (2017, methodology): “[47] introduced a search-based system, namely IRIS, to generate dialogues using vector space model and then released the experimental corpus for research and development [48].”
The Importance of Modeling Social Factors of Language: Theory and Practice (2021, background): “Despite conversational agents’ recent successes (Rit-ter et al., 2011; Banchs and Li, 2012; Serban et al., 2016), their lack of a consistent personality is still one of the common issues in us-ing data-driven approaches.”
Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture (2018, methodology): “The initial systems [Banchs and Li, 2012] were based on information retrieval techniques and operated by taking immediately preceding inputs (such as the human’s last turn, possibly in combination with the system’s last turn) as a retrieval key for a database of conversational material, such as ﬁlm…”
Luke, I am Your Father: Dealing with Out-of-Domain Requests by Using Movies Subtitles (2014, background): “Recently, the work presented in [3] describes a chat-oriented dialogue system, which has in its knowledge sources MovieDiC [2], a corpus extracted from movies scripts.”