Challenge: Repetition of constructions in task-oriented dialogue can have negative and positive effects on information rate and delivery, but is also predictive of task success.
Approach: They investigate the role that efficiency and effectiveness play in speakers’ repetition of shared word sequences, or constructions, in task-oriented dialogue.
Outcome: The results show that repeating constructions has negative and positive effects on information rate and delivery and that information rate managing strategies are predictive of task success.

Similar Papers

Construction Repetition Reduces Information Rate in Dialogue (2022.aacl-main)

Copied to clipboard

Challenge: We observe that construction usage lowers the information content of utterances.
Approach: They propose to use construction repetition to mitigate information rate in English open-domain spoken dialogues.
Outcome: The proposed method lowers the information content of utterances, while increasing the frequency and density of repetition.
The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialogues (2021.eacl-main)

Copied to clipboard

Challenge: chit-chat and task-oriented dialogue models are evaluated on their task success metric, but the best model is usually chosen based on task success.
Approach: They compare models playing different games to find out which one is best . they find that this discrepancy is model- and task-agnostic .
Outcome: The proposed model can generate utterances that are indistinguishable from human dialogues by learning to ground, encode, and decode words that do not occur frequently in the training set.
Is Information Density Uniform in Task-Oriented Dialogues? (2021.emnlp-main)

Copied to clipboard

Challenge: Evidence for the uniform information density principle has been found at many levels of language production.
Approach: They propose to use the Uniform Information Density principle to test whether and within which contextual units it holds in task-oriented dialogues.
Outcome: The proposed method is able to reduce fluctuations in the density of the information transmitted.
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers) (N18-3)

Copied to clipboard

Challenge: NAACL 2018 Industry Track aims to provide a forum for researchers, engineers and application developers to share their experience in real-world language problems.
Approach: NAACL 2018 Industry Track is the inaugural conference in the *ACL family of conferences . organizers wanted to provide a forum for researchers, engineers and application developers to share their experience . six of the papers were desk rejects due to non-conformance with submission requirements .
Outcome: the inaugural industry track at NAACL 2018 received 91 submissions, exceeding expectations . the track will focus on problems that manifest themselves more readily in industry .
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts) (2025.acl-tutorials)

Copied to clipboard

Challenge: ACL 2025 tutorial sessions are a cornerstone event of the conference . 76 tutorial submissions were received this year, many of which were very engaging .
Approach: 76 tutorial submissions were received this year for the tutorial session at ACL 2025 . the tutorials are designed to equip you with the latest insights, tools, and methodologies .
Outcome: the tutorial sessions at ACL 2025 will be held in london on november 8 . the conference received 76 tutorial submissions this year .
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts) (2023.acl-tutorials)

Copied to clipboard

Challenge: ACL 2023 tutorials are organized to give conference attendees a comprehensive introduction by expert researchers to some topics of importance drawn from our rapidly growing and changing research field.
Approach: ACL 2023 tutorials session is organized to give conference attendees a comprehensive introduction by experts in the field. 42 tutorial submissions were received, of which 6 were selected for presentation at ACL.
Outcome: ACL 2023 tutorials are organized to give conference attendees a comprehensive introduction . the review committee includes the EACL tutorial chairs and the ACL tutorial chair .
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts) (2026.acl-tutorials)

Copied to clipboard

Challenge: 61 submissions were received for the tutorials at ACL 2026 .
Approach: 61 tutorials were submitted for the joint call for proposals with EACL . the call for submissions was a highly competitive selection process .
Outcome: 61 submissions were received for the tutorial session at the conference this year . the tutorials cover a range of topics that have moved to the forefront of NLP research in 2026 .
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts) (2024.acl-tutorials)

Copied to clipboard

Challenge: ACL tutorial session is a highlight of the conference . it aims to provide attendees with a thorough introduction to key topics in our fast-evolving research field .
Approach: the ACL tutorial session is a highlight of the conference . it aims to provide attendees with a thorough introduction to key topics in the field .
Outcome: the ACL tutorial session is a highlight of the conference . the review process involved multiple conferences and three reviewers .
Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation (2023.eacl-srw)

Copied to clipboard

Challenge: Recent task-oriented dialogue systems are trained on annotated dialogues, but when domain knowledge changes, the initial model may become obsolete.
Approach: They propose to use an annotated dialogue dataset to train a dialogue model for domain changes . they propose to fine-tune a generative language model on domain changes to reduce performance .
Outcome: The proposed approach reduces performance by 55% by fine-tuning a generative language model on domain changes.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) (2025.acl-srw)

Copied to clipboard

Challenge: ACL 2025 Student Research Workshop is a forum for students conducting research in Computational Linguistics, Natural Language Processing, and Machine Learning.
Approach: the ACL 2025 Student Research Workshop will be held in conjunction with ACL 2020 . the virtual conference will be a forum for students conducting research in Computational Linguistics, Natural Language Processing, and Machine Learning.
Outcome: the ACL 2025 Student Research Workshop received 323 valid submissions this year . 104 papers accepted for oral presentation and poster presentations . final acceptance rate stands at 32.2%, consistent with last year's rate .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations