Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
117 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Open-Domain Topic Classification (2306.17290v1)

Published 29 Jun 2023 in cs.CL

Abstract: We introduce an open-domain topic classification system that accepts user-defined taxonomy in real time. Users will be able to classify a text snippet with respect to any candidate labels they want, and get instant response from our web interface. To obtain such flexibility, we build the backend model in a zero-shot way. By training on a new dataset constructed from Wikipedia, our label-aware text classifier can effectively utilize implicit knowledge in the pretrained LLM to handle labels it has never seen before. We evaluate our model across four datasets from various domains with different label sets. Experiments show that the model significantly improves over existing zero-shot baselines in open-domain scenarios, and performs competitively with weakly-supervised models trained on in-domain data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. Importance of Semantic Representation: Dataless Classification. In Proceedings of the National Conference on Artificial Intelligence (AAAI).
  2. NATCAT: Weakly supervised text classification with naturally annotated resources. In 3rd Conference on Automated Knowledge Base Construction.
  3. The pascal recognising textual entailment challenge. In Proceedings of PASCAL first Workshop on Recognising Textual Entailment.
  4. Recognizing Textual Entailment: Models and Applications.
  5. 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.
  6. E. Gabrilovich and S. Markovitch. 2007. Computing semantic relatedness using wikipeida-based explicit semantic analysis. In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI).
  7. Ken Lang. 1995. NewsWeeder: learning to filter netnews. In Proc. of the International Conference on Machine Learning (ICML).
  8. Dbpedia - A large-scale, multilingual knowledge base extracted from wikipedia. Semantic Web, 6(2):167–195.
  9. 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.
  10. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net.
  11. University of Pennsylvania LoReHLT 2019 Submission. Technical report.
  12. Dheeraj Mekala and Jingbo Shang. 2020. Contextualized weak supervision for text classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 323–333, Online. Association for Computational Linguistics.
  13. Text classification using label names only: A language model self-training approach. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9006–9017, Online. Association for Computational Linguistics.
  14. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States.
  15. All-in text: Learning document, label, and word representations jointly. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, Arizona, USA, pages 1948–1954. AAAI Press.
  16. Pushpankar Kumar Pushp and Muktabh Mayank Srivastava. 2017. Train once, test anywhere: Zero-shot learning for text classification. CoRR, abs/1712.05972.
  17. Anthony Rios and Ramakanth Kavuluru. 2018. Few-shot and zero-shot multi-label learning for structured label spaces. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3132–3142, Brussels, Belgium. Association for Computational Linguistics.
  18. Yangqiu Song and Dan Roth. 2014. On Dataless Hierarchical Text Classification. In Proceedings of the National Conference on Artificial Intelligence (AAAI).
  19. Cross-lingual Dataless Classification for Many Languages. In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI).
  20. Document modeling with gated recurrent neural network for sentiment classification. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1422–1432, Lisbon, Portugal. Association for Computational Linguistics.
  21. FEVER: a large-scale dataset for fact extraction and VERification. 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 809–819, New Orleans, Louisiana. Association for Computational Linguistics.
  22. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net.
  23. Sida Wang and Christopher Manning. 2012. Baselines and bigrams: Simple, good sentiment and topic classification. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 90–94, Jeju Island, Korea. Association for Computational Linguistics.
  24. A broad-coverage challenge corpus for sentence understanding through inference. 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 1112–1122, New Orleans, Louisiana. Association for Computational Linguistics.
  25. Zero-shot user intent detection via capsule neural networks. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3090–3099, Brussels, Belgium. Association for Computational Linguistics.
  26. Hierarchical attention networks for document classification. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1480–1489, San Diego, California. Association for Computational Linguistics.
  27. Benchmarking Zero-shot Text Classification: Datasets, Evaluation, and Entailment Approach. In Proc. of the Conference on Empirical Methods for Natural Language Processing (EMNLP).
  28. Integrating semantic knowledge to tackle zero-shot text classification. 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 1031–1040, Minneapolis, Minnesota. Association for Computational Linguistics.
  29. Character-level convolutional networks for text classification. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, pages 649–657.
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now