1 |
The Complex, Dynamic and Co-adaptive Relationship between Pronunciation Teachers’ Cognitions, Pedagogical Practices and Wider Contexts: A Case from Vietnamese Tertiary Education
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Giant Pigeon and Small Person: Prompting Visually Grounded Models about the Size of Objects ...
|
|
Zhang, Yi. - : Purdue University Graduate School, 2022
|
|
BASE
|
|
Show details
|
|
3 |
Giant Pigeon and Small Person: Prompting Visually Grounded Models about the Size of Objects ...
|
|
Zhang, Yi. - : Purdue University Graduate School, 2022
|
|
BASE
|
|
Show details
|
|
4 |
Towards a theoretical understanding of word and relation representation
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Knowledge Building with Low Proficiency English Language Learners: Facilitating Metalinguistic Awareness and Scientific Understanding in Parallel
|
|
|
|
BASE
|
|
Show details
|
|
7 |
nutsamaat uy’skwuluwun: Coast Salish pedagogy in higher education
|
|
|
|
BASE
|
|
Show details
|
|
8 |
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
|
|
9 |
A BDI Empathic Agent Model Based on a Multidimensional Cross-Cultural Emotion Representation
|
|
|
|
BASE
|
|
Show details
|
|
11 |
The Dragoman Renaissance: Diplomatic Interpreters and the Routes of Orientalism
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Story of a legal codex(t) : writing law in code ; L’histoire du codex(t) juridique : écrire le droit en code
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03618704 ; Droit. Institut d'études politiques de paris - Sciences Po, 2021. Français. ⟨NNT : 2021IEPP0041⟩ (2021)
|
|
BASE
|
|
Show details
|
|
13 |
Conceptual issues for the development of an ontological model : the case of the mining domain ; Enjeux conceptuels pour l'élaboration d'un modèle ontologique : le cas du domaine minier
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03501375 ; Sciences de l'information et de la communication. Université de Lille, 2021. Français (2021)
|
|
BASE
|
|
Show details
|
|
14 |
The diagnosis of listening in English as a foreign language, with a special focus on lexical knowledge ; Diagnostic et remédiation orientés vers le lexique en compréhension aurale de l’anglais
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03170753 ; Linguistique. Université Lyon 2 Lumière, 2021. Français (2021)
|
|
BASE
|
|
Show details
|
|
15 |
The diagnosis of listening in English as a foreign language, with a special focus on lexical knowledge ; Diagnostic et remédiation orientés vers le lexique en compréhension aurale de l'anglais
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03235381 ; Linguistique. Université de Lyon, 2021. Français. ⟨NNT : 2021LYSE2004⟩ (2021)
|
|
BASE
|
|
Show details
|
|
16 |
Text Generation with and without Retrieval ; Génération de textes basés sur la connaissance avec et sans recherche
|
|
|
|
In: https://hal.univ-lorraine.fr/tel-03542634 ; Computer Science [cs]. Université de Lorraine, 2021. English. ⟨NNT : 2021LORR0164⟩ (2021)
|
|
BASE
|
|
Show details
|
|
17 |
3D Serious Game Modeling and Design: Contributions to Language Learning ; Modélisation et Conception de jeu sérieux tridimensionnel : Contributions à l’apprentissage des langues
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03315793 ; Environnements Informatiques pour l'Apprentissage Humain. Université Ibn Tofail, Kénitra (Maroc), 2021. Français (2021)
|
|
BASE
|
|
Show details
|
|
18 |
Injecting Inductive Biases into Distributed Representations of Text ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Exploring Construction of a Company Domain-Specific Knowledge Graph from Financial Texts Using Hybrid Information Extraction
|
|
Jen, Chun-Heng. - : KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021
|
|
BASE
|
|
Show details
|
|
|
|