# Fuzzy Classification of Multi-intent Utterances

arXiv: https://arxiv.org/abs/2104.10830 · HTML: https://mlsanity.com/paper/2104.10830/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 38 references that are in the map.
- First posted on arXiv 22 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue](https://mlsanity.com/paper/2004.06871/) (2020)
- [Zero-shot User Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1809.00385/) (2018)
- [Being Bayesian about Categorical Probability](https://mlsanity.com/paper/2002.07965/) (2020)
- [Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks](https://mlsanity.com/paper/1603.03827/) (2016)
- [Resolving Intent Ambiguities by Retrieving Discriminative Clarifying Questions](https://mlsanity.com/paper/2008.07559/) (2020)
- [Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems](https://mlsanity.com/paper/1703.07055/) (2017)
- [Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks](https://mlsanity.com/paper/1805.06242/) (2018)

## Built on by (most cited first, 2 of 2)

- [Database Search Results Disambiguation for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2112.08351/) (2021)
- [Calibration Error Estimation Using Fuzzy Binning](https://mlsanity.com/paper/2305.00543/) (2023)

## Abstract (arXiv)

Current intent classification approaches assign binary intent class memberships to natural language utterances while disregarding the inherent vagueness in language and the corresponding vagueness in intent class boundaries. In this work, we propose a scheme to address the ambiguity in single-intent as well as multi-intent natural language utterances by creating degree memberships over fuzzified intent classes. To our knowledge, this is the first work to address and quantify the impact of the fuzzy nature of natural language utterances over intent category memberships. Additionally, our approach overcomes the sparsity of multi-intent utterance data to train classification models by using a small database of single intent utterances to generate class memberships over multi-intent utterances. We evaluate our approach over two task-oriented dialog datasets, across different fuzzy membership generation techniques and approximate string similarity measures. Our results reveal the impact of lexical overlap between utterances of different intents, and the underlying data distributions, on the fuzzification of intent memberships. Moreover, we evaluate the accuracy of our approach by comparing the defuzzified memberships to their binary counterparts, across different combinations of membership functions and string similarity measures.