Papers with end-to-end setting
LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization (2020.coling-main)
Copied to clipboard
Nurul Lubis, Christian Geishauser, Michael Heck, Hsien-chin Lin, Marco Moresi, Carel van Niekerk, Milica Gasic
| Challenge: | Reinforcement learning (RL) can be used to steer a conversation towards successful task completion. |
| Approach: | They propose to use latent latent variables to shape latent variable distributions . they use response auto-encoding as auxiliary task to capture generative factors . |
| Outcome: | The proposed approach yields a more action-characterized latent representations . the proposed approach achieves state-of-the-art success rates . |
Improving End-to-End Task-Oriented Dialog System with A Simple Auxiliary Task (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Using large pre-trained language models for end-to-end TOD modeling has made significant progress on benchmarks . a paradigm of leveraging large pretrained models has shown promising results . |
| Approach: | They combine paradigm of leveraging large pre-trained language models with multi-task learning framework . their model achieves new state-of-the-art results with combined scores of 108.3 and 107.5 . |
| Outcome: | The proposed model achieves state-of-the-art results on multiWOZ 2.0 and MultiWOZ 2.1 . it also improves generalization capability through domain adaptation experiments in the few-shot setting. |
End-to-end Neural Information Status Classification (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on information status classification and bridging anaphora recognition assume that gold mention or syntactic tree information is given. |
| Approach: | They propose an end-to-end neural approach for information status classification using a mention extraction component and an information status assignment component. |
| Outcome: | The proposed system achieves state-of-the-art on fine-grained IS classification based on gold mentions and better than baselines on ISNotes and SciCorp. |
Open-Domain Safety Policy Construction (2026.findings-eacl)
Copied to clipboard
| Challenge: | Moderation layers are core component of many products built on user-generated content. |
| Approach: | They propose a system that drafts a content moderation policy based on human-written seed domain information. |
| Outcome: | The proposed system outperforms definition-only and in-context learning baselines on openAI undesired content benchmarks and an in-house multimodal advertisement moderation benchmark. |
Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing work on document-level relation extraction has focused on end-to-end setting that extracts global entities and relations jointly. |
| Approach: | They propose to introduce a two-way interaction between COREF and RE that is specifically designed to leverage task characteristics, bridging decisions of two tasks for direct task interference. |
| Outcome: | The proposed model achieves the best performance by up to 2.3/5.1 F1 over the baseline. |
Symbolic Inductive Bias for Visually Grounded Learning of Spoken Language (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to processing spoken language are to first automatically transcribe it into text, but there is an alternative: end-to-end learning. |
| Approach: | They propose to use multitask learning to exploit existing transcribed speech within the end-to-end setting by matching spoken captions with corresponding images, speech with text, and text with images. |
| Outcome: | The proposed model improves image retrieval performance compared to training the speech/image task in isolation. |