DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 29

1
Can computers tell a story? Discourse Structure in Computer-generated Text and Humans
In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol 43, iss 43 (2021)
BASE
Show details
2
The Anatomy of Discourse: Linguistic Predictors of Narrative and Argument Quality
In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol 43, iss 43 (2021)
BASE
Show details
3
The Anatomy of Discourse: Linguistic Predictors of Narrative and Argument Quality Motivation ...
BASE
Show details
4
Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering ...
BASE
Show details
5
AND does not mean OR: Using Formal Languages to Study Language Models’ Representations ...
BASE
Show details
6
Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering ...
BASE
Show details
7
AND does not mean OR: Using Formal Languages to Study Language Models’ Representations ...
BASE
Show details
8
AND does not mean OR: Using Formal Languages to Study Language Models’ Representations ...
BASE
Show details
9
AND does not mean OR: Using Formal Languages to Study Language Models’ Representations ...
BASE
Show details
10
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color ...
BASE
Show details
11
The Anatomy of Discourse: Linguistic Predictors of Narrative and Argument Quality ...
BASE
Show details
12
Can computers tell a story? Discourse Structure in Computer-generated Text and Humans ...
BASE
Show details
13
Are Rotten Apples Edible? Challenging Commonsense Inference Ability with Exceptions ...
BASE
Show details
14
Does Vision-and-Language Pretraining Improve Lexical Grounding? ...
Yun, Tian; Sun, Chen; Pavlick, Ellie. - : arXiv, 2021
Abstract: Linguistic representations derived from text alone have been criticized for their lack of grounding, i.e., connecting words to their meanings in the physical world. Vision-and-Language (VL) models, trained jointly on text and image or video data, have been offered as a response to such criticisms. However, while VL pretraining has shown success on multimodal tasks such as visual question answering, it is not yet known how the internal linguistic representations themselves compare to their text-only counterparts. This paper compares the semantic representations learned via VL vs. text-only pretraining for two recent VL models using a suite of analyses (clustering, probing, and performance on a commonsense question answering task) in a language-only setting. We find that the multimodal models fail to significantly outperform the text-only variants, suggesting that future work is required if multimodal pretraining is to be pursued as a means of improving NLP in general. ... : Camera ready for Findings of EMNLP 2021 ...
Keyword: Artificial Intelligence cs.AI; Computation and Language cs.CL; Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences
URL: https://arxiv.org/abs/2109.10246
https://dx.doi.org/10.48550/arxiv.2109.10246
BASE
Hide details
15
Does Vision-and-Language Pretraining Improve Lexical Grounding? ...
BASE
Show details
16
Does Vision-and-Language Pretraining Improve Lexical Grounding? ...
BASE
Show details
17
Frequency Effects on Syntactic Rule Learning in Transformers ...
BASE
Show details
18
Frequency Effects on Syntactic Rule Learning in Transformers ...
Wei, Jason; Garrette, Dan; Linzen, Tal. - : arXiv, 2021
BASE
Show details
19
Leveraging Longitudinal Data for Personalized Prediction and Word Representations
Welch, Charles. - 2021
BASE
Show details
20
A Visuospatial Dataset for Naturalistic Verb Learning ...
Ebert, Dylan; Pavlick, Ellie. - : arXiv, 2020
BASE
Show details

Page: 1 2

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
29
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern