# Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systems

arXiv: https://arxiv.org/abs/1807.11567 · HTML: https://mlsanity.com/paper/1807.11567/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2018.

## Built on by (most cited first, 18 of 18)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Uncertainty in Natural Language Processing: Sources, Quantification, and Applications](https://mlsanity.com/paper/2306.04459/) (2023)
- [Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training](https://mlsanity.com/paper/2106.08616/) (2021)
- [A Survey on Out-of-Distribution Detection in NLP](https://mlsanity.com/paper/2305.03236/) (2023)
- [Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances](https://mlsanity.com/paper/2409.11884/) (2024)
- [Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU](https://mlsanity.com/paper/2106.14464/) (2021)
- [Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data](https://mlsanity.com/paper/2212.09171/) (2022)
- [GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation](https://mlsanity.com/paper/2109.03079/) (2021)
- [Estimating Soft Labels for Out-of-Domain Intent Detection](https://mlsanity.com/paper/2211.05561/) (2022)
- [Energy-based Unknown Intent Detection with Data Manipulation](https://mlsanity.com/paper/2107.12542/) (2021)
- [Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts](https://mlsanity.com/paper/2305.03237/) (2023)
- [ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection](https://mlsanity.com/paper/2108.12229/) (2021)
- [Effective Open Intent Classification with K-center Contrastive Learning and Adjustable Decision Boundary](https://mlsanity.com/paper/2304.10220/) (2023)
- [EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System](https://mlsanity.com/paper/2309.03246/) (2023)
- [NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models](https://mlsanity.com/paper/2110.02054/) (2021)
- [Exploring the Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Out-of-Scope Detection Tasks](https://mlsanity.com/paper/2205.09021/) (2022)
- [Identifying Hijacked Reviews](https://mlsanity.com/paper/2107.05385/) (2021)
- [BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.08852/) (2023)

## Abstract (arXiv)

To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentences are available as training data because collecting enough OOD sentences in an unbiased way is a laborious and time-consuming job. This paper proposes a novel neural sentence embedding method that represents sentences in a low-dimensional continuous vector space that emphasizes aspects that distinguish ID cases from OOD cases. We first used a large set of unlabeled text to pre-train word representations that are used to initialize neural sentence embedding. Then we used domain-category analysis as an auxiliary task to train neural sentence embedding for OOD sentence detection. After the sentence representations were learned, we used them to train an autoencoder aimed at OOD sentence detection. We evaluated our method by experimentally comparing it to the state-of-the-art methods in an eight-domain dialog system; our proposed method achieved the highest accuracy in all tests.