nlp:dialog

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
nlp:dialog [2023/07/24 22:26] – [Evaluation] jmflanignlp:dialog [2024/09/04 00:27] (current) – [Dialog Acts] jmflanig
Line 12: Line 12:
     * [[https://arxiv.org/pdf/2201.06657.pdf|Caldarini et al 2022 - A Literature Survey of Recent Advances in Chatbots]]     * [[https://arxiv.org/pdf/2201.06657.pdf|Caldarini et al 2022 - A Literature Survey of Recent Advances in Chatbots]]
     * [[https://arxiv.org/pdf/2212.09252.pdf|Shaier et al 2022 - Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems]]     * [[https://arxiv.org/pdf/2212.09252.pdf|Shaier et al 2022 - Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems]]
 +    * [[https://arxiv.org/pdf/2402.18013|Yi et al 2024 - A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems]]
 +  * Courses
 +    * **[[https://docs.google.com/spreadsheets/d/1nSKcnM5r9x82BdyPgn-obN1sRUlLC7zZ082a0132Igk/edit?fbclid=IwAR1tX8eztqZ4Kn4NNPUvkkGKCurikWtv-wcSnRyDRg4M544dQtSXTTb3vfM#gid=1523499517|Zhou Yu's Conversational AI course at Columbia]]**
   * Datasets   * Datasets
     * [[https://arxiv.org/pdf/1512.05742.pdf|Serban et al 2017 - A Survey of Available Corpora for Building Data-Driven Dialogue Systems]]     * [[https://arxiv.org/pdf/1512.05742.pdf|Serban et al 2017 - A Survey of Available Corpora for Building Data-Driven Dialogue Systems]]
Line 34: Line 37:
   * SOTA (2020, better than Meena) neural dialog generation: [[https://arxiv.org/pdf/2004.13637.pdf|Roller et al 2020 - Recipes for building an open-domain chatbot]]. [[https://parl.ai/projects/recipes/|Code and models]]   * SOTA (2020, better than Meena) neural dialog generation: [[https://arxiv.org/pdf/2004.13637.pdf|Roller et al 2020 - Recipes for building an open-domain chatbot]]. [[https://parl.ai/projects/recipes/|Code and models]]
   * [[https://arxiv.org/abs/2009.11423|Andreas et al 2020 - Task-Oriented Dialogue as Dataflow Synthesis]]   * [[https://arxiv.org/abs/2009.11423|Andreas et al 2020 - Task-Oriented Dialogue as Dataflow Synthesis]]
 +  * [[https://arxiv.org/pdf/2205.09073.pdf|Dai et al 2022 - Dialog Inpainting: Turning Documents into Dialogs]]
  
 ===== Chatbots ===== ===== Chatbots =====
 +See also [[Chatbots]].
 +
   * [[https://arxiv.org/abs/2008.12579|Madotto et al 2020 - The Adapter-Bot: All-In-One Controllable Conversational Model]]   * [[https://arxiv.org/abs/2008.12579|Madotto et al 2020 - The Adapter-Bot: All-In-One Controllable Conversational Model]]
  
Line 63: Line 69:
 See [[nlp:vision_and_language#Multimodal Dialog Agents|Vision and Language - Multimodal Dialog Agents]]. See [[nlp:vision_and_language#Multimodal Dialog Agents|Vision and Language - Multimodal Dialog Agents]].
  
 +
 +===== Dialog Policy =====
 +For a nice overview, see related work section of [[https://arxiv.org/pdf/2407.05674|Joshi 2024]].
 +
 +  * [[https://arxiv.org/pdf/2407.05674|Joshi et al 2024 - LLM-Based Open-Domain Integrated Task and Knowledge Assistants with Programmable Policies]] (Has a great overview)
  
 ===== Dialog Acts ===== ===== Dialog Acts =====
Line 71: Line 82:
   * [[https://groups.inf.ed.ac.uk/ami/corpus/Guidelines/dialogue_acts_manual_1.0.pdf|2005 - Guidelines for Dialogue Act and Addressee Annotation Version 1.0]] Guidelines for the [[https://groups.inf.ed.ac.uk/ami/corpus/index.shtml|AMI dataset]]   * [[https://groups.inf.ed.ac.uk/ami/corpus/Guidelines/dialogue_acts_manual_1.0.pdf|2005 - Guidelines for Dialogue Act and Addressee Annotation Version 1.0]] Guidelines for the [[https://groups.inf.ed.ac.uk/ami/corpus/index.shtml|AMI dataset]]
   * [[https://arxiv.org/pdf/1908.10023.pdf|Yu & Yu 2019 - MIDAS, A Dialog Act Annotation Scheme for Open-Domain Human-Machine Spoken Conversations]] There used to be a corpus and an open-source system available, but it has been taken down. Jurik uses this tagger in his system   * [[https://arxiv.org/pdf/1908.10023.pdf|Yu & Yu 2019 - MIDAS, A Dialog Act Annotation Scheme for Open-Domain Human-Machine Spoken Conversations]] There used to be a corpus and an open-source system available, but it has been taken down. Jurik uses this tagger in his system
 +
 +=== Taxonomies of Dialog Acts ===
 +  * [[https://arxiv.org/pdf/1907.03020.pdf|Paul et al 2019 - Towards Universal Dialogue Act Tagging for Task-Oriented Dialogues]]
  
 ==== Predicting Dialog Acts ==== ==== Predicting Dialog Acts ====
Line 102: Line 116:
   * [[https://parl.ai/projects/wizard_of_wikipedia/|Wizard of Wikipedia]] - Paper: [[https://arxiv.org/pdf/1811.01241.pdf|Dinan et al 2018 - Wizard of Wikipedia: Knowledge-Powered Conversational Agents]]   * [[https://parl.ai/projects/wizard_of_wikipedia/|Wizard of Wikipedia]] - Paper: [[https://arxiv.org/pdf/1811.01241.pdf|Dinan et al 2018 - Wizard of Wikipedia: Knowledge-Powered Conversational Agents]]
   * **[[https://github.com/jfainberg/self_dialogue_corpus|Self-dialogue Corpus]] - Paper: [[https://arxiv.org/pdf/1809.06641.pdf|Fainberg et al 2018 - Talking to myself: self-dialogues as data for conversational agents]]**   * **[[https://github.com/jfainberg/self_dialogue_corpus|Self-dialogue Corpus]] - Paper: [[https://arxiv.org/pdf/1809.06641.pdf|Fainberg et al 2018 - Talking to myself: self-dialogues as data for conversational agents]]**
 +  * [[https://github.com/google-research-datasets/dstc8-schema-guided-dialogue|Schema-Guided Dialogue Dataset]] - Paper: [[https://arxiv.org/pdf/1909.05855.pdf|Rastogi et al 2019 - Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset]]
   * [[https://github.com/alexa/Topical-Chat|Topical-Chat]] - Paper: [[https://m.media-amazon.com/images/G/01/amazon.jobs/3079_Paper._CB1565131710_.pdf|Gopalakrishnan et al 2019 - Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations]]   * [[https://github.com/alexa/Topical-Chat|Topical-Chat]] - Paper: [[https://m.media-amazon.com/images/G/01/amazon.jobs/3079_Paper._CB1565131710_.pdf|Gopalakrishnan et al 2019 - Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations]]
   * [[https://github.com/PolyAI-LDN/conversational-datasets|Repository of Conversational Datasets]] - Paper: [[https://arxiv.org/pdf/1904.06472.pdf|Henderson et al 2019 - A Repository of Conversational Datasets]]   * [[https://github.com/PolyAI-LDN/conversational-datasets|Repository of Conversational Datasets]] - Paper: [[https://arxiv.org/pdf/1904.06472.pdf|Henderson et al 2019 - A Repository of Conversational Datasets]]
Line 123: Line 138:
  
 ===== Evaluation ===== ===== Evaluation =====
-See also [[Chatbots#Evaluation]].+See also [[Chatbots#Evaluation|Chatbots - Evaluation]].
   * [[https://aclanthology.org/P97-1035.pdf|Walker et al 1997 - PARADISE: A Framework for Evaluating Spoken Dialogue Agents]] (Task oriented dialog I believe)   * [[https://aclanthology.org/P97-1035.pdf|Walker et al 1997 - PARADISE: A Framework for Evaluating Spoken Dialogue Agents]] (Task oriented dialog I believe)
  
Line 152: Line 167:
  
 ===== Related Pages ===== ===== Related Pages =====
 +  * [[Autonomous Language Agents]]
   * [[Chatbots]]   * [[Chatbots]]
   * [[Discourse Analysis]]   * [[Discourse Analysis]]
nlp/dialog.1690237582.txt.gz · Last modified: 2023/07/24 22:26 by jmflanig

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki