DE eng

Search in the Catalogues and Directories

Hits 1 – 18 of 18

1
QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension ...
BASE
Show details
2
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus ...
BASE
Show details
3
COVR: A Test-Bed for Visually Grounded Compositional Generalization with Real Images ...
BASE
Show details
4
Enforcing Consistency in Weakly Supervised Semantic Parsing ...
Abstract: Read paper: https://www.aclanthology.org/2021.acl-short.22 Abstract: The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate search strategies to mitigate the prevalence of spurious programs; however, they typically consider only one input at a time. In this work we explore the use of consistency between the output programs for related inputs to reduce the impact of spurious programs. We bias the program search (and thus the model's training signal) towards programs that map the same phrase in related inputs to the same sub-parts in their respective programs. Additionally, we study the importance of designing logical formalisms that facilitate this kind of consistency-based training. We find that a more consistent formalism leads to improved model performance even without consistency-based training. When combined together, these two insights lead to a 10% absolute improvement over the best ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
URL: https://underline.io/lecture/25954-enforcing-consistency-in-weakly-supervised-semantic-parsing
https://dx.doi.org/10.48448/1sq8-3767
BASE
Hide details
5
Understanding Mention Detector-Linker Interaction in Neural Coreference Resolution ...
BASE
Show details
6
Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization ...
BASE
Show details
7
Tailor: Generating and Perturbing Text with Semantic Controls ...
BASE
Show details
8
Competency Problems: On Finding and Removing Artifacts in Language Data ...
BASE
Show details
9
Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization ...
BASE
Show details
10
Break It Down: A Question Understanding Benchmark ...
BASE
Show details
11
Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering ...
BASE
Show details
12
Evaluating Models' Local Decision Boundaries via Contrast Sets ...
BASE
Show details
13
IIRC: A Dataset of Incomplete Information Reading Comprehension Questions ...
BASE
Show details
14
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning ...
BASE
Show details
15
Deep contextualized word representations ...
BASE
Show details
16
Grammatical Variation and Change in Industrial Cape Breton
BASE
Show details
17
The acoustic and articulatory characteristics of Cape Breton fricative /t/
In: Dialectologia et geolinguistica. - Berlin [u.a.] : Mouton de Gruyter 21 (2013), 3-20
BLLDB
OLC Linguistik
Show details
18
The Phonology of the Canadian Shift Revisited: Thunder Bay & Cape Breton
In: University of Pennsylvania Working Papers in Linguistics (2013)
BASE
Show details

Catalogues
0
0
1
0
0
0
0
Bibliographies
1
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
17
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern