Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Location Aware Modular Biencoder for Tourism Question Answering (2401.02187v1)

Published 4 Jan 2024 in cs.CL

Abstract: Answering real-world tourism questions that seek Point-of-Interest (POI) recommendations is challenging, as it requires both spatial and non-spatial reasoning, over a large candidate pool. The traditional method of encoding each pair of question and POI becomes inefficient when the number of candidates increases, making it infeasible for real-world applications. To overcome this, we propose treating the QA task as a dense vector retrieval problem, where we encode questions and POIs separately and retrieve the most relevant POIs for a question by utilizing embedding space similarity. We use pretrained LLMs (PLMs) to encode textual information, and train a location encoder to capture spatial information of POIs. Experiments on a real-world tourism QA dataset demonstrate that our approach is effective, efficient, and outperforms previous methods across all metrics. Enabled by the dense retrieval architecture, we further build a global evaluation baseline, expanding the search space by 20 times compared to previous work. We also explore several factors that impact on the model's performance through follow-up experiments. Our code and model are publicly available at https://github.com/haonan-li/LAMB.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Learning opinion summarizers by selecting informative reviews. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP).
  2. ELECTRA: pre-training text encoders as discriminators rather than generators. In Proceedings of the 8th International Conference on Learning Representations. OpenReview.net.
  3. Geotagging one hundred million twitter accounts with total variation minimization. In Proceedings of the 2014 IEEE International Conference on Big Data, pages 393–401. IEEE Computer Society.
  4. Joint spatio-textual reasoning for answering tourism questions. In Proceedings of the Web Conference 2021, pages 1978–1989.
  5. Answering poi-recommendation questions using tourism reviews. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management, pages 281–291. ACM.
  6. Personalized recommendation system based on collaborative filtering for IoT scenarios. IEEE Transactions on Services Computing, 13(4):685–695.
  7. Multi-step retriever-reader interaction for scalable open-domain question answering. In Proceedings of the 7th International Conference on Learning Representations. OpenReview.net.
  8. João Paulo Dias de Almeida and João B. Rocha-Junior. 2015. Top-k spatial keyword preference query. Journal of Information and Data Management, 6(3):162–177.
  9. 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.
  10. Personalized ranking metric embedding for next new POI recommendation. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, pages 2069–2075. AAAI Press.
  11. How smart is e-tourism? a systematic review of smart tourism recommendation system applying data management. Computer Science Review, 39:100337.
  12. Place questions and human-generated answers: A data analysis approach. In Proceedings of the 22nd AGILE Conference on Geographic Information Science, pages 3–19. Springer.
  13. Translating place-related questions to geosparql queries. In Proceedings of the ACM Web Conference 2022, pages 902–911. ACM.
  14. DeBERTa: decoding-enhanced Bert with disentangled attention. In Proceedings of the 9th International Conference on Learning Representations. OpenReview.net.
  15. Geographic adaptation of pretrained language models. arXiv preprint arXiv:2203.08565.
  16. GeoSQA: A benchmark for scenario-based question answering in the geography domain at high school level. 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 5866–5871, Hong Kong, China. Association for Computational Linguistics.
  17. GeoAI: Spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond. International Journal of Geographic Information Science, pages 625–636.
  18. Tinybert: Distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351.
  19. Billion-scale similarity search with GPUs. IEEE Trans. Big Data, 7(3):535–547.
  20. Geotxt: A scalable geoparsing system for unstructured text geolocation. Transactions in GIS, 23(1):118–136.
  21. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Online. Association for Computational Linguistics.
  22. Natural questions: A benchmark for question answering research. Transactions of the Association for Computational Linguistics, 7:452–466.
  23. Latent retrieval for weakly supervised open domain question answering. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6086–6096, Florence, Italy. Association for Computational Linguistics.
  24. 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.
  25. Neural factoid geospatial question answering. Journal of Spatial Information Science, 23:65–90.
  26. Efficient processing of location-aware group preference queries. In Proceedings of the 25th ACM International Conference on Information and Knowledge Management, pages 559–568. ACM.
  27. RoBERTa: A robustly optimized BERT pretraining approach. ArXiv preprint, abs/1907.11692.
  28. RSVQA: Visual question answering for remote sensing data. IEEE Transactions on Geoscience and Remote Sensing, 58(12):8555–8566.
  29. Geographic question answering: Challenges, uniqueness, classification, and future directions. AGILE: GIScience Series, 2:1–21.
  30. Location extraction from social media: Geoparsing, location disambiguation, and geotagging. ACM Transactions on Information Systems (TOIS), 36(4):1–27.
  31. Bhaskar Mitra and Nick Craswell. 2019. An updated duet model for passage re-ranking. ArXiv preprint, abs/1903.07666.
  32. Document expansion by query prediction. ArXiv preprint, abs/1904.08375.
  33. Template-based question answering over linked geospatial data. In Proceedings of the 12th Workshop on Geographic Information Retrieval, page 7.
  34. Geographic information retrieval: Progress and challenges in spatial search of text. Foundations and Trends in Information Retrieval, 12(2-3):164–318.
  35. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics.
  36. Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter. ArXiv preprint, abs/1910.01108.
  37. Geo-analytical question-answering with GIS. International Journal of Digital Earth, pages 1–14.
  38. Yves Scherrer and Nikola Ljubešić. 2021. Social media variety geolocation with GeoBERT. In Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects. The Association for Computational Linguistics.
  39. Bidirectional attention flow for machine comprehension. In Proceedings of the 5th International Conference on Learning Representations. OpenReview.net.
  40. Real-time open-domain question answering with dense-sparse phrase index. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4430–4441, Florence, Italy. Association for Computational Linguistics.
  41. MobileBERT: a compact task-agnostic bert for resource-limited devices. arXiv preprint arXiv:2004.02984.
  42. NeuroTPR: A neuro-net toponym recognition model for extracting locations from social media messages. Transactions in GIS, 24(3):719–735.
  43. MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems, 33:5776–5788.
  44. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45, Online. Association for Computational Linguistics.
  45. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In Proceedings of the 9th International Conference on Learning Representations. OpenReview.net.
  46. Progressively pretrained dense corpus index for open-domain question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2803–2815, Online. Association for Computational Linguistics.
  47. Extracting interrogative intents and concepts from geo-analytic questions. AGILE: GIScience Series, 1:23.
  48. XLNet: Generalized autoregressive pretraining for language understanding. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, pages 5754–5764.
  49. Incremental spatio-temporal graph learning for online query-poi matching. In Proceedings of the Web Conference 2021, pages 1586–1597. ACM / IW3C2.
  50. SG-Net: Syntax-guided machine reading comprehension. In Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, pages 9636–9643. AAAI Press.
  51. Incorporating semantic similarity with geographic correlation for query-poi relevance learning. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, pages 1270–1277. AAAI Press.
  52. Where to go next: A spatio-temporal gated network for next POI recommendation. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, pages 5877–5884. AAAI Press.

Summary

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

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

GitHub

  1. GitHub - haonan-li/LAMB: Location Aware Modular Biencoder (2 stars)