Efficiency and Effectiveness in Task-Oriented Dialogue: On Construction Repetition, Information Rate, and Task Success (2024.lrec-main)
Copied to clipboard
| 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 . |