2 |
A Corpus-Based Sentence Classifier for Entity–Relationship Modelling
|
|
|
|
In: Electronics; Volume 11; Issue 6; Pages: 889 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
Multi-National Topics Maps for Parliamentary Debate Analysis
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Which data do elementary school teachers use to determine reading difficulties in their students?
|
|
|
|
In: Journal of learning disabilities 54 (2021) 5, S. 349-364 (2021)
|
|
BASE
|
|
Show details
|
|
5 |
Which data do elementary school teachers use to determine reading difficulties in their students? ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Finetuning Pretrained Transformers into Variational Autoencoders ...
|
|
|
|
Abstract:
Text variational autoencoders (VAEs) are notorious for posterior collapse, a phenomenon where the model's decoder learns to ignore signals from the encoder. Because posterior collapse is known to be exacerbated by expressive decoders, Transformers have seen limited adoption as components of text VAEs. Existing studies that incorporate Transformers into text VAEs (Li et al., 2020; Fang et al., 2021) mitigate posterior collapse using massive pretraining, a technique unavailable to most of the research community without extensive computing resources. We present a simple two-phase training scheme to convert a sequence-to-sequence Transformer into a VAE with just finetuning. The resulting language model is competitive with massively pretrained Transformer-based VAEs in some internal metrics while falling short on others. To facilitate training we comprehensively explore the impact of common posterior collapse alleviation techniques in the literature. We release our code for reproducability. ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing; Topic Modelling
|
|
URL: https://dx.doi.org/10.48448/k987-hs66 https://underline.io/lecture/39450-finetuning-pretrained-transformers-into-variational-autoencoders
|
|
BASE
|
|
Hide details
|
|
9 |
Temporal social network reconstruction using wireless proximity sensors: model selection and consequences
|
|
|
|
In: ISSN: 2193-1127 ; EISSN: 2193-1127 ; EPJ Data Science ; https://hal.inria.fr/hal-03117988 ; EPJ Data Science, EDP Sciences, 2020, 9 (1), ⟨10.1140/epjds/s13688-020-00237-8⟩ (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Inscriptions, Hieroglyphs, Linguistics… and Beyond! The Corpus of Classic Mayan as an Ontological Information Resource ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Inscriptions, Hieroglyphs, Linguistics… and Beyond! The Corpus of Classic Mayan as an Ontological Information Resource ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Using Bidirectional Encoder Representations from Transformers for Conversational Machine Comprehension ; Användning av BERT-språkmodell för konversationsförståelse
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Semantic modelling and publishing of traditional data collection questionnaires and answers
|
|
|
|
In: Abgaz, Yalemisew orcid:0000-0002-3887-5342 , Dorn, Amelie, Piringer, Barbara orcid:0000-0001-9983-1362 , Wandl-Vogt, Eveline orcid:0000-0002-0802-0255 and Way, Andy orcid:0000-0001-5736-5930 (2018) Semantic modelling and publishing of traditional data collection questionnaires and answers. Information, 9 (12). pp. 1-24. ISSN 2078-2489 (2018)
|
|
BASE
|
|
Show details
|
|
20 |
Unlocking cultural conceptualisation in indigenous language resources: collaborative computing methodologies
|
|
|
|
In: Dorn, Amelie, Wandl-Vogt, Eveline orcid:0000-0002-0802-0255 , Abgaz, Yalemisew orcid:0000-0002-3887-5342 , Benito Santos, Alejandro orcid:0000-0001-5317-6390 and Therón, Roberto orcid:0000-0001-6739-8875 (2018) Unlocking cultural conceptualisation in indigenous language resources: collaborative computing methodologies. In: 11th Language Resources and Evaluation Conference, 7-12 May 2018, Miyazaki, Japan. ISBN 979-10-95546-22-1 (2018)
|
|
BASE
|
|
Show details
|
|
|
|