Efficient Intent Detection with Dual Sentence Encoders

By Iñigo Casanueva, Tadas Temvcinas, Daniela Gerz, Matthew Henderson, Ivan Vulic. 2020

640 citations recorded by the source corpus.

Building conversational systems in new domains and with added functionality requires resource-efficient models that work under low-data regimes (i.e., in few-shot setups). Motivated by these requirements, we introduce intent detection methods backed by pretrained dual sentence encoders such as USE and ConveRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that: 1) they outperform intent detectors based on fine-tuning the full BERT-Large model or using BERT as a fixed black-box encoder on three diverse intent detection data sets; 2) the gains are especially pronounced in few-shot setups (i.e., with only 10 or 30 annotated examples per intent); 3) our intent detectors can be trained in a matter of minutes on a single CPU; and 4) they are stable across different hyperparameter settings. In hope of facilitating and democratizing research focused on intention detection, we release our code, as well as a new challenging single-domain intent detection dataset comprising 13,083 annotated examples over 77 intents.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Dialogue & Conversational AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jianfeng Gao
  2. Richard Socher
  3. Caiming Xiong
  4. Mohit Bansal
  5. Ivan Vulic
  6. Luke S. Zettlemoyer
  7. Percy Liang
  8. Yoshua Bengio

In Information Systems

  1. Caiming Xiong
  2. Richard Socher
  3. Goran Glavas
  4. Dilek Z. Hakkani-Tür
  5. Philip S. Yu
  6. Matthew Henderson
  7. Anna Korhonen
  8. Prakhar Gupta

In Natural Language Processing

  1. Richard Socher
  2. Caiming Xiong
  3. Ivan Vulic
  4. Jianfeng Gao
  5. Chien-Sheng Wu
  6. Dilek Z. Hakkani-Tür
  7. Mohit Bansal
  8. Maxine Eskénazi

In Dialogue & Conversational AI

  1. Dilek Z. Hakkani-Tür
  2. Philip S. Yu
  3. Tsung-Hsien Wen
  4. Matthew Henderson
  5. Maxine Eskénazi
  6. Pei-hao Su
  7. Caiming Xiong
  8. Shikib Mehri

Citations in the corpus