• Publications
  • Influence
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
TLDR
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. Expand
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
TLDR
The Plug and Play Language Model (PPLM) for controllable language generation is proposed, which combines a pretrained LM with one or more simple attribute classifiers that guide text generation without any further training of the LM. Expand
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems
TLDR
This paper empirically shows how Mem2Seq controls each generation step, and how its multi-hop attention mechanism helps in learning correlations between memories. Expand
MoEL: Mixture of Empathetic Listeners
TLDR
A novel end-to-end approach for modeling empathy in dialogue systems: Mixture of Empathetic Listeners (MoEL), which outperforms multitask training baseline in terms of empathy, relevance, and fluency. Expand
Personalizing Dialogue Agents via Meta-Learning
TLDR
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. Expand
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
TLDR
Emo2Vec is proposed which encodes emotional semantics into vectors and outperforms existing affect-related representations, such as Sentiment-Specific Word Embedding and DeepMoji embeddings with much smaller training corpora. Expand
Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables
TLDR
A zero-shot adaptation of task-oriented dialogue system to low-resource languages to cope with the variance of similar sentences across different languages, which is induced by imperfect cross-lingual alignments and inherent differences in languages is proposed. Expand
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
TLDR
This paper introduces Levenshtein belief spans (Lev), that allows efficient dialogue state tracking with a minimal generation length, and greatly improves the inference efficiency of MinTL-based systems. Expand
Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning
TLDR
This paper introduces multi-task learning based language model which shares syntax representation of languages to leverage linguistic information and tackle the low resource data issue. Expand
Plug-and-Play Conversational Models
TLDR
This paper proposes and evaluates plug-and-play methods for controllable response generation, and demonstrates a high degree of control over the generated conversational responses with regard to multiple desired attributes, while being fluent. Expand
...
1
2
3
4
5
...