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 ...
BASE
Show 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 ...
Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.497/ Abstract: Question Answering (QA) tasks requiring information from multiple documents often rely on a retrieval model to identify relevant information for reasoning. The retrieval model is typically trained to maximize the likelihood of the labeled supporting evidence. However, when retrieving from large text corpora such as Wikipedia, the correct answer can often be obtained from multiple evidence candidates. Moreover, not all such candidates are labeled as positive during annotation, rendering the training signal weak and noisy. This problem is exacerbated when the questions are unanswerable or when the answers are Boolean, since the model cannot rely on lexical overlap to make a connection between the answer and supporting evidence. We develop a new parameterization of set-valued retrieval that handles unanswerable queries, and we show that marginalizing over this set during training allows a model to mitigate false negatives in ...
Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing; Question-Answering Systems
URL: https://dx.doi.org/10.48448/d96m-4f64
https://underline.io/lecture/38033-mitigating-false-negative-contexts-in-multi-document-question-answering-with-retrieval-marginalization
BASE
Hide 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