2000 character limit reached
Domain Adaptation in Intent Classification Systems: A Review
Published 26 Mar 2024 in cs.CL | (2404.14415v1)
Abstract: Dialogue agents, which perform specific tasks, are part of the long-term goal of NLP researchers to build intelligent agents that communicate with humans in natural language. Such systems should adapt easily from one domain to another to assist users in completing tasks. Researchers have developed a broad range of techniques, objectives, and datasets for intent classification to achieve such systems. Despite the progress in developing intent classification systems (ICS), a systematic review of the progress from a technical perspective is yet to be conducted. In effect, important implementation details of intent classification remain restricted and unclear, making it hard for NLP researchers to develop new methods. To fill this gap, we review contemporary works in intent classification. Specifically, we conduct a thorough technical review of the datasets, domains, tasks, and methods needed to train the intent classification part of dialogue systems. Our structured analysis describes why intent classification is difficult and studies the limitations to domain adaptation while presenting opportunities for future work.
- Intent classification and slot filling for privacy policies. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4402–4417, Online. Association for Computational Linguistics.
- HINT3: Raising the bar for intent detection in the wild. In Proceedings of the First Workshop on Insights from Negative Results in NLP, pages 100–105, Online. Association for Computational Linguistics.
- SLURP: A Spoken Language Understanding Resource Package. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).
- Almawave-slu: A new dataset for slu in italian. ArXiv, abs/1907.07526.
- On the opportunities and risks of foundation models.
- Explainable abuse detection as intent classification and slot filling.
- Efficient intent detection with dual sentence encoders. In Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI, pages 38–45, Online. Association for Computational Linguistics.
- Universal sentence encoder.
- Speak or chat with me: End-to-end spoken language understanding system with flexible inputs. In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021, pages 4723–4727. ISCA.
- Bert for joint intent classification and slot filling.
- Learning to classify open intent via soft labeling and manifold mixup. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30:635–645.
- Outflip: Generating out-of-domain samples for unknown intent detection with natural language attack. CoRR, abs/2105.05601.
- Z-bert-a: a zero-shot pipeline for unknown intent detection.
- Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8440–8451, Online. Association for Computational Linguistics.
- Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces.
- Attentively embracing noise for robust latent representation in BERT. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3479–3491, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Intent detection and slot filling for vietnamese.
- Intent Detection and Slot Filling for Vietnamese. In Proceedings of the 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH).
- Bert: Pre-training of deep bidirectional transformers for language understanding.
- BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
- Jack FitzGerald. 2020. Stil - simultaneous slot filling, translation, intent classification, and language identification: Initial results using mbart on multiatis++. In AACL 2020.
- Massive: A 1m-example multilingual natural language understanding dataset with 51 typologically-diverse languages.
- Induction networks for few-shot text classification.
- Slot-gated modeling for joint slot filling and intent prediction. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 753–757, New Orleans, Louisiana. Association for Computational Linguistics.
- From masked language modeling to translation: Non-English auxiliary tasks improve zero-shot spoken language understanding. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2479–2497, Online. Association for Computational Linguistics.
- From masked language modeling to translation: Non-english auxiliary tasks improve zero-shot spoken language understanding. arXiv.
- Semantic parsing for task oriented dialog using hierarchical representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2787–2792, Brussels, Belgium. Association for Computational Linguistics.
- ConveRT: Efficient and accurate conversational representations from transformers. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2161–2174, Online. Association for Computational Linguistics.
- Convert: Efficient and accurate conversational representations from transformers.
- Training neural response selection for task-oriented dialogue systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5392–5404, Florence, Italy. Association for Computational Linguistics.
- Hubert: Self-supervised speech representation learning by masked prediction of hidden units.
- Knowledge distillation from bert transformer to speech transformer for intent classification. In Interspeech.
- A multi-task bert model for schema-guided dialogue state tracking.
- Orcas-i.
- An evaluation dataset for intent classification and out-of-scope prediction. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1311–1316, Hong Kong, China. Association for Computational Linguistics.
- Neural data augmentation via example extrapolation. CoRR, abs/2102.01335.
- BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online. Association for Computational Linguistics.
- MTOP: A comprehensive multilingual task-oriented semantic parsing benchmark. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2950–2962, Online. Association for Computational Linguistics.
- Microsoft dialogue challenge: Building end-to-end task-completion dialogue systems.
- Bing Liu and Ian Lane. 2016. Attention-based recurrent neural network models for joint intent detection and slot filling.
- Reconstructing capsule networks for zero-shot intent classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4799–4809, Hong Kong, China. Association for Computational Linguistics.
- Out-of-scope domain and intent classification through hierarchical joint modeling.
- Benchmarking natural language understanding services for building conversational agents.
- Samuel Louvan and Bernardo Magnini. 2020. Recent neural methods on slot filling and intent classification for task-oriented dialogue systems: A survey. In Proceedings of the 28th International Conference on Computational Linguistics, pages 480–496, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Speech model pre-training for end-to-end spoken language understanding.
- Shikib Mehri and Mihail Eric. 2021. Example-driven intent prediction with observers. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2979–2992, Online. Association for Computational Linguistics.
- Dialoglue: A natural language understanding benchmark for task-oriented dialogue.
- Dialoglue: A natural language understanding benchmark for task-oriented dialogue. ArXiv, abs/2009.13570.
- Pretraining methods for dialog context representation learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3836–3845, Florence, Italy. Association for Computational Linguistics.
- ImpactCite: An XLNet-based solution enabling qualitative citation impact analysis utilizing sentiment and intent. In Proceedings of the 13th International Conference on Agents and Artificial Intelligence. SCITEPRESS - Science and Technology Publications.
- Self-training improves pre-training for few-shot learning in task-oriented dialog systems.
- Representation based meta-learning for few-shot spoken intent recognition. In Interspeech 2020. ISCA.
- Generalized intent discovery: Learning from open world dialogue system.
- ProtoInfoMax: Prototypical networks with mutual information maximization for out-of-domain detection. In Findings of the Association for Computational Linguistics: EMNLP 2021. Association for Computational Linguistics.
- Adapterhub: A framework for adapting transformers.
- Revisiting mahalanobis distance for transformer-based out-of-domain detection.
- Search4code: Code search intent classification using weak supervision.
- Data augmentation for intent classification with off-the-shelf large language models. In Proceedings of the 4th Workshop on NLP for Conversational AI, pages 47–57, Dublin, Ireland. Association for Computational Linguistics.
- Cross-lingual transfer learning for multilingual task oriented dialog.
- MTSI-BERT: A session-aware knowledge-based conversational agent. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 717–725, Marseille, France. European Language Resources Association.
- On the robustness of intent classification and slot labeling in goal-oriented dialog systems to real-world noise. In EMNLP 2021 Workshop on NLP for Conversational AI.
- Gwenaelle Cunha Sergio and Minho Lee. 2021. Stacked DeBERT: All attention in incomplete data for text classification. Neural Networks, 136:87–96.
- Multi-task pre-training for plug-and-play task-oriented dialogue system. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4661–4676, Dublin, Ireland. Association for Computational Linguistics.
- Phoneme-bert: Joint language modelling of phoneme sequence and asr transcript.
- What is left to be understood in atis? In 2010 IEEE Spoken Language Technology Workshop, pages 19–24.
- Attention is all you need.
- Lighthubert: Lightweight and configurable speech representation learning with once-for-all hidden-unit bert.
- Incremental few-shot text classification with multi-round new classes: Formulation, dataset and system.
- End-to-end slot alignment and recognition for cross-lingual nlu.
- mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 483–498, Online. Association for Computational Linguistics.
- Unknown intent detection using Gaussian mixture model with an application to zero-shot intent classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1050–1060, Online. Association for Computational Linguistics.
- Xlnet: Generalized autoregressive pretraining for language understanding.
- Diverse few-shot text classification with multiple metrics. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1206–1215, New Orleans, Louisiana. Association for Computational Linguistics.
- Deep open intent classification with adaptive decision boundary.
- Few-shot intent detection via contrastive pre-training and fine-tuning. CoRR, abs/2109.06349.
- Are pretrained transformers robust in intent classification? a missing ingredient in evaluation of out-of-scope intent detection. The 4th Workshop on NLP for Conversational AI, ACL 2022.
- Few-shot intent detection via contrastive pre-training and fine-tuning. EMNLP.
- Discriminative nearest neighbor few-shot intent detection by transferring natural language inference. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5064–5082, Online. Association for Computational Linguistics.
- Cblue: A chinese biomedical language understanding evaluation benchmark.
- Learning dialogue representations from consecutive utterances. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 754–768, Seattle, United States. Association for Computational Linguistics.
- Catslu: The 1st chinese audio-textual spoken language understanding challenge. In 2019 International Conference on Multimodal Interaction, ICMI ’19, page 521–525, New York, NY, USA. Association for Computing Machinery.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
