• Refine your search:
  • 
    Keyword:
    
    • Computation and Language cs.CL (6)
    • FOS Computer and information sciences (6)
    • natural language processing (4)
    • NLP (3)
    • ALGORITHMS (2)
    • Parsing (2)
    • morphemes (2)
    • morphology (2)
    • neural networks (2)
    • *DECODING (1)
    •   more
  • 
    Creator / Publisher:
    
    • Lopez, Adam (31)
    • Fancellu, Federico (5)
    • Callison-Burch, Chris (4)
    • Engineering and Physical Sciences Research Council (EPSRC) (4)
    • Goldwater, Sharon (4)
    • Lapata, Maria (4)
    • Webber, Bonnie (4)
    • Koehn, Philipp (3)
    • Post, Matt (3)
    • other (3)
    •   more
  • 
    Year
  • 
    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 31 1 Data-to-text generation with neural planning Puduppully, Ratish Surendran. - : The University of Edinburgh, 2022 BASE Show details 2 Intrinsic Bias Metrics Do Not Correlate with Application Bias ... 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; Goldfarb-Tarrant, Seraphina; Lopez, Adam. - : Underline Science Inc., 2021 BASE Show details 3 Training dynamics of neural language models Saphra, Naomi. - : The University of Edinburgh, 2021 Abstract: Why do artificial neural networks model language so well? We claim that in order to answer this question and understand the biases that lead to such high performing language models---and all models that handle language---we must analyze the training process. For decades, linguists have used the tools of developmental linguistics to study human bias towards linguistic structure. Similarly, we wish to consider a neural network's training dynamics, i.e., the analysis of training in practice and the study of why our optimization methods work when applied. This framing shows us how structural patterns and linguistic properties are gradually built up, revealing more about why LSTM models learn so effectively on language data. To explore these questions, we might be tempted to appropriate methods from developmental linguistics, but we do not wish to make cognitive claims, so we avoid analogizing between human and artificial language learners. We instead use mathematical tools designed for investigating language model training dynamics. These tools can take advantage of crucial differences between child development and model training: we have access to activations, weights, and gradients in a learning model, and can manipulate learning behavior directly or by perturbing inputs. While most research in training dynamics has focused on vision tasks, language offers direct annotation of its well-documented and intuitive latent hierarchical structures (e.g., syntax and semantics) and is therefore an ideal domain for exploring the effect of training dynamics on the representation of such structure. Focusing on LSTM models, we investigate the natural sparsity of gradients and activations, finding that word representations are focused on just a few neurons late in training. Similarity analysis reveals how word embeddings learned for different tasks are highly similar at the beginning of training, but gradually become task-specific. Using synthetic data and measuring feature interactions, we also discover that hierarchical representations in LSTMs may be a result of their learning strategy: they tend to build new trees out of familiar phrases, by mingling together the meaning of constituents so they depend on each other. These discoveries constitute just a few possible explanations for how LSTMs learn generalized language representations, with further theories on more architectures to be uncovered by the growing field of NLP training dynamics. Keyword: interpretability; NLP; training dynamics URL: https://hdl.handle.net/1842/38154 BASE Hide details 4 Inflecting when there's no majority: Limitations of encoder-decoder neural networks as cognitive models for German plurals ... McCurdy, Kate; Goldwater, Sharon; Lopez, Adam. - : arXiv, 2020 BASE Show details 5 Understanding and generating language with abstract meaning representation Damonte, Marco. - : The University of Edinburgh, 2020 BASE Show details 6 On understanding character-level models for representing morphology Vania, Clara. - : The University of Edinburgh, 2020 BASE Show details 7 Methods for morphology learning in low(er)-resource scenarios Bergmanis, Toms. - : The University of Edinburgh, 2020 BASE Show details 8 Modelling speaker adaptation in second language learner dialogue Sinclair, Arabella Jane. - : The University of Edinburgh, 2020 BASE Show details 9 Semantic Graph Parsing with Recurrent Neural Network DAG Grammars ... Fancellu, Federico; Gilroy, Sorcha; Lopez, Adam. - : arXiv, 2019 BASE Show details 10 Lifecycle of neural semantic parsing Cheng, Jianpeng. - : The University of Edinburgh, 2019 BASE Show details 11 Fast machine translation on parallel and massively parallel hardware Bogoychev, Nikolay Veselinov. - : The University of Edinburgh, 2019 BASE Show details 12 Learning natural language interfaces with neural models Dong, Li. - : The University of Edinburgh, 2019 BASE Show details 13 Probabilistic graph formalisms for meaning representations Gilroy, Sorcha. - : The University of Edinburgh, 2019 BASE Show details 14 Low-resource speech translation Bansal, Sameer. - : The University of Edinburgh, 2019 BASE Show details 15 Indicatements that character language models learn English morpho-syntactic units and regularities ... Kementchedjhieva, Yova; Lopez, Adam. - : arXiv, 2018 BASE Show details 16 Neural Networks for Cross-lingual Negation Scope Detection ... Fancellu, Federico; Lopez, Adam; Webber, Bonnie. - : arXiv, 2018 BASE Show details 17 Understanding Learning Dynamics Of Language Models with SVCCA ... Saphra, Naomi; Lopez, Adam. - : arXiv, 2018 BASE Show details 18 Entity-based coherence in statistical machine translation: a modelling and evaluation perspective Wetzel, Dominikus Emanuel. - : The University of Edinburgh, 2018 BASE Show details 19 Computational models for multilingual negation scope detection Fancellu, Federico. - : The University of Edinburgh, 2018 BASE Show details 20 CoNLL 2017 Shared Task System Outputs Zeman, Daniel; Potthast, Martin; Straka, Milan. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2017 BASE Show details Page: 1 2

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 2 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 2 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 28 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0