Hits 1.221 – 1.237 of 1.237
1221 |
UnNatural Language Inference ...
|
|
|
|
Abstract:
Read paper: https://www.aclanthology.org/2021.acl-long.569 Abstract: Recent investigations into the inner-workings of state-of-the-art large-scale pre-trained Transformer-based Natural Language Understanding (NLU) models indicate that they appear to understand human-like syntax, at least to some extent. We provide novel evidence that complicates this claim: we find that state-of-the-art Natural Language Inference (NLI) models assign the same labels to permuted examples as they do to the original, i.e. they are invariant to random word-order permutations. This behavior notably differs from that of humans; we struggle to understand the meaning of ungrammatical sentences. To measure the severity of this issue, we propose a suite of metrics and investigate which properties of particular permutations lead models to be word order invariant. For example, in MNLI dataset we find almost all (98.7%) examples contain at least one permutation which elicits the gold label. Models are even able to assign gold labels to ...
|
|
Keyword:
Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
|
|
URL: https://underline.io/lecture/25789-unnatural-language-inference https://dx.doi.org/10.48448/dv9d-6k56
|
|
BASE
|
|
Hide details
|
|
1222 |
Syntax-augmented Multilingual BERT for Cross-lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
1224 |
Dynamic and Multi-Channel Graph Convolutional Networks for Aspect-Based Sentiment Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
1225 |
Structured Sentiment Analysis as Dependency Graph Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
1226 |
Jointly Identifying Rhetoric and Implicit Emotions via Multi-Task Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
1228 |
Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
1229 |
Representing Syntax and Composition with Geometric Transformations ...
|
|
|
|
BASE
|
|
Show details
|
|
1231 |
Surprisal Estimators for Human Reading Times Need Character Models ...
|
|
|
|
BASE
|
|
Show details
|
|
1232 |
A Case Study of Analysis of Construals in Language on Social Media Surrounding a Crisis Event ...
|
|
|
|
BASE
|
|
Show details
|
|
1233 |
Psycholinguistic Tripartite Graph Network for Personality Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
1234 |
11B: Linguistic Theories, Cognitive Modeling and Psycholinguistics #1 ...
|
|
|
|
BASE
|
|
Show details
|
|
1235 |
How is BERT surprised? Layerwise detection of linguistic anomalies ...
|
|
|
|
BASE
|
|
Show details
|
|
1236 |
Catchphrase: Automatic Detection of Cultural References ...
|
|
|
|
BASE
|
|
Show details
|
|
1237 |
Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|