Enhancing keyphrase extraction from academic articles with their reference information

Zhang, Chengzhi; Zhao, Lei; Zhao, Mengyuan

doi:10.1007/s11192-021-04230-4

Cited by 15 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reformulating it as a ranking problem and marking top N entities as the KP, the research by Witten Ian et al [25], a popular approach, KEA uses statistical features like TF-IDF and Word’s First Occurrence Position (WFOP), whereas the work by Chengzhi Zhang et al [26] exploded into the usage of features such as TF-IDF and WFOP with length of token and linguistic features such as Part of Speech (POS) [27] tags to normalize the position and occurrence of the KP. A linear ranking SVM was used to rank the KP [28].…”

Section: Introductionmentioning

confidence: 99%

Keyphrase Identification Using Minimal Labeled Data with Hierarchical Context and Transfer Learning

Rohan

Hubig

Min

et al. 2023

Preprint

View full text Add to dashboard Cite

Interoperable clinical decision support system (CDSS) rules are a pathway to achieving interoperability which is a well-recognized challenge in health information technology. Building an ontology facilitates the creation of interoperable CDSS rules, which can be achieved by identifying the keyphrases (KP) from the existing literature. However, KP identification for labeling the data requires human expertise, consensus, and contextual understanding. This paper aims to present a semi-supervised framework for the CDSS using minimal labeled data based on hierarchical attention over the documents fused with domain adaptation approaches. Then, evaluate the effectiveness of KP identification with this framework. In the view of semi-supervised learning, our methodology toward building this framework outperforms the prior neural architectures by learning with document-level context, no explicit hand-crafted features, knowledge transfer from pre-trained models (on unlabeled corpus), and post-fine-tuning with smaller gold standard-labeled data. To the best of our knowledge, this is the first functional framework for the CDSS sub-domain to identify the KP, which is trained on limited labeled data. It contributes to the general natural language processing (NLP) architectures in areas such as clinical NLP, where manual data labeling is challenging.

show abstract

Section: Introductionmentioning

confidence: 99%

Keyphrase Identification Using Minimal Labeled Data with Hierarchical Context and Transfer Learning

Rohan

Hubig

Min

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The AlphaGo defeating the world champion of Go is the best example. However, in the field of natural language processing (NLP), due to the complexity and diversity of human languages, machines cannot fully understand human expressions in some tasks, e.g., machine translation (Lä ubli et al, 2020), summary generation (Sheela and Janet, 2021), keyphrase extraction (Zhang, Zhao, et al, 2022) and so on. Whether machines really possess a human-like way of thinking is worthy of in-depth exploration in this background.…”

Section: Introductionmentioning

confidence: 99%

“…machine translation (Läubli et al. , 2020), summary generation (Sheela and Janet, 2021), keyphrase extraction (Zhang et al. , 2022a) and so on.…”

Section: Introductionmentioning

confidence: 99%

Does attention mechanism possess the feature of human reading? A perspective of sentiment classification task

Zhao

Zhang

2022

AJIM

Self Cite

View full text Add to dashboard Cite

PurposeTo understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize the attention mechanism in deep learning models. But these studies lack to explain the rationality of this approach. Whether the attention mechanism possesses this feature of human reading needs to be explored.Design/methodology/approachThe authors conducted experiments on a sentiment classification task. Firstly, they obtained eye-tracking values from two open-source eye-tracking corpora to describe the feature of human reading. Then, the machine attention values of each sentence were learned from a sentiment classification model. Finally, a comparison was conducted to analyze machine attention values and eye-tracking values.FindingsThrough experiments, the authors found the attention mechanism can focus on important words, such as adjectives, adverbs and sentiment words, which are valuable for judging the sentiment of sentences on the sentiment classification task. It possesses the feature of human reading, focusing on important words in sentences when reading. Due to the insufficient learning of the attention mechanism, some words are wrongly focused. The eye-tracking values can help the attention mechanism correct this error and improve the model performance.Originality/valueOur research not only provides a reasonable explanation for the study of using eye-tracking values to optimize the attention mechanism but also provides new inspiration for the interpretability of attention mechanism.

show abstract

“…10 Among these methodologies, text summarization has emerged as an innovative solution to manage the phenomenon of information overload, 11 helping scholars to pinpoint the information they need. 12 Text summarization automatically identifies relevant information from one or more documents using two main approaches: extractive summarization, which involves selecting and extracting key sentences directly from the text, and abstractive summarization, which rewrites and condenses the input text into a shorter version while preserving the main ideas and reducing redundancy. 13,14 Relying on a combination of NLP, statistical, and machine learning techniques, artificial intelligence (AI) plays a crucial role in bringing academic research to a transformative era.…”

mentioning

confidence: 99%

Unveiling the Larsen effect in the scientific literature domain: Navigating quality amidst the artificial intelligence‐driven deluge

D'Aniello

2024

J Oral Pathology Medicine

View full text Add to dashboard Cite

The challenges faced by the massive increase in scientific publications draw parallels to the Larsen effect, where an amplified sound loop leads to escalating noise. This phenomenon has resulted in information overload, making it difficult for researchers to stay updated and identify significant findings. To address this, knowledge synthesis techniques are recommended. These methods help synthesize and visualize large bodies of literature, aiding researchers in navigating the expanding information landscape. Furthermore, artificial intelligence (AI) and natural language processing tools, such as text summarization, offer innovative solutions for managing information overload. However, the overuse of AI in producing scientific literature raises concerns about the quality and integrity of research. This manuscript highlights the need for balanced use of AI tools and collaborative efforts to maintain high‐quality scientific output while leveraging the benefits of extensive research.

show abstract

Enhancing keyphrase extraction from academic articles with their reference information

Cited by 15 publications

References 33 publications

Keyphrase Identification Using Minimal Labeled Data with Hierarchical Context and Transfer Learning

Keyphrase Identification Using Minimal Labeled Data with Hierarchical Context and Transfer Learning

Does attention mechanism possess the feature of human reading? A perspective of sentiment classification task

Unveiling the Larsen effect in the scientific literature domain: Navigating quality amidst the artificial intelligence‐driven deluge

Contact Info

Product

Resources

About