Pretraining Methods for Dialog Context Representation Learning
Not on the map. Why?
Abstract (arXiv)
This paper examines various unsupervised pretraining objectives for learning dialog context representations. Two novel methods of pretraining dialog context encoders are proposed, and a total of four methods are examined. Each pretraining objective is fine-tuned and evaluated on a set of downstream dialog tasks using the MultiWoz dataset and strong performance improvement is observed. Further evaluation shows that our pretraining objectives result in not only better performance, but also better convergence, models that are less data hungry and have better domain generalizability.
Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Jun 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 11; 2022: 12; 2023: 8; 2024: 1; 2025: 3.
35 papers.
Sort:
By area:
- 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
- 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
- 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
- 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
- 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
- 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
- 2022Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialogcited by 30
- 2021ConvFiT: Conversational Fine-Tuning of Pretrained Language Modelscited by 25
- 2021Structural Pre-training for Dialogue Comprehensioncited by 20
- 2021Effective Sequence-to-Sequence Dialogue State Trackingcited by 20
- 2021Cross-lingual Intermediate Fine-tuning improves Dialogue State Trackingcited by 11
- 2021Code-switched inspired losses for generic spoken dialog representationscited by 10
23 more
- 2021Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generationcited by 8
- 2021Representation Learning for Conversational Data using Discourse Mutual Information Maximizationcited by 4
- 2022OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialoguecited by 4
- 2023Pre-training Multi-party Dialogue Models with Latent Discourse Inferencecited by 4
- 2024Domain Adaptation in Intent Classification Systems: A Reviewcited by 4
- 2022DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modelingcited by 3
- 2022KPT: Keyword-guided Pre-training for Grounded Dialog Generationcited by 3
- 2023Bengali Intent Classification with Generative Adversarial BERTcited by 3
- 2021When is it permissible for artificial intelligence to lie? A trust-based approachcited by 2
- 2023Matching-based Term Semantics Pre-training for Spoken Patient Query Understandingcited by 2
- 2022Learning Locality and Isotropy in Dialogue Modelingcited by 1
- 2023An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systemscited by 1
- 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systemscited by 1
- 2023Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixescited by 1
- 2025SS-MPC: A Sequence-Structured Multi-Party Conversation Systemcited by 1
- 2025Beyond Context: Large Language Models' Failure to Grasp Users' Intentcited by 1
- 2022A survey of neural models for the automatic analysis of conversation: Towards a better integration of the social sciencescited by 0
- 2022Zero-shot Cross-lingual Conversational Semantic Role Labelingcited by 0
- 2022On Task-Adaptive Pretraining for Dialogue Response Selectioncited by 0
- 2022SUMBot: Summarizing Context in Open-Domain Dialogue Systemscited by 0
- 2022Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systemscited by 0
- 2023InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admissioncited by 0
- 2025Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandingscited by 0
- 2025Beyond Context: Large Language Models' Failure to Grasp Users' Intent24 Dec 2025
- 2025Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings7 Mar 2025
- 2025SS-MPC: A Sequence-Structured Multi-Party Conversation System24 Feb 2025
- 2024Domain Adaptation in Intent Classification Systems: A Review26 Mar 2024
- 2023Bengali Intent Classification with Generative Adversarial BERT17 Dec 2023
- 2023Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes11 Aug 2023
- 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems14 Jul 2023
- 2023Pre-training Multi-party Dialogue Models with Latent Discourse Inference24 May 2023
- 2023An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systems17 Apr 2023
- 2023InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admission27 Mar 2023
- 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?21 Mar 2023
- 2023Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding2 Mar 2023
23 more
- 2022KPT: Keyword-guided Pre-training for Grounded Dialog Generation4 Dec 2022
- 2022Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems7 Nov 2022
- 2022SUMBot: Summarizing Context in Open-Domain Dialogue Systems12 Oct 2022
- 2022On Task-Adaptive Pretraining for Dialogue Response Selection8 Oct 2022
- 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation14 Sep 2022
- 2022OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue10 Sep 2022
- 2022Learning Locality and Isotropy in Dialogue Modeling29 May 2022
- 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning25 May 2022
- 2022Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog20 May 2022
- 2022DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling15 Apr 2022
- 2022Zero-shot Cross-lingual Conversational Semantic Role Labeling11 Apr 2022
- 2022A survey of neural models for the automatic analysis of conversation: Towards a better integration of the social sciences31 Mar 2022
- 2021Representation Learning for Conversational Data using Discourse Mutual Information Maximization4 Dec 2021
- 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection29 Nov 2021
- 2021Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking28 Sep 2021
- 2021ConvFiT: Conversational Fine-Tuning of Pretrained Language Models21 Sep 2021
- 2021Dialogue State Tracking with a Language Model using Schema-Driven Prompting15 Sep 2021
- 2021Effective Sequence-to-Sequence Dialogue State Tracking31 Aug 2021
- 2021Code-switched inspired losses for generic spoken dialog representations27 Aug 2021
- 2021Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation30 May 2021
- 2021Structural Pre-training for Dialogue Comprehension23 May 2021
- 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey10 May 2021
- 2021When is it permissible for artificial intelligence to lie? A trust-based approach9 Mar 2021
- 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
- 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
- 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
- 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
- 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
- 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
- 2022Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialogcited by 30
- 2021ConvFiT: Conversational Fine-Tuning of Pretrained Language Modelscited by 25
- 2021Structural Pre-training for Dialogue Comprehensioncited by 20
- 2021Effective Sequence-to-Sequence Dialogue State Trackingcited by 20
- 2021Cross-lingual Intermediate Fine-tuning improves Dialogue State Trackingcited by 11
- 2021Code-switched inspired losses for generic spoken dialog representationscited by 10
12 most cited of 33 All 33 (JSON)
- 2025Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings7 Mar 2025
- 2025SS-MPC: A Sequence-Structured Multi-Party Conversation System24 Feb 2025
- 2024Domain Adaptation in Intent Classification Systems: A Review26 Mar 2024
- 2023Bengali Intent Classification with Generative Adversarial BERT17 Dec 2023
- 2023Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes11 Aug 2023
- 2023Pre-training Multi-party Dialogue Models with Latent Discourse Inference24 May 2023
- 2023An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systems17 Apr 2023
- 2023InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admission27 Mar 2023
- 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?21 Mar 2023
- 2023Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding2 Mar 2023
- 2022KPT: Keyword-guided Pre-training for Grounded Dialog Generation4 Dec 2022
- 2022Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems7 Nov 2022
12 newest of 33 All 33 (JSON)