Efficient Intent Detection with Dual Sentence Encoders

• URL: http://arxiv.org/abs/2003.04807v1
• Date: Tue, 10 Mar 2020 15:33:54 GMT
• Title: Efficient Intent Detection with Dual Sentence Encoders
• Authors: I\~nigo Casanueva, Tadas Tem\v{c}inas, Daniela Gerz, Matthew Henderson, Ivan Vuli\'c
• Abstract summary: 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 they outperform intent detectors based on fine-tuning the full BERT-Large model. We release our code, as well as a new challenging single-domain intent detection dataset.
• Score: 53.16532285820849
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• IntentGPT: Few-shot Intent Discovery with Large Language Models [9.245106106117317]
  We develop a model capable of identifying new intents as they emerge. IntentGPT is a training-free method that effectively prompts Large Language Models (LLMs) to discover new intents with minimal labeled data. Our experiments show that IntentGPT outperforms previous methods that require extensive domain-specific data and fine-tuning.
  arXiv  Detail & Related papers  (2024-11-16T02:16:59Z)
• Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification [6.975902383951604]
  Current methodologies face difficulties with the unpredictable distribution of outliers. We present the Dual for Threshold-Based Re-Classification (DETER) to address these challenges. Our model outperforms previous benchmarks, increasing up to 13% and 5% in F1 score for known and unknown intents.
  arXiv  Detail & Related papers  (2024-05-30T11:46:42Z)
• All Labels Together: Low-shot Intent Detection with an Efficient Label Semantic Encoding Paradigm [48.02790193676742]
  In intent detection tasks, leveraging meaningful semantic information from intent labels can be particularly beneficial for few-shot scenarios. We present an end-to-end One-to-All system that enables the comparison of an input utterance with all label candidates. Experiments on three few-shot intent detection tasks demonstrate that One-to-All is especially effective when the training resource is extremely scarce.
  arXiv  Detail & Related papers  (2023-09-07T08:50:45Z)
• Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving [91.39625612027386]
  We propose a novel task, called generalized few-shot 3D object detection, where we have a large amount of training data for common (base) objects, but only a few data for rare (novel) classes. Specifically, we analyze in-depth differences between images and point clouds, and then present a practical principle for the few-shot setting in the 3D LiDAR dataset. To solve this task, we propose an incremental fine-tuning method to extend existing 3D detection models to recognize both common and rare objects.
  arXiv  Detail & Related papers  (2023-02-08T07:11:36Z)
• Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection [93.40525251094071]
  We first point out the importance of in-domain out-of-scope detection in few-shot intent recognition tasks. We then illustrate the vulnerability of pretrained Transformer-based models against samples that are in-domain but out-of-scope (ID-OOS)
  arXiv  Detail & Related papers  (2021-06-08T17:51:12Z)
• Benchmarking Intent Detection for Task-Oriented Dialog Systems [6.54201796167054]
  Intent detection is a key component of modern goal-oriented dialog systems that accomplish a user task by predicting the intent of users' text input. There are three primary challenges in designing robust and accurate intent detection models. Our results show that Watson Assistant's intent detection model outperforms other commercial solutions.
  arXiv  Detail & Related papers  (2020-12-07T18:58:57Z)
• Learning Disentangled Intent Representations for Zero-shot Intent Detection [13.19024497857648]
  We propose a class-transductive framework that utilizes unseen class labels to learn Disentangled Representations (DIR) Under this framework, we introduce a multi-task learning objective, which encourages the model to learn the distinctions among intents. Experiments on two real-world datasets show that the proposed framework brings consistent improvement to the baseline systems.
  arXiv  Detail & Related papers  (2020-12-03T06:41:09Z)
• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference [150.07326223077405]
  Few-shot learning is attracting much attention to mitigate data scarcity. We present a discriminative nearest neighbor classification with deep self-attention. We propose to boost the discriminative ability by transferring a natural language inference (NLI) model.
  arXiv  Detail & Related papers  (2020-10-25T00:39:32Z)
• EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement [53.69674636044927]
  We present EHSOD, an end-to-end hybrid-supervised object detection system. It can be trained in one shot on both fully and weakly-annotated data. It achieves comparable results on multiple object detection benchmarks with only 30% fully-annotated data.
  arXiv  Detail & Related papers  (2020-02-18T08:04:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.