• Refine your search:
  • 
    Keyword
  • 
    Creator / Publisher
  • 
    Year:
    
    • 2020 (600)
  • 
    Medium:
    
    • Online (600)
  • 
    Type:
    
    • Article (600)
  • 
    BLLDB-Access:
    • free (600)
    • 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 Page: 1 2 3 4 5...30 Hits 1 – 20 of 600 1 Priorless Recurrent Networks Learn Curiously ... The 28th International Conference on Computational Linguistics 2020; Bowers, Jeff; Mitchell, Jeff. - : Underline Science Inc., 2020 BASE Show details 2 Character Alignment in Morphologically Complex Translation Sets for Related Languages ... The 28th International Conference on Computational Linguistics 2020; Ephrem, Binyam; Gasser, Michael. - : Underline Science Inc., 2020 BASE Show details 3 Composing Byte-Pair Encodings for Morphological Sequence Classification ... The 28th International Conference on Computational Linguistics 2020; Bernardy, Jean-Philipe; Ek, Adam. - : Underline Science Inc., 2020 BASE Show details 4 Variation in Universal Dependencies annotation: A token based typological case study on adpossessive constructions ... The 28th International Conference on Computational Linguistics 2020; Haakama, Viljami; Sinnemäki, Kaius. - : Underline Science Inc., 2020 BASE Show details 5 Corpus evidence for word order freezing in Russian and German ... The 28th International Conference on Computational Linguistics 2020; Berdicevskis, Aleksandrs; Piperski, Alexander. - : Underline Science Inc., 2020 BASE Show details 6 An analysis of language models for metaphor recognition ... The 28th International Conference on Computational Linguistics 2020; Markert, Katja; Neidlein, Arthur. - : Underline Science Inc., 2020 BASE Show details 7 Noise Isn't Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models ... The 28th International Conference on Computational Linguistics 2020; Nicolai, Garrett; Silfverberg, Miikka. - : Underline Science Inc., 2020 BASE Show details 8 Exhaustive Entity Recognition for Coptic - Challenges and Solutions ... The 28th International Conference on Computational Linguistics 2020; Martin, Lance; Tu, Sichang. - : Underline Science Inc., 2020 BASE Show details 9 Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games ... The 28th International Conference on Computational Linguistics 2020; Bastianelli, Emanuele; Bisk, Yonatan. - : Underline Science Inc., 2020 BASE Show details 10 Attentively Embracing Noise for Robust Latent Representation in BERT ... The 28th International Conference on Computational Linguistics 2020; Cunha Sergio, Gwenaelle; Lee, Minho. - : Underline Science Inc., 2020 BASE Show details 11 Catching Attention with Automatic Pull Quote Selection ... The 28th International Conference on Computational Linguistics 2020; Bohn, Tanner. - : Underline Science Inc., 2020 BASE Show details 12 Opening Ceremony ... The 28th International Conference on Computational Linguistics 2020; Scott, Donia. - : Underline Science Inc., 2020 BASE Show details 13 Classifier Probes May Just Learn from Linear Context Features ... The 28th International Conference on Computational Linguistics 2020; Kuhlmann, Marco; Kunz, Jenny. - : Underline Science Inc., 2020 Abstract: "Classifiers trained on auxiliary probing tasks are a popular tool to analyze the representations learned by neural sentence encoders such as BERT and ELMo. While many authors are aware of the difficulty to distinguish between extracting the linguistic structure encoded in the representations'' andlearning the probing task,'' the validity of probing methods calls for further research. Using a neighboring word identity prediction task, we show that the token embeddings learned by neural sentence encoders contain a significant amount of information about the exact linear context of the token, and hypothesize that, with such information, learning standard probing tasks may be feasible even without additional linguistic structure. We develop this hypothesis into a framework in which analysis efforts can be scrutinized and argue that, with current models and baselines, conclusions that representations contain linguistic structure are not well-founded. Current probing methodology, such as restricting the ... Keyword: Computer and Information Science; Natural Language Processing; Neural Network URL: https://dx.doi.org/10.48448/ydk3-v029 https://underline.io/lecture/6288-classifier-probes-may-just-learn-from-linear-context-features BASE Hide details 14 Seeing the world through text: Evaluating image descriptions for commonsense reasoning in machine reading comprehension ... The 28th International Conference on Computational Linguistics 2020; Galvan-Sosa, Diana; Inui, Kentaro. - : Underline Science Inc., 2020 BASE Show details 15 Part 6 - Cross-linguistic Studies ... The 28th International Conference on Computational Linguistics 2020; ., Omri. - : Underline Science Inc., 2020 BASE Show details 16 Manifold Learning-based Word Representation Refinement Incorporating Global and Local Information ... The 28th International Conference on Computational Linguistics 2020; Chen, Jinjun; Li , Lin. - : Underline Science Inc., 2020 BASE Show details 17 HMSid and HMSid2 at PARSEME Shared Task 2020: Computational Corpus Linguistics and unseen-in-training MWEs ... The 28th International Conference on Computational Linguistics 2020; Colson, Jean-Pierre. - : Underline Science Inc., 2020 BASE Show details 18 Multi-dialect Arabic BERT for Country-level Dialect Identification ... The 28th International Conference on Computational Linguistics 2020; Ali, Mohammad; Al-Natsheh, Hussein. - : Underline Science Inc., 2020 BASE Show details 19 Autoencoding Improves Pre-trained Word Embeddings ... The 28th International Conference on Computational Linguistics 2020; Bollegala, Danushka; Kaneko, Masahiro. - : Underline Science Inc., 2020 BASE Show details 20 Exploring End-to-End Differentiable Natural Logic Modeling ... The 28th International Conference on Computational Linguistics 2020; Feng, Yufei; Greenspan, Michael. - : Underline Science Inc., 2020 BASE Show details Page: 1 2 3 4 5...30

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 0 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 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 600 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0