LIVIVO - Das Suchportal für Lebenswissenschaften

switch to English language
Zurück zur letzten Suche Suchhistorie
Erweiterte Suche

Ihre letzten Suchen

  1. AU=Qi Maosong
  2. AU="Tian, Mengting"
  3. AU="Ghosh, Debdatta"
  4. AU="Madheswaran, Suresh"
  5. AU=Rogerio Alexandre de Paula
  6. AU=Warshaw A L
  7. AU="Waqar Ahmed"
  8. AU="Harper, William A."
  9. AU="Fargo, Keith"
  10. AU=Reed Matthew J
  11. AU="Harris, Hannah L"
  12. AU="Asahi, Hiroko"
  13. AU="Mohamed El Mohadab"
  14. AU="Jamjoom, Maan"
  15. AU="Benjamin K. Harley"
  16. AU="Redpath, Stephanie"
  17. AU="Costa Oliveira, Diogo"
  18. AU="Ibarra-Meneses, Ana Victoria"
  19. AU=Ozgenel Guzin Yesim
  20. AU="Shu-Ying Li"
  21. AU="Umemura, Yutaka"
  22. AU=Eiring A M
  23. AU="Eunhee Ha"
  24. AU="Espíndola, Otávio M"
  25. AU=Shahbazian Heshmatollah
  26. AU="Esmaeel Panahi kokhdan"
  27. AU=Peekhaus N
  28. AU="Ferrari-Toniolo, Simone"
  29. AU="Oleg M. Mikhailenok"

Suchergebnis

Treffer 1 - 10 von insgesamt 55

Suchoptionen

  1. Buch ; Online: Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks

    Chen, Yangyi / Qi, Fanchao / Liu, Zhiyuan / Sun, Maosong

    2021  

    Abstract: Backdoor attacks are a kind of emergent security threat in deep learning. When a deep neural model is injected with a backdoor, it will behave normally on standard inputs but give adversary-specified predictions once the input contains specific backdoor ... ...

    Abstract Backdoor attacks are a kind of emergent security threat in deep learning. When a deep neural model is injected with a backdoor, it will behave normally on standard inputs but give adversary-specified predictions once the input contains specific backdoor triggers. Current textual backdoor attacks have poor attack performance in some tough situations. In this paper, we find two simple tricks that can make existing textual backdoor attacks much more harmful. The first trick is to add an extra training task to distinguish poisoned and clean data during the training of the victim model, and the second one is to use all the clean training data rather than remove the original clean data corresponding to the poisoned data. These two tricks are universally applicable to different attack models. We conduct experiments in three tough situations including clean data fine-tuning, low poisoning rate, and label-consistent attacks. Experimental results show that the two tricks can significantly improve attack performance. This paper exhibits the great potential harmfulness of backdoor attacks. All the code and data will be made public to facilitate further research.

    Comment: Work in progress
    Schlagwörter Computer Science - Cryptography and Security ; Computer Science - Artificial Intelligence ; Computer Science - Computation and Language
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2021-10-15
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  2. Buch ; Online: QuoteR

    Qi, Fanchao / Yang, Yanhui / Yi, Jing / Cheng, Zhili / Liu, Zhiyuan / Sun, Maosong

    A Benchmark of Quote Recommendation for Writing

    2022  

    Abstract: It is very common to use quotations (quotes) to make our writings more elegant or convincing. To help people find appropriate quotes efficiently, the task of quote recommendation is presented, aiming to recommend quotes that fit the current context of ... ...

    Abstract It is very common to use quotations (quotes) to make our writings more elegant or convincing. To help people find appropriate quotes efficiently, the task of quote recommendation is presented, aiming to recommend quotes that fit the current context of writing. There have been various quote recommendation approaches, but they are evaluated on different unpublished datasets. To facilitate the research on this task, we build a large and fully open quote recommendation dataset called QuoteR, which comprises three parts including English, standard Chinese and classical Chinese. Any part of it is larger than previous unpublished counterparts. We conduct an extensive evaluation of existing quote recommendation methods on QuoteR. Furthermore, we propose a new quote recommendation model that significantly outperforms previous methods on all three parts of QuoteR. All the code and data of this paper are available at https://github.com/thunlp/QuoteR.

    Comment: Accepted by the main conference of ACL 2022 as a long paper. The camera-ready version
    Schlagwörter Computer Science - Computation and Language ; Computer Science - Artificial Intelligence ; Computer Science - Information Retrieval
    Thema/Rubrik (Code) 004
    Erscheinungsdatum 2022-02-26
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  3. Buch ; Online: Turn the Combination Lock

    Qi, Fanchao / Yao, Yuan / Xu, Sophia / Liu, Zhiyuan / Sun, Maosong

    Learnable Textual Backdoor Attacks via Word Substitution

    2021  

    Abstract: Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is activated, ... ...

    Abstract Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is activated, presenting serious security threats to real-world applications. Since existing textual backdoor attacks pay little attention to the invisibility of backdoors, they can be easily detected and blocked. In this work, we present invisible backdoors that are activated by a learnable combination of word substitution. We show that NLP models can be injected with backdoors that lead to a nearly 100% attack success rate, whereas being highly invisible to existing defense strategies and even human inspections. The results raise a serious alarm to the security of NLP models, which requires further research to be resolved. All the data and code of this paper are released at https://github.com/thunlp/BkdAtk-LWS.

    Comment: Accepted by the main conference of ACL-IJCNLP as a long paper. Camera-ready version
    Schlagwörter Computer Science - Computation and Language ; Computer Science - Cryptography and Security
    Thema/Rubrik (Code) 303
    Erscheinungsdatum 2021-06-11
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  4. Buch ; Online: Lexical Sememe Prediction using Dictionary Definitions by Capturing Local Semantic Correspondence

    Du, Jiaju / Qi, Fanchao / Sun, Maosong / Liu, Zhiyuan

    2020  

    Abstract: Sememes, defined as the minimum semantic units of human languages in linguistics, have been proven useful in many NLP tasks. Since manual construction and update of sememe knowledge bases (KBs) are costly, the task of automatic sememe prediction has been ...

    Abstract Sememes, defined as the minimum semantic units of human languages in linguistics, have been proven useful in many NLP tasks. Since manual construction and update of sememe knowledge bases (KBs) are costly, the task of automatic sememe prediction has been proposed to assist sememe annotation. In this paper, we explore the approach of applying dictionary definitions to predicting sememes for unannotated words. We find that sememes of each word are usually semantically matched to different words in its dictionary definition, and we name this matching relationship local semantic correspondence. Accordingly, we propose a Sememe Correspondence Pooling (SCorP) model, which is able to capture this kind of matching to predict sememes. We evaluate our model and baseline methods on a famous sememe KB HowNet and find that our model achieves state-of-the-art performance. Moreover, further quantitative analysis shows that our model can properly learn the local semantic correspondence between sememes and words in dictionary definitions, which explains the effectiveness of our model. The source codes of this paper can be obtained from https://github.com/thunlp/scorp.

    Comment: Accepted by Journal of Chinese Information Processing
    Schlagwörter Computer Science - Computation and Language
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2020-01-16
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  5. Buch ; Online: Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information

    Qi, Fanchao / Lv, Chuancheng / Liu, Zhiyuan / Meng, Xiaojun / Sun, Maosong / Zheng, Hai-Tao

    2022  

    Abstract: In linguistics, a sememe is defined as the minimum semantic unit of languages. Sememe knowledge bases (KBs), which are built by manually annotating words with sememes, have been successfully applied to various NLP tasks. However, existing sememe KBs only ...

    Abstract In linguistics, a sememe is defined as the minimum semantic unit of languages. Sememe knowledge bases (KBs), which are built by manually annotating words with sememes, have been successfully applied to various NLP tasks. However, existing sememe KBs only cover a few languages, which hinders the wide utilization of sememes. To address this issue, the task of sememe prediction for BabelNet synsets (SPBS) is presented, aiming to build a multilingual sememe KB based on BabelNet, a multilingual encyclopedia dictionary. By automatically predicting sememes for a BabelNet synset, the words in many languages in the synset would obtain sememe annotations simultaneously. However, previous SPBS methods have not taken full advantage of the abundant information in BabelNet. In this paper, we utilize the multilingual synonyms, multilingual glosses and images in BabelNet for SPBS. We design a multimodal information fusion model to encode and combine this information for sememe prediction. Experimental results show the substantial outperformance of our model over previous methods (about 10 MAP and F1 scores). All the code and data of this paper can be obtained at https://github.com/thunlp/MSGI.

    Comment: Accepted by Findings of ACL 2022 as a long paper. Camera-ready version
    Schlagwörter Computer Science - Computation and Language ; Computer Science - Artificial Intelligence
    Thema/Rubrik (Code) 410
    Erscheinungsdatum 2022-03-14
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  6. Artikel ; Online: Country Image in COVID-19 Pandemic

    Chen, Huimin / Zhu, Zeyu / Qi, Fanchao / Ye, Yining / Liu, Zhiyuan / Sun, Maosong / Jin, Jianbin

    IEEE Transactions on Big Data

    A Case Study of China

    2020  , Seite(n) 1–1

    Schlagwörter covid19
    Verlag Institute of Electrical and Electronics Engineers (IEEE)
    Erscheinungsland us
    Dokumenttyp Artikel ; Online
    ISSN 2332-7790
    DOI 10.1109/tbdata.2020.3023459
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  7. Buch ; Online: Using BERT for Word Sense Disambiguation

    Du, Jiaju / Qi, Fanchao / Sun, Maosong

    2019  

    Abstract: Word Sense Disambiguation (WSD), which aims to identify the correct sense of a given polyseme, is a long-standing problem in NLP. In this paper, we propose to use BERT to extract better polyseme representations for WSD and explore several ways of ... ...

    Abstract Word Sense Disambiguation (WSD), which aims to identify the correct sense of a given polyseme, is a long-standing problem in NLP. In this paper, we propose to use BERT to extract better polyseme representations for WSD and explore several ways of combining BERT and the classifier. We also utilize sense definitions to train a unified classifier for all words, which enables the model to disambiguate unseen polysemes. Experiments show that our model achieves the state-of-the-art results on the standard English All-word WSD evaluation.
    Schlagwörter Computer Science - Computation and Language
    Erscheinungsdatum 2019-09-18
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  8. Artikel: Country Image in COVID-19 Pandemic: A Case Study of China.

    Chen, Huimin / Zhu, Zeyu / Qi, Fanchao / Ye, Yining / Liu, Zhiyuan / Sun, Maosong / Jin, Jianbin

    IEEE transactions on big data

    2020  Band 7, Heft 1, Seite(n) 81–92

    Abstract: Country image has a profound influence on international relations and economic development. In the worldwide outbreak of COVID-19, countries and their people display different reactions, resulting in diverse perceived images among foreign public. ... ...

    Abstract Country image has a profound influence on international relations and economic development. In the worldwide outbreak of COVID-19, countries and their people display different reactions, resulting in diverse perceived images among foreign public. Therefore, in this article, we take China as a specific and typical case and investigate its image with aspect-based sentiment analysis on a large-scale Twitter dataset. To our knowledge, this is the first study to explore country image in such a fine-grained way. To perform the analysis, we first build a manually-labeled Twitter dataset with aspect-level sentiment annotations. Afterward, we conduct the aspect-based sentiment analysis with BERT to explore the image of China. We discover an overall sentiment change from non-negative to negative in the general public, and explain it with the increasing mentions of negative ideology-related aspects and decreasing mentions of non-negative fact-based aspects. Further investigations into different groups of Twitter users, including U.S. Congress members, English media, and social bots, reveal different patterns in their attitudes toward China. This article provides a deeper understanding of the changing image of China in COVID-19 pandemic. Our research also demonstrates how aspect-based sentiment analysis can be applied in social science researches to deliver valuable insights.
    Sprache Englisch
    Erscheinungsdatum 2020-09-11
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 2332-7790
    ISSN 2332-7790
    DOI 10.1109/TBDATA.2020.3023459
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  9. Buch ; Online: Know What You Don't Need

    Zhang, Zhengyan / Qi, Fanchao / Liu, Zhiyuan / Liu, Qun / Sun, Maosong

    Single-Shot Meta-Pruning for Attention Heads

    2020  

    Abstract: Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually overparameterized and ... ...

    Abstract Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually overparameterized and significantly increase the computational overhead in applications. It is intuitive to address this issue by model compression. In this work, we propose a method, called Single-Shot Meta-Pruning, to compress deep pre-trained Transformers before fine-tuning. Specifically, we focus on pruning unnecessary attention heads adaptively for different downstream tasks. To measure the informativeness of attention heads, we train our Single-Shot Meta-Pruner (SMP) with a meta-learning paradigm aiming to maintain the distribution of text representations after pruning. Compared with existing compression methods for pre-trained models, our method can reduce the overhead of both fine-tuning and inference. Experimental results show that our pruner can selectively prune 50% of attention heads with little impact on the performance on downstream tasks and even provide better text representations. The source code will be released in the future.
    Schlagwörter Computer Science - Computation and Language
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2020-11-07
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  10. Buch ; Online: Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer

    Qi, Fanchao / Chen, Yangyi / Zhang, Xurui / Li, Mukai / Liu, Zhiyuan / Sun, Maosong

    2021  

    Abstract: Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to most NLP tasks, ... ...

    Abstract Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to most NLP tasks, and thus suitable for adversarial and backdoor attacks. In this paper, we make the first attempt to conduct adversarial and backdoor attacks based on text style transfer, which is aimed at altering the style of a sentence while preserving its meaning. We design an adversarial attack method and a backdoor attack method, and conduct extensive experiments to evaluate them. Experimental results show that popular NLP models are vulnerable to both adversarial and backdoor attacks based on text style transfer -- the attack success rates can exceed 90% without much effort. It reflects the limited ability of NLP models to handle the feature of text style that has not been widely realized. In addition, the style transfer-based adversarial and backdoor attack methods show superiority to baselines in many aspects. All the code and data of this paper can be obtained at https://github.com/thunlp/StyleAttack.

    Comment: Accepted by the main conference of EMNLP 2021 as a long paper. The camera-ready version
    Schlagwörter Computer Science - Computation and Language ; Computer Science - Artificial Intelligence ; Computer Science - Cryptography and Security
    Erscheinungsdatum 2021-10-13
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Zum Seitenanfang