paper-with-me

Papers

Fine-tuning Pre-trained Contextual Embeddings for Citation Content Analysis in Scholarly Publication

2020-09-12 · Haihua Chen, Huyen Nguyen

Citation function and citation sentiment are two essential aspects of citation content analysis (CCA), which are useful for influence analysis, the recommendation of scientific publications. However, existing studies are mostly traditional machine learning methods, although deep learning techniques have also been explored, the improvement of the performance seems not significant due to insufficient training data, which brings difficulties to applications. In this paper, we propose to fine-tune pre-trained contextual embeddings ULMFiT, BERT, and XLNet for the task. Experiments on three public datasets show that our strategy outperforms all the baselines in terms of the F1 score. For citation function identification, the XLNet model achieves 87.2%, 86.90%, and 81.6% on DFKI, UMICH, and TKDE2019 datasets respectively, while it achieves 91.72% and 91.56% on DFKI and UMICH in term of citation sentiment identification. Our method can be used to enhance the influence analysis of scholars and scholarly publications.

📄 PDF Abstract BibTeX arXiv:2009.05836

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Embedding Dropout Embedding Dropout is equivalent to performing dropout on the embedding matrix at a word level, where the dropout is broadcast…
Activation Regularization Activation Regularization (AR), or $L\_{2}$ activation regularization, is regularization performed on activations as opposed to weights. It is usually used in conjunction with…
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Temporal Activation Regularization 설명 없음
Variational Dropout Variational Dropout is a regularization technique based on dropout, but uses a variational inference grounded approach. In…

Similar Papers 제목 키워드 기반

Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task

2020-05-01 · LREC 2020 5 · Md Tahmid Rahman Laskar, Jimmy Xiangji Huang, Enamul Hoque

Word embeddings that consider context have attracted great attention for various natural language processing tasks in recent years. In this paper, we utilize contextualized word embeddings with the transformer encoder fo…

Answer SelectionSentenceSentence SimilarityWord Embeddings

Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning

2025-05-20 · Tong Li, Jiachuan Wang, Yongqi Zhang, Shuangyin Li 외

Citation classification, which identifies the intention behind academic citations, is pivotal for scholarly analysis. Previous works suggest fine-tuning pretrained language models (PLMs) on citation classification datase…

Contrastive LearningDecoderSentence

Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification

2022-06-20 · Massimiliano Patacchiola, John Bronskill, Aliaksandra Shysheya, Katja Hofmann 외

Recent years have seen a growth in user-centric applications that require effective knowledge transfer across tasks in the low-data regime. An example is personalization, where a pretrained system is adapted by learning …

Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage Classification+1

Improved Biomedical Word Embeddings in the Transformer Era

2020-12-22 · Jiho Noh, Ramakanth Kavuluru

Biomedical word embeddings are usually pre-trained on free text corpora with neural methods that capture local and global distributional properties. They are leveraged in downstream tasks using various neural architectur…

SentenceWord EmbeddingsWord Similarity

Debiasing Pre-trained Contextualised Embeddings

2021-01-23 · EACL 2021 2 · Masahiro Kaneko, Danushka Bollegala

In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a f…

SentenceWord Embeddings