1 |
Problematizing Fluent Speakers’ Unintentional Exclusion of Emergent Bilinguals: A Case Study of an English-Medium Instruction Classroom in Japan
|
|
|
|
In: International Journal of Literacy, Culture, and Language Education; Vol. 2 (2022): Special Issue: Language Weaponization in Society and Education; 6-19 ; 2642-4002 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Developing Critical Cultural Awareness in the ELT Classroom
|
|
|
|
In: Faculty Publications: Department of Teaching, Learning and Teacher Education (2022)
|
|
BASE
|
|
Show details
|
|
3 |
A quantitative perspective on Japanese accent
|
|
|
|
In: 34th Paris Meeting on East Asian Linguistics ; https://hal.archives-ouvertes.fr/hal-03283679 ; 34th Paris Meeting on East Asian Linguistics, Jul 2021, Paris, France (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Phrase-Level Action Reinforcement Learning for Neural Dialog Response Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Embracing Ambiguity: Shifting the Training Target of NLI Models ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Improving Multilingual Translation by Representation and Gradient Regularization ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Embracing Ambiguity: Shifting the Training Target of NLI Models ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap ...
|
|
|
|
Abstract:
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question-context lexical overlap. This hinders QA models from generalizing to under-represented samples such as questions with low lexical overlap. Question generation (QG), a method for augmenting QA datasets, can be a solution for such performance degradation if QG can properly debias QA datasets. However, we discover that recent neural QG models are biased towards generating questions with high lexical overlap, which can amplify the dataset bias. Moreover, our analysis reveals that data augmentation with these QG models frequently impairs the performance on questions with low lexical overlap, while improving that on questions with high lexical overlap. To address this problem, we use a synonym replacement-based approach to augment questions with low lexical overlap. We demonstrate that the proposed data augmentation approach is simple yet effective to mitigate the degradation ... : MRQA workshop at EMNLP 2021 ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2109.11256 https://arxiv.org/abs/2109.11256
|
|
BASE
|
|
Hide details
|
|
12 |
The Effect of Phonological Short-Term Memory on Japanese EFL Learners’ Listening Skills
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Bend Like Bamboo: Resilience and Tools for Teaching in an Unstable World
|
|
|
|
In: South East Coastal Conference on Languages & Literatures (SECCLL) (2021)
|
|
BASE
|
|
Show details
|
|
14 |
A quantitative perspective on Japanese accent
|
|
|
|
In: 34th Paris Meeting on East Asian Linguistics ; https://hal.archives-ouvertes.fr/hal-03283679 ; 34th Paris Meeting on East Asian Linguistics, Jul 2021, Paris, France (2021)
|
|
BASE
|
|
Show details
|
|
15 |
Effects of gender on language revitalisation & documentation in the Ryukyus
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Multilingual society:the legacy of the Tokyo Olympics and Paralympics?
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Maintaining Common Ground in Dynamic Environments
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 9, Pp 995-1011 (2021) (2021)
|
|
BASE
|
|
Show details
|
|
18 |
An Evaluation Dataset for Identifying Communicative Functions of Sentences in English Scholarly Papers
|
|
|
|
In: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) ; 12th Conference on Language Resources and Evaluation (LREC 2020) ; https://hal.archives-ouvertes.fr/hal-03272825 ; 12th Conference on Language Resources and Evaluation (LREC 2020), May 2020, Marseille, France (2020)
|
|
BASE
|
|
Show details
|
|
19 |
Keyphrase Generation for Scientific Document Retrieval
|
|
|
|
In: The 58th Annual Meeting of the Association for Computational Linguistics (ACL) ; https://hal.archives-ouvertes.fr/hal-02556086 ; The 58th Annual Meeting of the Association for Computational Linguistics (ACL), Jul 2020, Online, United States. ⟨10.18653/v1/2020.acl-main.105⟩ (2020)
|
|
BASE
|
|
Show details
|
|
20 |
非漢字系初級学習者の読解困難点 [Difficultés de lecture en japonais chez les apprenants du niveau débutant issus de culture alphabétique]
|
|
|
|
In: 日本語学習者の読解過程の解明 [Analyses du processus de lecture des apprenants de japonais] ; https://halshs.archives-ouvertes.fr/halshs-02415261 ; 日本語学習者の読解過程の解明 [Analyses du processus de lecture des apprenants de japonais], Coco shuppan, 2020 (2020)
|
|
BASE
|
|
Show details
|
|
|
|