DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 1 – 20 of 48

1
Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition ...
Sun, Bo; Wang, Baoxin; Che, Wanxiang. - : arXiv, 2022
BASE
Show details
2
ExpMRC: explainability evaluation for machine reading comprehension
In: Heliyon (2022)
BASE
Show details
3
Multilingual multi-aspect explainability analyses on machine reading comprehension models
In: iScience (2022)
Abstract: Achieving human-level performance on some of the machine reading comprehension (MRC) datasets is no longer challenging with the help of powerful pre-trained language models (PLMs). However, the internal mechanism of these artifacts remains unclear, placing an obstacle to further understand these models. This paper focuses on conducting a series of analytical experiments to examine the relations between the multi-head self-attention and the final MRC system performance, revealing the potential explainability in PLM-based MRC models. To ensure the robustness of the analyses, we perform our experiments in a multilingual way on top of various PLMs. We discover that passage-to-question and passage understanding attentions are the most important ones in the question answering process, showing strong correlations to the final performance than other parts. Through comprehensive visualizations and case studies, we also observe several general findings on the attention maps, which can be helpful to understand how these models solve the questions.
Keyword: Article
URL: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9019247/
https://doi.org/10.1016/j.isci.2022.104176
BASE
Hide details
4
Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models ...
BASE
Show details
5
Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training ...
Zheng, Bo; Dong, Li; Huang, Shaohan. - : arXiv, 2021
BASE
Show details
6
Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL ...
BASE
Show details
7
GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling ...
BASE
Show details
8
A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples ...
BASE
Show details
9
Dynamic Connected Networks for Chinese Spelling Check ...
BASE
Show details
10
Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling ...
BASE
Show details
11
Neural Stylistic Response Generation with Disentangled Latent Variables ...
BASE
Show details
12
Guided Generation of Cause and Effect ...
Li, Zhongyang; Ding, Xiao; Liu, Ting. - : arXiv, 2021
BASE
Show details
13
Language learners' enjoyment and emotion regulation in online collaborative learning
Zhang, Zhipeng (S34844); Liu, Ting; Lee, Chweebeng (R17032). - : U.K., Elsevier, 2021
BASE
Show details
14
Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network ...
Jiang, Tianwen; Zhao, Tong; Qin, Bing. - : arXiv, 2020
BASE
Show details
15
TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching ...
BASE
Show details
16
N-LTP: An Open-source Neural Language Technology Platform for Chinese ...
BASE
Show details
17
Cross-Lingual Machine Reading Comprehension ...
Cui, Yiming; Che, Wanxiang; Liu, Ting. - : arXiv, 2019
BASE
Show details
18
Neural recovery machine for chinese dropped pronoun [<Journal>]
Zhang, Weinan [Verfasser]; Liu, Ting [Verfasser]; Yin, Qingyu [Verfasser].
DNB Subject Category Language
Show details
19
CoNLL 2018 Shared Task System Outputs
Zeman, Daniel; Potthast, Martin; Duthoo, Elie. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2018
BASE
Show details
20
Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation ...
BASE
Show details

Page: 1 2 3

Catalogues
0
0
6
0
2
0
0
Bibliographies
3
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
40
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern