Ensembling Transformers for Cross-domain Automatic Term Extraction

Tran, Hanh Thi Hong; Martinc, Matej; Pelicon, Andraž; Doucet, Antoine; Pollak, Senja

doi:10.1007/978-3-031-21756-2_7

Cited by 6 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“….])' (Tran et al, 2022b) or 'The results [of ATE] can either be used directly to facilitate term management for, e.g., terminologists and translators, or as a preprocessing step for other tasks within natural language processing (NLP) [. .…”

Section: Discussionmentioning

confidence: 99%

“…In particular, we found six papers that used the same dataset, the Annotated Corpora for Term Extraction Research (ACTER) dataset. 6 The authors of the papers Tran et al (2022a) and Tran et al (2022b) compare the multilingual learning to the monolingual learning in the cross-domain sequence-labeling term extraction task (Gooding and Kochmar, 2019). They examine the cross-lingual effect of rich-resource training language over fewer resources, such as Slovenian.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A systematic review of Automatic Term Extraction: What happened in 2022?

Nunzio

Marchesin

Silvello

2023

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

Automatic Term Extraction (ATE) systems have been studied for many decades as, among other things, one of the most important tools for tasks such as information retrieval, sentiment analysis, named entity recognition, and others. The interest in this topic has even increased in recent years given the support and improvement of the new neural approaches. In this article, we present a follow-up on the discussions about the pipeline that allows extracting key terms from medical reports, presented at MDTT 2022, and analyze the very last papers about ATE in a systematic review fashion. We analyzed the journal and conference papers published in 2022 (and partially in 2023) about ATE and cluster them into subtopics according to the focus of the papers for a better presentation.

show abstract

Section: Discussionmentioning

confidence: 99%