DE eng

Search in the Catalogues and Directories

Page: 1...59 60 61 62 63
Hits 1.241 – 1.255 of 1.255

1241
Dynamic and Multi-Channel Graph Convolutional Networks for Aspect-Based Sentiment Analysis ...
BASE
Show details
1242
Structured Sentiment Analysis as Dependency Graph Parsing ...
BASE
Show details
1243
Jointly Identifying Rhetoric and Implicit Emotions via Multi-Task Learning ...
BASE
Show details
1244
Recursive prosody is not finite-state ...
BASE
Show details
1245
Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing ...
BASE
Show details
1246
Representing Syntax and Composition with Geometric Transformations ...
BASE
Show details
1247
Lower Perplexity is Not Always Human-Like ...
BASE
Show details
1248
Surprisal Estimators for Human Reading Times Need Character Models ...
BASE
Show details
1249
A Case Study of Analysis of Construals in Language on Social Media Surrounding a Crisis Event ...
BASE
Show details
1250
Psycholinguistic Tripartite Graph Network for Personality Detection ...
BASE
Show details
1251
Can Transformer Langauge Models Predict Psychometric Properties? ...
BASE
Show details
1252
11B: Linguistic Theories, Cognitive Modeling and Psycholinguistics #1 ...
BASE
Show details
1253
How is BERT surprised? Layerwise detection of linguistic anomalies ...
Abstract: Read paper: https://www.aclanthology.org/2021.acl-long.325 Abstract: Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly. In this work, we use Gaussian models for density estimation at intermediate layers of three language models (BERT, RoBERTa, and XLNet), and evaluate our method on BLiMP, a grammaticality judgement benchmark. In lower layers, surprisal is highly correlated to low token frequency, but this correlation diminishes in upper layers. Next, we gather datasets of morphosyntactic, semantic, and commonsense anomalies from psycholinguistic studies; we find that the best performing model RoBERTa exhibits surprisal in earlier layers when the anomaly is morphosyntactic than when it is semantic, while commonsense anomalies do not exhibit surprisal at any intermediate layer. These results suggest that language models employ separate mechanisms to detect different types of ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
URL: https://dx.doi.org/10.48448/455f-ep51
https://underline.io/lecture/26030-how-is-bert-surprisedquestion-layerwise-detection-of-linguistic-anomalies
BASE
Hide details
1254
Catchphrase: Automatic Detection of Cultural References ...
BASE
Show details
1255
Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study ...
BASE
Show details

Page: 1...59 60 61 62 63

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
1.255
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern