https://www.bibsonomy.org/user/hangdongBibSonomy RSS Feed for /user/hangdonghttps://fortune.com/2025/07/20/uk-health-service-ai-tool-false-diagnoses-patient-screening-nhs-anima-health-annie/hangdong2025-08-12T22:41:51+02:00NHS diagnosis digital-health gen-AI <a itemprop="url" data-versiondate="2025-08-12T22:41:51+02:00" href="https://fortune.com/2025/07/20/uk-health-service-ai-tool-false-diagnoses-patient-screening-nhs-anima-health-annie/" rel="nofollow" class="description-link">https://fortune.com/2025/07/20/uk-health-service-ai-tool-false-diagnoses-patient-screening-nhs-anima-health-annie/</a>https://journals.sagepub.com/doi/full/10.1177/17248035251363882hangdong2025-08-11T09:57:19+02:001d-arc abstract-reasoning-corpus inductive-reasoning llm myown program-synthesis <a itemprop="url" data-versiondate="2025-08-11T09:57:19+02:00" href="https://journals.sagepub.com/doi/full/10.1177/17248035251363882" rel="nofollow" class="description-link">https://journals.sagepub.com/doi/full/10.1177/17248035251363882</a>https://christophm.github.io/interpretable-ml-book/hangdong2025-07-19T20:47:11+02:00XAI explainability interpretability machine-learning shap <a itemprop="url" data-versiondate="2025-07-19T20:47:11+02:00" href="https://christophm.github.io/interpretable-ml-book/" rel="nofollow" class="description-link">https://christophm.github.io/interpretable-ml-book/</a>https://www.google.co.uk/books/edition/Oliver_Twist_Or_The_Parish_Boy_s_Progres/PwI3AAAAYAAJ?hl=en&gbpv=0hangdong2025-04-28T23:09:58+02:00literature oliver-twist <a itemprop="url" data-versiondate="2025-04-28T23:09:58+02:00" href="https://www.google.co.uk/books/edition/Oliver_Twist_Or_The_Parish_Boy_s_Progres/PwI3AAAAYAAJ?hl=en&amp;gbpv=0" rel="nofollow" class="description-link">https://www.google.co.uk/books/edition/Oliver_Twist_Or_The_Parish_Boy_s_Progres/PwI3AAAAYAAJ?hl=en&amp;gbpv=0</a>We investigate the task of inserting new concepts extracted from texts into an ontology using language models. We explore an approach with three steps: edge search which is to find a set of candidate locations to insert (i.e., subsumptions between concepts), edge formation and enrichment which leverages the ontological structure to produce and enhance the edge candidates, and edge selection which eventually locates the edge to be placed into. In all steps, we propose to leverage neural methods, where we apply embedding-based methods and contrastive learning with Pre-trained Language Models (PLMs) such as BERT for edge search, and adapt a BERT fine-tuning-based multi-label Edge-Cross-encoder, and Large Language Models (LLMs) such as GPT series, FLAN-T5, and Llama 2, for edge selection. We evaluate the methods on recent datasets created using the SNOMED CT ontology and the MedMentions entity linking benchmark. The best settings in our framework use fine-tuned PLM for search and a multi-label Cross-encoder for selection. Zero-shot prompting of LLMs is still not adequate for the task, and we propose explainable instruction tuning of LLMs for improved performance. Our study shows the advantages of PLMs and highlights the encouraging performance of LLMs that motivates future studies.https://videolectures.net/videos/eswc2024_dong_concept_placementhangdong2025-04-19T10:15:03+02:00llm myown ontologies ontology_learning plm snomedct video <span itemprop="description">We investigate the task of inserting new concepts extracted from texts into an ontology using language models. We explore an approach with three steps: edge search which is to find a set of candidate locations to insert (i.e., subsumptions between concepts), edge formation and enrichment which leverages the ontological structure to produce and enhance the edge candidates, and edge selection which eventually locates the edge to be placed into. In all steps, we propose to leverage neural methods, where we apply embedding-based methods and contrastive learning with Pre-trained Language Models (PLMs) such as BERT for edge search, and adapt a BERT fine-tuning-based multi-label Edge-Cross-encoder, and Large Language Models (LLMs) such as GPT series, FLAN-T5, and Llama 2, for edge selection. We evaluate the methods on recent datasets created using the SNOMED CT ontology and the MedMentions entity linking benchmark. The best settings in our framework use fine-tuned PLM for search and a multi-label Cross-encoder for selection. Zero-shot prompting of LLMs is still not adequate for the task, and we propose explainable instruction tuning of LLMs for improved performance. Our study shows the advantages of PLMs and highlights the encouraging performance of LLMs that motivates future studies.</span>Featuring exclusive new work, Precious and Impossible gathers together over three decades of poetry from the T S Eliot Prize-winning Anthony Joseph. With an introduction by Lauri ScheyerFor over three decades, Anthony Joseph's work has explored the transnational vibrations of the African diaspora. Precious and Impossible brings together thirty years of Joseph's poetry and lyrics – cementing his status as one of our greatest living poets and polymaths'Joseph is both a faithful heir and an agnostic rebel; a Black poet haunted by Africa's past as well as a bilingual post-modernist amused by the possibilities of the future' Ali Alizadehhttps://www.google.co.uk/books/edition/Precious_Impossible_Selected_Poems/3Y8WEQAAQBAJ?hl=en&gbpv=0hangdong2025-02-27T12:59:20+01:00Anthony_Joseph african black poem <span itemprop="description">Featuring exclusive new work, Precious and Impossible gathers together over three decades of poetry from the T S Eliot Prize-winning Anthony Joseph. With an introduction by Lauri ScheyerFor over three decades, Anthony Joseph&#039;s work has explored the transnational vibrations of the African diaspora. Precious and Impossible brings together thirty years of Joseph&#039;s poetry and lyrics – cementing his status as one of our greatest living poets and polymaths&#039;Joseph is both a faithful heir and an agnostic rebel; a Black poet haunted by Africa&#039;s past as well as a bilingual post-modernist amused by the possibilities of the future&#039; Ali Alizadeh</span>https://www.simonandschuster.com/books/Bibliotherapy-in-the-Bronx/Emely-Rumble-LCSW/9781955905879hangdong2025-02-27T12:56:47+01:00bibliotherapy <a itemprop="url" data-versiondate="2025-02-27T12:56:47+01:00" href="https://www.simonandschuster.com/books/Bibliotherapy-in-the-Bronx/Emely-Rumble-LCSW/9781955905879" rel="nofollow" class="description-link">https://www.simonandschuster.com/books/Bibliotherapy-in-the-Bronx/Emely-Rumble-LCSW/9781955905879</a>https://www.insticc.org/node/TechnicalProgram/IC3K/2024/presentationDetails/130136hangdong2024-12-09T18:43:24+01:00KG Knowledge-graph-construction LLM kowledge-graph language-model literature literature-KG myown poster <a itemprop="url" data-versiondate="2024-12-09T18:43:24+01:00" href="https://www.insticc.org/node/TechnicalProgram/IC3K/2024/presentationDetails/130136" rel="nofollow" class="description-link">https://www.insticc.org/node/TechnicalProgram/IC3K/2024/presentationDetails/130136</a>https://aidanhogan.com/blog/index.php/2022/10/27/publishing-research-semantic-web/hangdong2024-12-08T14:21:44+01:00OA open-access publishing semantic-web <a itemprop="url" data-versiondate="2024-12-08T14:21:44+01:00" href="https://aidanhogan.com/blog/index.php/2022/10/27/publishing-research-semantic-web/" rel="nofollow" class="description-link">https://aidanhogan.com/blog/index.php/2022/10/27/publishing-research-semantic-web/</a>https://purple-plant-0f4023d0f.2.azurestaticapps.net/OMOPConceptSetshangdong2024-05-18T17:38:46+02:00ontology-mapping phenotyping terminologies <a itemprop="url" data-versiondate="2024-05-18T17:38:46+02:00" href="https://purple-plant-0f4023d0f.2.azurestaticapps.net/OMOPConceptSets" rel="nofollow" class="description-link">https://purple-plant-0f4023d0f.2.azurestaticapps.net/OMOPConceptSets</a>https://blog.dblp.org/2024/01/01/7-million-publications/hangdong2024-05-18T15:23:06+02:00dblp dblp-data knowledge-graph publication-data <a itemprop="url" data-versiondate="2024-05-18T15:23:06+02:00" href="https://blog.dblp.org/2024/01/01/7-million-publications/" rel="nofollow" class="description-link">https://blog.dblp.org/2024/01/01/7-million-publications/</a>https://opensource.org/deepdive/drafts/the-open-source-ai-definition-draft-v-0-0-8hangdong2024-05-17T11:10:45+02:00open-AI open-access open-science <a itemprop="url" data-versiondate="2024-05-17T11:10:45+02:00" href="https://opensource.org/deepdive/drafts/the-open-source-ai-definition-draft-v-0-0-8" rel="nofollow" class="description-link">https://opensource.org/deepdive/drafts/the-open-source-ai-definition-draft-v-0-0-8</a>https://neurosymbolic-ai-journal.com/paper/survey-neurosymbolic-visual-reasoning-scene-graphs-and-common-sense-knowledgehangdong2024-04-06T12:21:00+02:00computer-vision multi-modal-learning neuro-symbolic <a itemprop="url" data-versiondate="2024-04-06T12:21:00+02:00" href="https://neurosymbolic-ai-journal.com/paper/survey-neurosymbolic-visual-reasoning-scene-graphs-and-common-sense-knowledge" rel="nofollow" class="description-link">https://neurosymbolic-ai-journal.com/paper/survey-neurosymbolic-visual-reasoning-scene-graphs-and-common-sense-knowledge</a>https://github.com/jingcshi/bert_subsumptionhangdong2023-10-13T12:10:21+02:00e-commerce ontology_learning subsumption <a itemprop="url" data-versiondate="2023-10-13T12:10:21+02:00" href="https://github.com/jingcshi/bert_subsumption" rel="nofollow" class="description-link">https://github.com/jingcshi/bert_subsumption</a>http://videolectures.net/eswc2023_veseli_evaluating_language_models/hangdong2023-09-22T12:56:47+02:00eswc kbc kgc knowledge-base-completion lm <a itemprop="url" data-versiondate="2023-09-22T12:56:47+02:00" href="http://videolectures.net/eswc2023_veseli_evaluating_language_models/" rel="nofollow" class="description-link">http://videolectures.net/eswc2023_veseli_evaluating_language_models/</a>https://www.youtube.com/watch?v=vuKKubFaOjshangdong2023-09-22T12:55:10+02:00ontologies pinterest social-media taxonomy taxonomy-expansion <a itemprop="url" data-versiondate="2023-09-22T12:55:10+02:00" href="https://www.youtube.com/watch?v=vuKKubFaOjs" rel="nofollow" class="description-link">https://www.youtube.com/watch?v=vuKKubFaOjs</a>http://videolectures.net/eswc2023_van_erp_graphs/hangdong2023-08-15T12:35:57+02:00archives digital-humanities entities entity-linking erc-projects kgs knowledge-representation newspapers ontologies word-sense-disambiguation <a itemprop="url" data-versiondate="2023-08-15T12:35:57+02:00" href="http://videolectures.net/eswc2023_van_erp_graphs/" rel="nofollow" class="description-link">http://videolectures.net/eswc2023_van_erp_graphs/</a>https://zenodo.org/record/8147589hangdong2023-07-19T12:18:33+02:00futurology ontology semantic-web wisdom-web <a itemprop="url" data-versiondate="2023-07-19T12:18:33+02:00" href="https://zenodo.org/record/8147589" rel="nofollow" class="description-link">https://zenodo.org/record/8147589</a>https://underline.io/lecture/51425-horses-to-zebras-ontology-guided-data-augmentation-and-synthesis-for-icd-9-codinghangdong2023-06-14T14:49:48+02:00clinical-coding icd-10 multi-label_classification ontologies text-classification video <a itemprop="url" data-versiondate="2023-06-14T14:49:48+02:00" href="https://underline.io/lecture/51425-horses-to-zebras-ontology-guided-data-augmentation-and-synthesis-for-icd-9-coding" rel="nofollow" class="description-link">https://underline.io/lecture/51425-horses-to-zebras-ontology-guided-data-augmentation-and-synthesis-for-icd-9-coding</a>https://www.newscientist.com/article/2370923-chemists-are-teaching-gpt-4-to-do-chemistry-and-control-lab-robots/hangdong2023-05-06T10:52:43+02:00chemistry gpt-4 <a itemprop="url" data-versiondate="2023-05-06T10:52:43+02:00" href="https://www.newscientist.com/article/2370923-chemists-are-teaching-gpt-4-to-do-chemistry-and-control-lab-robots/" rel="nofollow" class="description-link">https://www.newscientist.com/article/2370923-chemists-are-teaching-gpt-4-to-do-chemistry-and-control-lab-robots/</a>