DE eng

Search in the Catalogues and Directories

Page: 1...133 134 135 136 137
Hits 2.721 – 2.739 of 2.739

2721
Efficient Content-Based Sparse Attention with Routing Transformers
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 53-68 (2021) (2021)
BASE
Show details
2722
On the Difficulty of Translating Free-Order Case-Marking Languages
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 1233-1248 (2021) (2021)
BASE
Show details
2723
Self-supervised Regularization for Text Classification
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 641-656 (2021) (2021)
BASE
Show details
2724
An Error Analysis Framework for Shallow Surface Realization
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 429-446 (2021) (2021)
BASE
Show details
2725
On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 139-159 (2021) (2021)
BASE
Show details
2726
Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 1047-1060 (2021) (2021)
BASE
Show details
2727
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 160-175 (2021) (2021)
BASE
Show details
2728
QED: A Framework and Dataset for Explanations in Question Answering
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 790-806 (2021) (2021)
Abstract: A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggability, extensibility, and trust. To this end, we propose QED, a linguistically informed, extensible framework for explanations in question answering. A QED explanation specifies the relationship between a question and answer according to formal semantic notions such as referential equality, sentencehood, and entailment. We describe and publicly release an expert-annotated dataset of QED explanations built upon a subset of the Google Natural Questions dataset, and report baseline models on two tasks—post- hoc explanation generation given an answer, and joint question answering and explanation generation. In the joint setting, a promising result suggests that training on a relatively small amount of QED data can improve question answering. In addition to describing the formal, language-theoretic motivations for the QED approach, we describe a large user study showing that the presence of QED explanations significantly improves the ability of untrained raters to spot errors made by a strong neural QA baseline.
Keyword: Computational linguistics. Natural language processing; P98-98.5
URL: https://doi.org/10.1162/tacl_a_00398
https://doaj.org/article/06787832af234ed685bae92217b8247a
BASE
Hide details
2729
Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 691-706 (2021) (2021)
BASE
Show details
2730
Dependency Syntax in the Automatic Detection of Irony and Stance
Cignarella, Alessandra Teresa. - : Universitat Politècnica de València, 2021
BASE
Show details
2731
Sujeito oculto às claras: uma abordagem descritivo-computacional / Omitted subjects revealed: a quantitative-descriptive approach
In: Revista de Estudos da Linguagem, Vol 29, Iss 2, Pp 1033-1058 (2021) (2021)
BASE
Show details
2732
Propriedades linguísticas da redação do Enem: uma análise computacional / Linguistic properties of Enem essays: a computational analysis
In: Revista de Estudos da Linguagem, Vol 29, Iss 2, Pp 999-1032 (2021) (2021)
BASE
Show details
2733
Multi-script morphological transducers and transcribers for seven Turkic languages
In: Proceedings of the Workshop on Turkic and Languages in Contact with Turkic; Vol 5 (2020); 173-185 ; 2641-3485 (2021)
BASE
Show details
2734
Deriving frequency effects from biases in learning
In: Proceedings of the Linguistic Society of America; Vol 6, No 1 (2021): Proceedings of the Linguistic Society of America; 514–525 ; 2473-8689 (2021)
BASE
Show details
2735
Intention and Attention in Image-Text Presentations: A Coherence Approach
In: Experiments in Linguistic Meaning; Vol 1 (2021); 273-283 ; 2694-1791 (2021)
BASE
Show details
2736
Cross-linguistic scope ambiguity: An investigation of English, Spanish, and Mandarin
In: Proceedings of the Linguistic Society of America; Vol 6, No 1 (2021): Proceedings of the Linguistic Society of America; 572–586 ; 2473-8689 (2021)
BASE
Show details
2737
Speech tested for Zipfian fit using rigorous statistical techniques
In: Proceedings of the Linguistic Society of America; Vol 6, No 1 (2021): Proceedings of the Linguistic Society of America; 394–402 ; 2473-8689 (2021)
BASE
Show details
2738
Concord begets concord: A Bayesian model of nominal concord typology
In: Proceedings of the Linguistic Society of America; Vol 6, No 1 (2021): Proceedings of the Linguistic Society of America; 541–555 ; 2473-8689 (2021)
BASE
Show details
2739
The role of verb semantics in Hungarian verb-object order
In: Proceedings of the Linguistic Society of America; Vol 6, No 1 (2021): Proceedings of the Linguistic Society of America; 54–68 ; 2473-8689 (2021)
BASE
Show details

Page: 1...133 134 135 136 137

Catalogues
0
0
0
0
0
0
1
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
2.737
1
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern