DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 41 – 45 of 45

41
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering ...
BASE
Show details
42
Just Ask! Evaluating Machine Translation by Asking and Answering Questions ...
BASE
Show details
43
Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering ...
BASE
Show details
44
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
45
SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map ...
BASE
Show details

Page: 1 2 3

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
45
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern