Filters








531 Hits in 5.4 sec

Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization [article]

Ruipeng Jia, Xingxing Zhang, Yanan Cao, Shi Wang, Zheng Lin, Furu Wei
2022 arXiv   pre-print
To fully leverage the information of these different sets of labels, we propose NLSSum (Neural Label Search for Summarization), which jointly learns hierarchical weights for these different sets of labels  ...  In zero-shot multilingual extractive text summarization, a model is typically trained on English summarization dataset and then applied on summarization datasets of other languages.  ...  In multi-lingual zero-shot setting, the summarization model is trained on English dataset and is finally applied on documents of other languages.  ... 
arXiv:2204.13512v2 fatcat:42toqnprsjad3avowq2qayuyym

Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization

Ruipeng Jia, Xingxing Zhang, Yanan Cao, Zheng Lin, Shi Wang, Furu Wei
2022 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   unpublished
To fully leverage the information of these different sets of labels, we propose NLSSum (Neural Label Search for Summarization), which jointly learns hierarchical weights for these different sets of labels  ...  In zero-shot multilingual extractive text summarization, a model is typically trained on English summarization dataset and then applied on summarization datasets of other languages.  ...  In multi-lingual zero-shot setting, the summarization model is trained on English dataset and is finally applied on documents of other languages.  ... 
doi:10.18653/v1/2022.acl-long.42 fatcat:ar5mqc223ncrfprl4bt2i7gzn4

Knowledge Extraction in Low-Resource Scenarios: Survey and Perspective [article]

Shumin Deng, Ningyu Zhang, Hui Chen, Feiyu Xiong, Jeff Z. Pan, Huajun Chen
2022 arXiv   pre-print
Many neural approaches on low-resource KE have been widely investigated and achieved impressive performance.  ...  In addition, we describe promising applications and outline some potential directions for future research.  ...  consistency and complementarity among cross-lingual texts. have studied the multi-lingual EE task and exploited the consistent information in multi-lingual data via cross-lingual attention gate mechanism  ... 
arXiv:2202.08063v1 fatcat:2q64tx2mzne53gt24adi6ymj7a

A Survey on Spoken Language Understanding: Recent Advances and New Frontiers [article]

Libo Qin, Tianbao Xie, Wanxiang Che, Ting Liu
2021 arXiv   pre-print
Spoken Language Understanding (SLU) aims to extract the semantics frame of user queries, which is a core component in a task-oriented dialog system.  ...  With the burst of deep neural networks and the evolution of pre-trained language models, the research of SLU has obtained significant breakthroughs.  ...  Cosda-ml: Multi-lingual code-switching [Wang et al., 2020] Yuxuan Wang, Yutai Hou, Wanxiang data augmentation for zero-shot cross-lingual  ... 
arXiv:2103.03095v2 fatcat:krhrfeomafd6nds2m4o5djbzby

Contextualized Cross-Lingual Event Trigger Extraction with Minimal Resources

Meryem M'hamdi, Marjorie Freedman, Jonathan May
2019 Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)  
However, there has not been much effort in exploring language transfer using BERT for event extraction.  ...  Event trigger extraction is an information extraction task of practical utility, yet it is challenging due to the difficulty of disambiguating word sense meaning.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
doi:10.18653/v1/k19-1061 dblp:conf/conll/MhamdiFM19 fatcat:u2bi77j5vbeqneqvi3mwydjhhm

Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing [article]

Necva Bölücü, Burcu Can
2021 arXiv   pre-print
We present the results for both single-lingual and cross-lingual tasks using zero-shot and few-shot learning for low-resource languages.  ...  The paper not only presents the existing approaches proposed for UCCA representation, but also proposes a novel self-attentive neural parsing model for the UCCA representation.  ...  Zero-shot and Few-shot Cross-Lingual Model: Zero-shot learning [73, 74] and few-shot learning [75] have shown outstanding success recently in various NLP tasks such as dependency parsing and text classification  ... 
arXiv:2110.00621v1 fatcat:5maoxftntbbpvj4umfxrnf5ibm

An Empirical Study of Pre-trained Transformers for Arabic Information Extraction [article]

Wuwei Lan, Yang Chen, Wei Xu, Alan Ritter
2020 arXiv   pre-print
., 2020a), have been shown to enable the effective cross-lingual zero-shot transfer. However, their performance on Arabic information extraction (IE) tasks is not very well studied.  ...  We study GigaBERT's effectiveness on zero-short transfer across four IE tasks: named entity recognition, part-of-speech tagging, argument role labeling, and relation extraction.  ...  Acknowledgement We thank Nizar Habash and anonymous reviewers for their valuable suggestions. We also thank the Google TFRC program for providing free TPU access.  ... 
arXiv:2004.14519v5 fatcat:z7nrw356wfehjlw7oj43j6ek5i

Table of Contents [EDICS]

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
Blanco 1395 Reinforced Zero-Shot Cross-Lingual Neural Headline Generation . . . . . . . . Ayana, Y. Chen, C. Yang, Z. Liu, and M.  ...  Yu 1936 A Joint Sentence Scoring and Selection Framework for Neural Extractive Document Summarization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/taslp.2020.3046150 fatcat:easrxuwl6zdppejsrf4bskxfw4

Cross-lingual Approaches for the Detection of Adverse Drug Reactions in German from a Patient's Perspective [article]

Lisa Raithel, Philippe Thomas, Roland Roller, Oliver Sapina, Sebastian Möller, Pierre Zweigenbaum
2022 arXiv   pre-print
We aim to encourage further multi-lingual efforts in the domain of ADR detection and provide preliminary experiments for binary classification using different methods of zero- and few-shot learning based  ...  on a multi-lingual model.  ...  We would also like to thank the Lifeline administrators for allowing us to use their data, explosion.ai for providing us with a researchers licence for Prodigy, and the anonymous reviewers for their detailed  ... 
arXiv:2208.02031v1 fatcat:4qdeg34kxre4fm6whyflhn7aea

Neural Entity Linking: A Survey of Models Based on Deep Learning [article]

Ozge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, Chris Biemann
2021 arXiv   pre-print
techniques including zero-shot and distant supervision methods, and cross-lingual approaches.  ...  We distill generic architectural components of a neural EL system, like candidate generation and entity ranking, and summarize prominent methods for each of them.  ...  The work of Artem Shelmanov in the current study (preparation of sections related to application of entity linking to neural language models, entity ranking, contextmention encoding, and overall harmonization  ... 
arXiv:2006.00575v3 fatcat:ra3kwc4tmbfhlmgtlevkcshcqq

Low-Resource Adaptation of Neural NLP Models [article]

Farhad Nooralahzadeh
2020 arXiv   pre-print
The objective of this thesis is to investigate methods for dealing with such low-resource scenarios in information extraction and natural language understanding.  ...  We develop and adapt neural NLP models to explore a number of research questions concerning NLP tasks with minimal or no training data.  ...  "MLQA: Evaluating Cross-lingual Extractive Question Answering". In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics.  ... 
arXiv:2011.04372v1 fatcat:626mbe5ba5bkdflv755o35u5pq

Multi-Modal Zero-Shot Sign Language Recognition [article]

Razieh Rastgoo, Kourosh Kiani, Sergio Escalera, Mohammad Sabokrou
2021 arXiv   pre-print
A Transformer-based model along with a C3D model is used for hand detection and deep features extraction, respectively.  ...  Zero-Shot Learning (ZSL) has rapidly advanced in recent years.  ...  Section 2 briefly reviews recent works in the ZS-SLR, Zero-Shot Gesture Recognition (ZS-GR), and Zero-Shot Action Recognition (ZS-AR). The proposed model is presented in details in section 3.  ... 
arXiv:2109.00796v1 fatcat:6ca2ge676rabvnnrchazxwshri

Multilingual and Zero-Shot is Closing in on Monolingual Web Register Classification

Samuel Rönnqvist, Valtteri Skantsi, Miika Oinonen, Veronika Laippala
2021 Nordic Conference of Computational Linguistics  
zero-shot cross-lingual transfer.  ...  While the wide range of linguistic variation found on the web poses challenges for register classification, recent studies have shown that good levels of cross-lingual transfer from the extensive English  ...  We also wish to acknowledge CSC -IT Center for Science, Finland, and the NVIDIA Corporation GPU Grant Program, for computational resources.  ... 
dblp:conf/nodalida/RonnqvistSOL21 fatcat:kft7ltityzautodj3mqj4nahdq

Zero-Shot Cross-lingual Name Retrieval for Low-Resource Languages

Kevin Blissett, Heng Ji
2019 Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)  
Our method proceeds in a multi-step process: first, we pretrain a language-independent orthographic encoder using Wikipedia inter-lingual links from dozens of languages.  ...  We present a novel method which relies on zero annotation or resources from the target language.  ...  Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.  ... 
doi:10.18653/v1/d19-6131 dblp:conf/acl-deeplo/BlissettJ19 fatcat:ivqb6bplyze6pmok7rzsxoiuju

Neural entity linking: A survey of models based on deep learning

Özge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, Chris Biemann, Mehwish Alam, Davide Buscaldi, Michael Cochez, Francesco Osborne, Diego Reforgiato Recupero, Harald Sack
2022 Semantic Web Journal  
including zero-shot and distant supervision methods, and cross-lingual approaches.  ...  This work distills a generic architecture of a neural EL system and discusses its components, such as candidate generation, mention-context encoding, and entity ranking, summarizing prominent methods for  ...  The work of Artem Shelmanov in the current study (preparation of sections related to application of entity linking to neural language models, entity ranking, context-mention encoding, and overall harmonization  ... 
doi:10.3233/sw-222986 fatcat:6gwmbtev7ngbliovf6cpf5hyde
« Previous Showing results 1 — 15 out of 531 results