• Refine your search:
  • 
    Keyword:
    
    • Computation and Language cs.CL (3)
    • FOS Computer and information sciences (3)
    • Computational Linguistics (2)
    • Condensed Matter Physics (1)
    • Deep Learning (1)
    • Electromagnetism (1)
    • FOS Physical sciences (1)
    • Information and Knowledge Engineering (1)
    • Machine Learning (1)
    • Machine Learning and Data Mining (1)
    •   more
  • 
    Creator / Publisher
  • 
    Year
  • 
    Medium
  • 
    Type
  • 
    BLLDB-Access:
    • free (11)
    • subject to license (0)

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 Hits 1 – 11 of 11 1 Learning How to Translate North Korean through South Korean ... Kim, Hwichan; Moon, Sangwhan; Okazaki, Naoaki. - : arXiv, 2022 BASE Show details 2 Joint Optimization of Tokenization and Downstream Model ... The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing 2021; Hiraoka, Tatsuya; Keyaki, Atsushi; Okazaki, Naoaki; Takase, Sho; Uchiumi, Kei. - : Underline Science Inc., 2021 Abstract: Read paper: https://www.aclanthology.org/2021.findings-acl.21 Abstract: Since traditional tokenizers are isolated from a downstream task and model, they cannot output an appropriate tokenization depending on the task and model, although recent studies imply that the appropriate tokenization improves the performance. In this paper, we propose a novel method to find an appropriate tokenization to a given downstream model by jointly optimizing a tokenizer and the model. The proposed method has no restriction except for using loss values computed by the downstream model to train the tokenizer, and thus, we can apply the proposed method to any NLP task. Moreover, the proposed method can be used to explore the appropriate tokenization for an already trained model as post-processing. Therefore, the proposed method is applicable to various situations. We evaluated whether our method contributes to improving performance on text classification in three languages and machine translation in eight language pairs. ... Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics URL: https://underline.io/lecture/26112-joint-optimization-of-tokenization-and-downstream-model https://dx.doi.org/10.48448/89v4-2x30 BASE Hide details 3 Multimodal pretraining unmasked: A meta-analysis and a unified framework of vision-and-language berts ... Bugliarello, Emanuele; Cotterell, Ryan; Okazaki, Naoaki. - : ETH Zurich, 2021 BASE Show details 4 Transformer-based Lexically Constrained Headline Generation ... Yamada, Kosuke; Hitomi, Yuta; Tamori, Hideaki. - : arXiv, 2021 BASE Show details 5 Multimodal pretraining unmasked: A meta-analysis and a unified framework of vision-and-language berts Okazaki, Naoaki; Bugliarello, Emanuele; Cotterell, Ryan... In: Transactions of the Association for Computational Linguistics, 9 (2021) BASE Show details 6 Transformer-based Lexically Constrained Headline Generation ... The 2021 Conference on Empirical Methods in Natural Language Processing 2021; Hitomi, Yuta; Inui, Kentaro. - : Underline Science Inc., 2021 BASE Show details 7 It’s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information ... Bugliarello, Emanuele; Mielke, Sabrina J.; Anastasopoulos, Antonios. - : ETH Zurich, 2020 BASE Show details 8 It’s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information Mielke, Sabrina J.; Okazaki, Naoaki; Anastasopoulos, Antonios... In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020) BASE Show details 9 The mechanism of additive composition [<Journal>] Tian, Ran [Verfasser]; Okazaki, Naoaki [Sonstige]; Inui, Kentaro [Sonstige] DNB Subject Category Language Show details 10 Other Topics You May Also Agree or Disagree: Modeling Inter-Topic Preferences using Tweets and Matrix Factorization ... Sasaki, Akira; Hanawa, Kazuaki; Okazaki, Naoaki. - : arXiv, 2017 BASE Show details 11 A preference learning approach to sentence ordering for multi-document summarization Bollegala, Danushka; Okazaki, Naoaki; Ishizuka, Mitsuru In: Information sciences. - New York, NY : Elsevier Science Inc. 217 (2012), 78-95 OLC Linguistik Show details

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 1 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 1 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 0 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 9 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0