Skip to search formSkip to main contentSkip to account menu

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

A Transferable Dialogue State Generator (TRADE) that generates dialogue states from utterances using copy mechanism, facilitating transfer when predicting (domain, slot, value) triplets not encountered during training.
View on ACL (opens in a new tab)

A Simple Language Model for Task-Oriented Dialogue

SimpleTOD is a simple approach to task-oriented dialogue that uses a single causal language model trained on all sub-tasks recast as a single sequence prediction problem, which allows it to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2.
View PDF on arXiv (opens in a new tab)

TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue

The experimental results show that the pre-trained task- oriented dialogue BERT (ToD-BERT) surpasses BERT and other strong baselines in four downstream task-oriented dialogue applications, including intention detection, dialogue state tracking, dialogue act prediction, and response selection.
View on ACL (opens in a new tab)

Global-to-local Memory Pointer Networks for Task-Oriented Dialogue

The proposed global-to-local memory pointer networks can improve copy accuracy and mitigate the common out-of-vocabulary problem, and is able to improve over the previous state- of-the-art models in both simulated bAbI Dialogue dataset and human-human Stanford Multi-domain Dialogue dataset on automatic and human evaluation.
View PDF on arXiv (opens in a new tab)

Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking

This paper proposes a simple yet effective dual-strategy model for DST, by adapting a single BERT-style reading comprehension model to jointly handle both the categorical and non-categorical slots.
View on ACL (opens in a new tab)

Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems

This paper empirically shows how Mem2Seq controls each generation step, and how its multi-hop attention mechanism helps in learning correlations between memories.
View on ACL (opens in a new tab)

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing

GraPPa is an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data and significantly outperforms RoBERTa-large as the feature representation layers and establishes new state-of-the-art results on all of them.
View PDF on arXiv (opens in a new tab)

Personalizing Dialogue Agents via Meta-Learning

This paper proposes to extend Model-Agnostic Meta-Learning (MAML) to personalized dialogue learning without using any persona descriptions, and demonstrates that its model outperforms non-meta-learning baselines using automatic evaluation metrics, and in terms of human-evaluated fluency and consistency.
View on ACL (opens in a new tab)

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference

This paper proposes to boost the discriminative ability by transferring a natural language inference (NLI) model, and achieves more stable and accurate in-domain and OOS detection accuracy than RoBERTa-based classifiers and embedding-based nearest neighbor approaches.
View on ACL (opens in a new tab)

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models

The UnifiedSKG framework is proposed, which unifies 21 SKG tasks into a text-to-text format, aiming to promote systematic SKG research, instead of being exclusive to a single task, domain, or dataset.
View on ACL (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)