paper-with-me

홈 › Papers

Using Deep Mixture-of-Experts to Detect Word Meaning Shift for TempoWiC

2022-11-07 · Ze Chen, Kangxu Wang, Zijian Cai, Jiewen Zheng, Jiarong He, Max Gao, Jason Zhang

This paper mainly describes the dma submission to the TempoWiC task, which achieves a macro-F1 score of 77.05% and attains the first place in this task. We first explore the impact of different pre-trained language models. Then we adopt data cleaning, data augmentation, and adversarial training strategies to enhance the model generalization and robustness. For further improvement, we integrate POS information and word semantic representation using a Mixture-of-Experts (MoE) approach. The experimental results show that MoE can overcome the feature overuse issue and combine the context, POS, and word semantic features well. Additionally, we use a model ensemble method for the final prediction, which has been proven effective by many research works.

📄 PDF Abstract BibTeX arXiv:2211.03466

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationMixture-of-ExpertsPOS

Methods 이 논문이 사용한 방법론

DMA In image inpainting task, the mechanism extracts complementary features from the word embedding in two paths by reciprocal attention, which is done by comparing the descriptive…

Similar Papers 제목 키워드 기반

A Methodology for Building a Diachronic Dataset of Semantic Shifts and its Application to QC-FR-Diac-V1.0, a Free Reference for French

2022-06-01 · LREC 2022 6 · David Kletz, Philippe Langlais, François Lareau, Patrick Drouin

Different algorithms have been proposed to detect semantic shifts (changes in a word meaning over time) in a diachronic corpus. Yet, and somehow surprisingly, no reference corpus has been designed so far to evaluate them…

Semantic Shift DetectionWord Sense Disambiguation

What is Done is Done: an Incremental Approach to Semantic Shift Detection

2022-05-01 · LChange (ACL) 2022 5 · Francesco Periti, Alfio Ferrara, Stefano Montanelli, Martin Ruskov

Contextual word embedding techniques for semantic shift detection are receiving more and more attention. In this paper, we present What is Done is Done (WiDiD), an incremental approach to semantic shift detection based o…

ClusteringSemantic Shift Detection

Words are Malleable: Computing Semantic Shifts in Political and Media Discourse

2017-11-15 · Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut 외

Recently, researchers started to pay attention to the detection of temporal shifts in the meaning of words. However, most (if not all) of these approaches restricted their efforts to uncovering change over time, thus neg…

SEKE: Specialised Experts for Keyword Extraction

2024-12-18 · Matej Martinc, Hanh Thi Hong Tran, Senja Pollak, Boshko Koloski

Keyword extraction involves identifying the most descriptive words in a document, allowing automatic categorisation and summarisation of large quantities of diverse textual data. Relying on the insight that real-world ke…

DescriptiveKeyword ExtractionMixture-of-Experts

Toward Effective Multi-Domain Rumor Detection in Social Networks Using Domain-Gated Mixture-of-Experts

2026-01-28 · Mohadeseh Sheikhqoraei, Zainabolhoda Heshmati, Zeinab Rajabi, Leila Rabiei arxiv

Social media platforms have become key channels for spreading and tracking rumors due to their widespread accessibility and ease of information sharing. Rumors can continuously emerge across diverse domains and topics, o…