• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher
  • 
    Year:
    
    • 2022 (1)
    • 2021 (2)
    • 2019 (6)
    • 2018 (2)
    • 2017 (1)
    • 2013 (1)
    • 2012 (1)
    • 2009 (2)
    • 2007 (4)
    • 2006 (2)
    •   more
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Page: 1 2 Hits 1 – 20 of 27 1 Towards Best Practices for Training Multilingual Dense Retrieval Models ... Zhang, Xinyu; Ogueji, Kelechi; Ma, Xueguang. - : arXiv, 2022 BASE Show details 2 Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval ... Zhang, Xinyu; Ma, Xueguang; Shi, Peng. - : arXiv, 2021 BASE Show details 3 Sparsifying Sparse Representations for Passage Retrieval by Top-$k$ Masking ... Yang, Jheng-Hong; Ma, Xueguang; Lin, Jimmy. - : arXiv, 2021 BASE Show details 4 Cross-Lingual Relevance Transfer for Document Retrieval ... Shi, Peng; Lin, Jimmy. - : arXiv, 2019 BASE Show details 5 Aligning Cross-Lingual Entities with Multi-Aspect Information ... Yang, Hsiu-Wei; Zou, Yanyan; Shi, Peng. - : arXiv, 2019 BASE Show details 6 End-to-End Open-Domain Question Answering with BERTserini ... Yang, Wei; Xie, Yuqing; Lin, Aileen. - : arXiv, 2019 BASE Show details 7 What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning ... Lee, Jaejun; Tang, Raphael; Lin, Jimmy. - : arXiv, 2019 Abstract: Pretrained transformer-based language models have achieved state of the art across countless tasks in natural language processing. These models are highly expressive, comprising at least a hundred million parameters and a dozen layers. Recent evidence suggests that only a few of the final layers need to be fine-tuned for high quality on downstream tasks. Naturally, a subsequent research question is, "how many of the last layers do we need to fine-tune?" In this paper, we precisely answer this question. We examine two recent pretrained language models, BERT and RoBERTa, across standard tasks in textual entailment, semantic similarity, sentiment analysis, and linguistic acceptability. We vary the number of final layers that are fine-tuned, then study the resulting change in task-specific effectiveness. We show that only a fourth of the final layers need to be fine-tuned to achieve 90% of the original quality. Surprisingly, we also find that fine-tuning all layers does not always help. ... : 5 pages ... Keyword: Computation and Language cs.CL; FOS Computer and information sciences URL: https://arxiv.org/abs/1911.03090 https://dx.doi.org/10.48550/arxiv.1911.03090 BASE Hide details 8 Simple BERT Models for Relation Extraction and Semantic Role Labeling ... Shi, Peng; Lin, Jimmy. - : arXiv, 2019 BASE Show details 9 Lucene for Approximate Nearest-Neighbors Search on Arbitrary Dense Vectors ... Teofili, Tommaso; Lin, Jimmy. - : arXiv, 2019 BASE Show details 10 Simple Attention-Based Representation Learning for Ranking Short Social Media Posts ... Shi, Peng; Rao, Jinfeng; Lin, Jimmy. - : arXiv, 2018 BASE Show details 11 ARCHITECTURE, MODELS, AND ALGORITHMS FOR TEXTUAL SIMILARITY He, Hua. - 2018 BASE Show details 12 Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams ... Rao, Jinfeng; He, Hua; Zhang, Haotian. - : arXiv, 2017 BASE Show details 13 Searching to Translate and Translating to Search: When Information Retrieval Meets Machine Translation Ture, Ferhan. - 2013 BASE Show details 14 Frontiers, Challenges, and Opportunities for Information Retrieval – Report from SWIRL 2012, The Second Strategic Workshop on Information Retrieval in Lorne Kelly, Diane; Clarke, Charles L.A.; Moffat, Alistair. - : KTH, Teoretisk datalogi, TCS, 2012. : ACM, 2012 BASE Show details 15 A cost-effective lexical acquisition process for large-scale thesaurus translation Lin, Jimmy; Murray, G. Craig; Dorr, Bonnie Jean... In: Language resources and evaluation. - Dordrecht [u.a.] : Springer 43 (2009) 1, 27-40 BLLDB Show details 16 COMPUTATIONAL ANALYSIS OF THE CONVERSATIONAL DYNAMICS OF THE UNITED STATES SUPREME COURT Hawes, Timothy. - 2009 BASE Show details 17 Special section on question answering in restricted domains Vicedo, José Luis; Scott, Donia; Power, Richard... In: Computational linguistics. - Cambridge, Mass. : MIT Press 33 (2007) 1, 41-133 BLLDB OLC Linguistik Show details 18 Answering Clinical Questions with Knowledge-Based and Statistical Techniques Demner-Fushman, Dina; Lin, Jimmy In: Computational linguistics. - Cambridge, Mass. : MIT Press 33 (2007) 1, 63 OLC Linguistik Show details 19 Syntactic sentence compression in the biomedical domain: facilitating access to related articles Lin, Jimmy; Wilbur, W. John In: Information Retrieval Journal. - Dordrecht [u.a.] : Springer Science + Business Media B.V. 10 (2007) 4-5, 393-414 BLLDB Show details 20 Multiple Alternative Sentene Compressions as a Tool for Automatic Summarization Tasks Zajic, David Michael. - 2007 BASE Show details Page: 1 2

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 4 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 5 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 20 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0