{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T04:10:29Z","timestamp":1743826229693,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031887079","type":"print"},{"value":"9783031887086","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-88708-6_18","type":"book-chapter","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T11:51:10Z","timestamp":1743767470000},"page":"276-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LSTM-Based Selective Dense Text Retrieval Guided by\u00a0Sparse Lexical Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6454-5796","authenticated-orcid":false,"given":"Yingrui","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-5088","authenticated-orcid":false,"given":"Parker","family":"Carlson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5717-2637","authenticated-orcid":false,"given":"Yifan","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7870-3100","authenticated-orcid":false,"given":"Wentai","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8581-6733","authenticated-orcid":false,"given":"Shanxiu","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1902-3387","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Altingovde, I.S., Demir, E., Can, F., Ulusoy, O.: Incremental cluster-based retrieval using compressed cluster-skipping inverted files. ACM Trans. Inf. Syst. 26(3) (2008). https:\/\/doi.org\/10.1145\/1361684.1361688","DOI":"10.1145\/1361684.1361688"},{"key":"18_CR2","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems. vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"18_CR3","unstructured":"Campos, D.F., et al.: MS MARCO: A human generated machine reading comprehension dataset. NIPS (2016)"},{"key":"18_CR4","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1016\/S0306-4379(03)00062-0","volume":"29","author":"F Can","year":"2004","unstructured":"Can, F., Alting\u00f6vde, I.S., Demir, E.: Efficiency and effectiveness of query processing in cluster-based retrieval. Inf. Syst. 29, 697\u2013717 (2004)","journal-title":"Inf. Syst."},{"key":"18_CR5","unstructured":"Chen, Q., et al.: SPANN: Highly-efficient billion-scale approximate nearest neighborhood search. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=-1rrzmJCp4"},{"key":"18_CR6","unstructured":"Cheriton, D.R.: From doc2query to docTTTTTquery (2019). https:\/\/api.semanticscholar.org\/CorpusID:208612557"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Craswell, N., Mitra, B., Yilmaz, E., Campos, D.F., Voorhees, E.M.: Overview of the TREC 2020 deep learning track. ArXiv abs\/2102.07662 (2020)","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Dai, Z., Callan, J.: Context-aware term weighting for first stage passage retrieval. SIGIR (2020)","DOI":"10.1145\/3397271.3401204"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Formal, T., Lassance, C., Piwowarski, B., Clinchant, S.: From distillation to hard negative sampling: Making sparse neural IR models more effective. Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (2022)","DOI":"10.1145\/3477495.3531857"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Formal, T., Piwowarski, B., Clinchant, S.: SPLADE: Sparse lexical and expansion model for first stage ranking. SIGIR (2021)","DOI":"10.1145\/3404835.3463098"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Gao, L., Dai, Z., Callan, J.: COIL: revisit exact lexical match in information retrieval with contextualized inverted list. NAACL (2021)","DOI":"10.18653\/v1\/2021.naacl-main.241"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Gao, L., Dai, Z., Fan, Z., Callan, J.: Complementing lexical retrieval with semantic residual embedding. ECIR abs\/2004.13969 (2021)","DOI":"10.1007\/978-3-030-72113-8_10"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Ge, T., He, K., Ke, Q., Sun, J.: Optimized product quantization for approximate nearest neighbor search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)","DOI":"10.1109\/CVPR.2013.379"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Gollapudi, S., et al.: Filtered-diskANN: graph algorithms for approximate nearest neighbor search with filters. In: Proceedings of the ACM Web Conference 2023, pp. 3406\u20133416. WWW \u201923, ACM, New York, NY, USA (2023)","DOI":"10.1145\/3543507.3583552"},{"key":"18_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1007\/978-3-319-56608-5_69","volume-title":"Advances in Information Retrieval","author":"F Hafizoglu","year":"2017","unstructured":"Hafizoglu, F., Kucukoglu, E.C., Altingovde, I.S.: On the efficiency of selective search. In: Jose, J.M., et al. (eds.) ECIR 2017. LNCS, vol. 10193, pp. 705\u2013712. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-56608-5_69"},{"issue":"8","key":"18_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"18_CR17","unstructured":"Jayaram\u00a0Subramanya, S., Devvrit, F., Simhadri, H.V., Krishnawamy, R., Kadekodi, R.: DiskANN: fast accurate billion-point nearest neighbor search on a single node. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol.\u00a032. Curran Associates, Inc. (2019). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/09853c7fb1d3f8ee67a61b6bf4a7f8e6-Paper.pdf"},{"issue":"3","key":"18_CR18","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. EMNLP\u20192020 ArXiv abs\/2010.08191 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Kulkarni, H., MacAvaney, S., Goharian, N., Frieder, O.: Lexically-accelerated dense retrieval. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 152\u2013162. SIGIR \u201923, Association for Computing Machinery, New York, NY, USA (2023)","DOI":"10.1145\/3539618.3591715"},{"key":"18_CR21","unstructured":"Kuzi, S., Zhang, M., Li, C., Bendersky, M., Najork, M.: Leveraging semantic and lexical matching to improve the recall of document retrieval systems: A hybrid approach. arXiv preprint arXiv:2010.01195 (2020)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Lassance, C., Clinchant, S.: An efficiency study for splade models. SIGIR (2022)","DOI":"10.1145\/3477495.3531833"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Lewis, P., O\u011fuz, B., Xiong, W., Petroni, F., tau Yih, W., Riedel, S.: Boosted dense retriever. Proceedings of NAACL, pp. 3102\u20133117 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.226"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: To interpolate or not to interpolate: PRF, dense and sparse retrievers. SIGIR (2022)","DOI":"10.1145\/3477495.3531884"},{"key":"18_CR25","unstructured":"Lin, J.J., Ma, X.: A few brief notes on Deepimpact, COIL, and a conceptual framework for information retrieval techniques. ArXiv abs\/2106.14807 (2021)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Xiao, S., Shao, Y., Cao, Z.: RetroMAE-2: duplex masked auto-encoder for pre-training retrieval-oriented language models. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2635\u20132648. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.acl-long.148"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, L., Yang, N., Wei, F., Lin, J.: Fine-tuning llama for multi-stage text retrieval (2023)","DOI":"10.1145\/3626772.3657951"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"MacAvaney, S., Tonellotto, N., Macdonald, C.: Adaptive re-ranking with a corpus graph. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 1491\u20131500. CIKM \u201922, Association for Computing Machinery, New York, NY, USA (2022)","DOI":"10.1145\/3511808.3557231"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Malkov, Y.A., Yashunin, D.A.: Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 824-836 (2020)","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Mallia, A., Khattab, O., Tonellotto, N., Suel, T.: Learning passage impacts for inverted indexes. SIGIR (2021)","DOI":"10.1145\/3404835.3463030"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Mallia, A., Mackenzie, J., Suel, T., Tonellotto, N.: Faster learned sparse retrieval with guided traversal. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1901\u20131905 (2022)","DOI":"10.1145\/3477495.3531774"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Yang, Y., He, S., Yang, T.: Representation sparsification with hybrid thresholding for fast SPLADE-based document retrieval. ACM SIGIR\u201923 (2023)","DOI":"10.1145\/3539618.3592051"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Yang, Y., Lin, H., Yang, T.: Optimizing guided traversal for fast learned sparse retrieval. In: Proceedings of the ACM Web Conference 2023, pp. 3375\u20133385 (2023)","DOI":"10.1145\/3543507.3583497"},{"key":"18_CR34","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"SE Robertson","year":"2009","unstructured":"Robertson, S.E., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retr. 3, 333\u2013389 (2009)","journal-title":"Found. Trends Inf. Retr."},{"key":"18_CR35","unstructured":"Shen, T., et al.: LexMAE: Lexicon-bottlenecked pretraining for large-scale retrieval. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=PfpEtB3-csK"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Tan, S., Xu, Z., Zhao, W., Fei, H., Zhou, Z., Li, P.: Norm adjusted proximity graph for fast inner product retrieval. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1552\u20131560. KDD \u201921, Association for Computing Machinery, New York, NY, USA (2021)","DOI":"10.1145\/3447548.3467412"},{"key":"18_CR37","unstructured":"Thakur, N., Reimers, N., R\u00fcckl\u00e9, A., Srivastava, A., Gurevych, I.: BEIR: a heterogeneous benchmark for zero-shot evaluation of information retrieval models. In: NeurIPS (2021)"},{"key":"18_CR38","unstructured":"Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models (2023)"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: SimLM: Pre-training with representation bottleneck for dense passage retrieval. ACL (2023)","DOI":"10.18653\/v1\/2023.acl-long.125"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Xiao, S., et al.: Distill-VQ: learning retrieval oriented vector quantization by distilling knowledge from dense embeddings. SIGIR (2022)","DOI":"10.1145\/3477495.3531799"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Shao, Y., Cao, Z.: RetroMAE: pre-training retrieval-oriented transformers via masked auto-encoder. EMNLP (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Y., Carlson, P., He, S., Qiao, Y., Yang, T.: Cluster-based partial dense retrieval fused with sparse text retrieval. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2327\u20132331. SIGIR \u201924, ACM, New York, NY, USA (2024)","DOI":"10.1145\/3626772.3657972"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., Ma, S.: Jointly optimizing query encoder and product quantization to improve retrieval performance. CIKM (2021)","DOI":"10.1145\/3459637.3482358"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88708-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T11:51:38Z","timestamp":1743767498000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88708-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031887079","9783031887086"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88708-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lucca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2025.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}