NLP Wiki

User Tools

Site Tools

Trace:
nlp:task_oriented_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:task_oriented_dialog [2023/04/05 23:47] – [Few-Shot Task Oriented Dialog] jmflanignlp:task_oriented_dialog [2023/09/08 18:39] (current) – [Response Generation] jmflanig
Line 14: Line 14:
  
 ===== Prompting and In-Context Learning ===== ===== Prompting and In-Context Learning =====
 +See also Response Generation, below.
 +
   * [[https://arxiv.org/pdf/2110.08118.pdf|Madotto et al 2021 - Few-Shot Bot: Prompt-Based Learning for Dialogue Systems]]   * [[https://arxiv.org/pdf/2110.08118.pdf|Madotto et al 2021 - Few-Shot Bot: Prompt-Based Learning for Dialogue Systems]]
   * [[https://arxiv.org/pdf/2203.08568.pdf|Hu et al 2022 - In-Context Learning for Few-Shot Dialogue State Tracking]]   * [[https://arxiv.org/pdf/2203.08568.pdf|Hu et al 2022 - In-Context Learning for Few-Shot Dialogue State Tracking]]
 +  * [[https://arxiv.org/pdf/2307.01453.pdf|King & Flanigan 2023 - Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking]]
 +
 +===== Semi-supervised Methods =====
 +  * [[https://aclanthology.org/2022.aacl-short.37.pdf|Zhang et al 2022 - CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking]]
  
 ===== Domain Adaptation ===== ===== Domain Adaptation =====
Line 24: Line 30:
  
   * MultiWoz   * MultiWoz
 +    * [[https://github.com/budzianowski/multiwoz|MultiWOZ]] Also a data to text generation dataset.
 +    * Paper v1.0: [[https://arxiv.org/pdf/1807.06517.pdf|Ramadan et al 2018 - Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing]].
 +    * Paper v2.0: [[https://arxiv.org/pdf/1810.00278.pdf|Budzianowski et al 2018 - MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling]]
     * See also [[https://paperswithcode.com/sota/multi-domain-dialogue-state-tracking-on-1|Multi-domain Dialogue State Tracking on MULTIWOZ 2.1]]     * See also [[https://paperswithcode.com/sota/multi-domain-dialogue-state-tracking-on-1|Multi-domain Dialogue State Tracking on MULTIWOZ 2.1]]
     * STAR: [[https://arxiv.org/pdf/2101.09374.pdf|Ye et al 2021 - Slot Self-Attentive Dialogue State Tracking]] SOTA as of 2022     * STAR: [[https://arxiv.org/pdf/2101.09374.pdf|Ye et al 2021 - Slot Self-Attentive Dialogue State Tracking]] SOTA as of 2022
Line 29: Line 38:
   * [[https://arxiv.org/pdf/2106.00291.pdf|Dai et al 2021 - Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking]]   * [[https://arxiv.org/pdf/2106.00291.pdf|Dai et al 2021 - Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking]]
  
 +===== Response Generation =====
 +  * **With LLMs**
 +    * [[https://arxiv.org/pdf/2110.08118.pdf|Madotto et al 2021 - Few-Shot Bot: Prompt-Based Learning for Dialogue Systems]]
 +    * [[https://arxiv.org/pdf/2302.11520.pdf|Li et al 2023 - Guiding Large Language Models via Directional Stimulus Prompting]]
  
 ===== Related Pages ===== ===== Related Pages =====
nlp/task_oriented_dialog.1680738455.txt.gz · Last modified: 2023/06/15 07:36 (external edit)
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki