← Search

Iñigo Casanueva

2 accepted papers

2022

Multi-Label Intent Detection via Contrastive Task Specialization of Sentence Encoders

EMNLP 2022main

Deploying task-oriented dialog ToD systems for new domains and tasks requires natural language understanding models that are 1) resource-efficient and work under low-data regimes; 2) adaptable, efficient, and quick-to-train; 3) expressive and can handle complex ToD scenarios with multiple user inten…

2021

ConvFiT: Conversational Fine-Tuning of Pretrained Language Models

EMNLP 2021main

Transformer-based language models (LMs) pretrained on large text collections are proven to store a wealth of semantic knowledge. However, 1) they are not effective as sentence encoders when used off-the-shelf, and 2) thus typically lag behind conversationally pretrained (e.g., via response selection…