Exploring scientific literature by textual and image content using DRIFT

VA + Embeddings STAR: A State‐of‐the‐Art Report on the Use of Embeddings in Visual Analytics

“…The implementation was, however, extended to accommodate the free‐text detail categories and potential multiple references and URLs specified per survey entry. For instance, while the entry for DRIFT by Pocco et al is based on the 2022 journal article [PdSP * 22] identified during the literature search stage, another reference for the related conference paper [PPV * 21] is also mentioned in the browser entry. This might come across as a trivial implementation detail, but the aim here is to keep supporting and extending the survey data in the future for the benefit of the visualization research community, while promoting the cases of several successful applications of visual analytic approaches with embeddings that the respective authors might describe in a series of publications.…”

“…Visualization for NLP and CL Creating and using embeddings in NLP and CL is crucial for representing and capturing the context and content of words, phrases, sentences, and documents. VA + embedding techniques in this set focus on four themes: exploring the semantics and contextualization of embedding spaces [CTL18,LBT * 18,EAKC * 20,MWZ19,SSKEA21, GHM21, BN21, BCS22,VMZL22,LWZ * 23,MM23], active learning and interpretation for language models [LCSEK19, TWB * 20, SH20, ARCL21, LXW * 21, SKB * 21, SCR * 23], data‐driven information retrieval [CWDH09,BMS17,ZSHL18,KOK * 18,DMdO19, RSBV21, PdSP * 22, JWC * 23], and annotation tools [SJB * 17, BNL * 18,PKL * 18,MWJ22].…”