Saved in:
Bibliographic Details
Main Authors: Zawbaa, Hossam M., Rashwan, Wael, Dutta, Sourav, Assem, Haytham
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.19967
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913371661533184
author Zawbaa, Hossam M.
Rashwan, Wael
Dutta, Sourav
Assem, Haytham
author_facet Zawbaa, Hossam M.
Rashwan, Wael
Dutta, Sourav
Assem, Haytham
contents Detecting out-of-scope user utterances is essential for task-oriented dialogues and intent classification. Current methodologies face difficulties with the unpredictable distribution of outliers and often rely on assumptions about data distributions. We present the Dual Encoder for Threshold-Based Re-Classification (DETER) to address these challenges. This end-to-end framework efficiently detects out-of-scope intents without requiring assumptions on data distributions or additional post-processing steps. The core of DETER utilizes dual text encoders, the Universal Sentence Encoder (USE) and the Transformer-based Denoising AutoEncoder (TSDAE), to generate user utterance embeddings, which are classified through a branched neural architecture. Further, DETER generates synthetic outliers using self-supervision and incorporates out-of-scope phrases from open-domain datasets. This approach ensures a comprehensive training set for out-of-scope detection. Additionally, a threshold-based re-classification mechanism refines the model's initial predictions. Evaluations on the CLINC-150, Stackoverflow, and Banking77 datasets demonstrate DETER's efficacy. Our model outperforms previous benchmarks, increasing up to 13% and 5% in F1 score for known and unknown intents on CLINC-150 and Stackoverflow, and 16% for known and 24% % for unknown intents on Banking77. The source code has been released at https://github.com/Hossam-Mohammed-tech/Intent_Classification_OOS.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19967
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification
Zawbaa, Hossam M.
Rashwan, Wael
Dutta, Sourav
Assem, Haytham
Computation and Language
Artificial Intelligence
Machine Learning
Detecting out-of-scope user utterances is essential for task-oriented dialogues and intent classification. Current methodologies face difficulties with the unpredictable distribution of outliers and often rely on assumptions about data distributions. We present the Dual Encoder for Threshold-Based Re-Classification (DETER) to address these challenges. This end-to-end framework efficiently detects out-of-scope intents without requiring assumptions on data distributions or additional post-processing steps. The core of DETER utilizes dual text encoders, the Universal Sentence Encoder (USE) and the Transformer-based Denoising AutoEncoder (TSDAE), to generate user utterance embeddings, which are classified through a branched neural architecture. Further, DETER generates synthetic outliers using self-supervision and incorporates out-of-scope phrases from open-domain datasets. This approach ensures a comprehensive training set for out-of-scope detection. Additionally, a threshold-based re-classification mechanism refines the model's initial predictions. Evaluations on the CLINC-150, Stackoverflow, and Banking77 datasets demonstrate DETER's efficacy. Our model outperforms previous benchmarks, increasing up to 13% and 5% in F1 score for known and unknown intents on CLINC-150 and Stackoverflow, and 16% for known and 24% % for unknown intents on Banking77. The source code has been released at https://github.com/Hossam-Mohammed-tech/Intent_Classification_OOS.
title Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.19967