Page: 1... 3 4 5 6 7 8 9 10 11... 373
| 121 |
Der Konjunktiv II in den ruralen Basisdialekten Österreichs.
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 122 |
Konjunktiv II-Variation im urbanen Sprachgebrauch in Österreich
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 123 |
Der Konjunktiv II in Salzburger Varietäten: Grammatik, Gebrauch, soziale Faktoren
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 124 |
Informationen zu den Beitragenden/Information about the authors
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 125 |
„Frische Brot, lecker Brot, taze Brot“ – Eigene Muster in der Adjektivverwendung auf einem mehrsprachigen Wochenmarkt
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 126 |
Ein Modell zur systematischen Erfassung genuenischer Phraseme in Wörterbüchern, illustriert am Beispiel der Forschungsprojekte GEPHRAS und GEPHRAS2
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 127 |
The development of the Old High German umlauted vowels and the reflex of New High German /ɛ:/ in Present Standard German
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 128 |
Informationen zu den Beitragenden/Information about the authors
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 129 |
Examining graphemic and lexical anglicisms in Twi for academic purposes in textbooks written in Twi
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 130 |
Formulaic Expressions for Foreign Language Learning and Teaching
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 131 |
The Chinese Messaging Application WeChat as Used by German Speakers in China
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 132 |
Geschlechtsübergreifende Personenbezeichnungen in wissenschaftlichen Zeitschriftenartikeln
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 133 |
Agent Demotion in German and Polish
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 134 |
Informationen zu den Beitragenden/Information about the authors
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 135 |
Fraseologia dell’algherese: risorse e nuovi impulsi per la fraseografia e la fraseodidattica di una varietà linguistica minoritaria italiana
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 136 |
Informationen zu den Beitragenden/Information about the authors
|
|
|
|
In: Linguistik Online, Vol 112, Iss 7 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 137 |
Humour et création lexicale dans le discours révolutionnaire du Hirak algérien
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 138 |
Neural-based Knowledge Transfer in Natural Language Processing
|
|
|
|
Abstract:
In Natural Language Processing (NLP), neural-based knowledge transfer, which is to transfer out-of-domain (OOD) knowledge to task-specific neural networks, has been applied to many NLP tasks. To further explore neural-based knowledge transfer in NLP, in this dissertation, we consider both structured OOD knowledge and unstructured OOD knowledge, and deal with several representative NLP tasks. For structured OOD knowledge, we study the neural-based knowledge transfer in Machine Reading Comprehension (MRC). In single-passage MRC tasks, to bridge the gap between MRC models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, we integrate the neural networks of MRC models with the general knowledge of human beings embodied in knowledge bases. On the one hand, we propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. On the other hand, we propose a novel MRC model named Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms. According to the experimental results, KAR is comparable in performance with the state-of-the-art MRC models, and significantly more robust to noise than them. On top of that, when only a subset (20%-80%) of the training examples are available, KAR outperforms the state-of-the-art MRC models by a large margin, and is still reasonably robust to noise. In multi-hop MRC tasks, to probe the strength of Graph Neural Networks (GNNs), we propose a novel multi-hop MRC model named Graph Aided Reader (GAR), which uses GNN methods to perform multi-hop reasoning, but is free of any pre-trained language model and completely end-to-end. For graph construction, GAR utilizes the topic-referencing relations between passages and the entity-sharing relations between sentences, which is aimed at obtaining the most sensible reasoning clues. For message passing, GAR simulates a top-down reasoning and a bottom-up reasoning, which is aimed at making the best use of the above obtained reasoning clues. According to the experimental results, GAR even outperforms several competitors relying on pre-trained language models and filter-reader pipelines, which implies that GAR benefits a lot from its GNN methods. On this basis, GAR can further benefit from applying pre-trained language models, but pre-trained language models can mainly facilitate the within-passage reasoning rather than cross-passage reasoning of GAR. Moreover, compared with the competitors constructed as filter-reader pipelines, GAR is not only easier to train, but also more applicable to the low-resource cases. For unstructured OOD knowledge, we study the neural-based knowledge transfer in Natural Language Understanding (NLU), and focus on the neural-based knowledge transfer between languages, which is also known as Cross-Lingual Transfer Learning (CLTL). To facilitate the CLTL of NLU models, especially the CLTL between distant languages, we propose a novel CLTL model named Translation Aided Language Learner (TALL), where CLTL is integrated with Machine Translation (MT). Specifically, we adopt a pre-trained multilingual language model as our baseline model, and construct TALL by appending a decoder to it. On this basis, we directly fine-tune the baseline model as an NLU model to conduct CLTL, but put TALL through an MT-oriented pre-training before its NLU-oriented fine-tuning. To make use of unannotated data, we implement the recently proposed Unsupervised Machine Translation (UMT) technique in the MT-oriented pre-training of TALL. According to the experimental results, the application of UMT enables TALL to consistently achieve better CLTL performance than the baseline model without using more annotated data, and the performance gain is relatively prominent in the case of distant languages.
|
|
Keyword:
Cross-lingual transfer learning; Graph neural network; Information technology; Knowledge base; Knowledge graph; Knowledge transfer; Machine Reading Comprehension; Multi-hop reasoning; Natural Language Processing; Natural language understanding; Neural network; unsupervised machine translation
|
|
URL: http://hdl.handle.net/10315/39096
|
|
BASE
|
|
Hide details
|
|
|
| 139 |
A Multi-Level Optimization Framework for End-to-End Text Augmentation
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 343-358 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
| 140 |
Czech Grammar Error Correction with a Large and Diverse Corpus
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 452-467 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
Page: 1... 3 4 5 6 7 8 9 10 11... 373 |
|
