21 |
HFL at SemEval-2022 Task 8: A Linguistics-inspired Regression Model with Data Augmentation for Multilingual News Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
22 |
A Systematic Evaluation of Large Language Models of Code ...
|
|
|
|
BASE
|
|
Show details
|
|
23 |
EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
24 |
SGL: Symbolic Goal Learning in a Hybrid, Modular Framework for Human Instruction Following ...
|
|
|
|
BASE
|
|
Show details
|
|
26 |
Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
27 |
GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Models ...
|
|
|
|
Abstract:
Deep learning (DL) techniques involving fine-tuning large numbers of model parameters have delivered impressive performance on the task of discriminating between language produced by cognitively healthy individuals, and those with Alzheimer's disease (AD). However, questions remain about their ability to generalize beyond the small reference sets that are publicly available for research. As an alternative to fitting model parameters directly, we propose a novel method by which a Transformer DL model (GPT-2) pre-trained on general English text is paired with an artificially degraded version of itself (GPT-D), to compute the ratio between these two models' \textit{perplexities} on language from cognitively healthy and impaired individuals. This technique approaches state-of-the-art performance on text data from a widely used "Cookie Theft" picture description task, and unlike established alternatives also generalizes well to spontaneous conversations. Furthermore, GPT-D generates text with characteristics ... : This paper has been accepted by ACL 2022 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2203.13397 https://arxiv.org/abs/2203.13397
|
|
BASE
|
|
Hide details
|
|
28 |
IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
30 |
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
31 |
Improving Lexical Embeddings for Robust Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
32 |
HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
34 |
An Unsupervised Masking Objective for Abstractive Multi-Document News Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
35 |
LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
36 |
MEduKG: A Deep-Learning-Based Approach for Multi-Modal Educational Knowledge Graph Construction
|
|
|
|
In: Information; Volume 13; Issue 2; Pages: 91 (2022)
|
|
BASE
|
|
Show details
|
|
37 |
Understanding Temporal Relations in Mandarin Chinese: An ERP Investigation
|
|
|
|
In: Brain Sciences; Volume 12; Issue 4; Pages: 474 (2022)
|
|
BASE
|
|
Show details
|
|
38 |
Computational Modelling of Tone Perception Based on Direct Processing of f0 Contours
|
|
|
|
In: Brain Sciences; Volume 12; Issue 3; Pages: 337 (2022)
|
|
BASE
|
|
Show details
|
|
39 |
Current Advancement in Diagnosing Atrial Fibrillation by Utilizing Wearable Devices and Artificial Intelligence: A Review Study
|
|
|
|
In: Diagnostics; Volume 12; Issue 3; Pages: 689 (2022)
|
|
BASE
|
|
Show details
|
|
40 |
S-NER: A Concise and Efficient Span-Based Model for Named Entity Recognition
|
|
|
|
In: Sensors; Volume 22; Issue 8; Pages: 2852 (2022)
|
|
BASE
|
|
Show details
|
|
|
|