Panda: Prompt transfer meets knowledge distillation for efficient model adaptation
Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by
initializing the target prompt with the existing prompt trained on similar source tasks …
initializing the target prompt with the existing prompt trained on similar source tasks …
A neural network based price sensitive recommender model to predict customer choices based on price effect
SS Chen, B Choubey, V Singh - Journal of Retailing and Consumer …, 2021 - Elsevier
The impact of price and price changes should not be ignored while designing algorithms for
predicting customer choice. Consumer preferences should be modeled with consideration of …
predicting customer choice. Consumer preferences should be modeled with consideration of …
Modularized interaction network for named entity recognition
Abstract Although the existing Named Entity Recognition (NER) models have achieved
promising performance, they suffer from certain drawbacks. The sequence labeling-based …
promising performance, they suffer from certain drawbacks. The sequence labeling-based …
Pronounce differently, mean differently: a multi-tagging-scheme learning method for Chinese NER integrated with lexicon and phonetic features
C Mai, J Liu, M Qiu, K Luo, Z Peng, C Yuan… - Information Processing & …, 2022 - Elsevier
Abstract Named Entity Recognition (NER) aims to automatically extract specific entities from
the unstructured text. Compared with performing NER in English, Chinese NER is more …
the unstructured text. Compared with performing NER in English, Chinese NER is more …
E2S2: Encoding-enhanced sequence-to-sequence pretraining for language understanding and generation
Sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining
language models. However, the previous seq2seq pretraining models generally focus on …
language models. However, the previous seq2seq pretraining models generally focus on …
A reinforced active learning approach for optimal sampling in aspect term extraction for sentiment analysis
M Venugopalan, D Gupta - Expert Systems with Applications, 2022 - Elsevier
Aspect level sentiment analysis is a fine grained task in sentiment analysis which identifies
the product features from an opinionated piece of text and maps the sentiment towards each …
the product features from an opinionated piece of text and maps the sentiment towards each …
Learning relation prototype from unlabeled texts for long-tail relation extraction
Relation Extraction (RE) is a vital step to complete Knowledge Graph (KG) by extracting
entity relations from texts. However, it usually suffers from the long-tail issue. The training …
entity relations from texts. However, it usually suffers from the long-tail issue. The training …
Effective named entity recognition with boundary-aware bidirectional neural networks
Named Entity Recognition (NER) is a fundamental problem in Natural Language Processing
and has received much research attention. Although the current neural-based NER …
and has received much research attention. Although the current neural-based NER …
Towards Malay named entity recognition: an open-source dataset and a multi-task framework
Y Fu, N Lin, Z Yang, S Jiang - Connection Science, 2023 - Taylor & Francis
Named entity recognition (NER) is a key component of many natural language processing
(NLP) applications. The majority of advanced research, however, has not been widely …
(NLP) applications. The majority of advanced research, however, has not been widely …
EPIC: An epidemiological investigation of COVID-19 dataset for Chinese named entity recognition
P Li, G Zhou, Y Guo, S Zhang, Y Jiang… - Information Processing & …, 2024 - Elsevier
Since the outbreak of COVID-19, it has had a huge impact on the whole world. In China,
there have been a large number of epidemiological investigation reports in response to …
there have been a large number of epidemiological investigation reports in response to …