{"id":69,"date":"2024-04-08T16:11:30","date_gmt":"2024-04-08T14:11:30","guid":{"rendered":"https:\/\/www.liita.it\/?page_id=69"},"modified":"2026-09-01T11:47:58","modified_gmt":"2026-09-01T09:47:58","slug":"data","status":"publish","type":"page","link":"https:\/\/www.liita.it\/?page_id=69","title":{"rendered":"Data and Tools"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\">Milestone 1: Building the Lemma Bank<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">The first phase of the LiITA: Linking Italian project focusses on building a Lemma Bank from existing Italian lemma sets that will be meticulously selected and compared. The Lemma Bank is available as Linked Open Data, adhering to the widely accepted vocabulary outlined in the OntoLex-Lemon model for describing lexical resources: <\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Browse the Lemma Bank: <a href=\"https:\/\/liita-lod.github.io\/query-interface\/\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/liita-lod.github.io\/query-interface\/<\/a><\/li>\n\n\n\n<li>View: <a href=\"http:\/\/liita.it\/data\/id\/lemma\/LemmaBank\">http:\/\/liita.it\/data\/id\/lemma\/LemmaBank<\/a><\/li>\n\n\n\n<li>Download: <a href=\"https:\/\/github.com\/LiITA-LOD\/LiITA_LemmaBank\">https:\/\/github.com\/LiITA-LOD\/LiITA_LemmaBank<\/a><\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">Milestone 2: Linking the Resources<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Access the data through our <a href=\"https:\/\/www.liita.it\/?page_id=158\" data-type=\"page\" data-id=\"158\">SPARQL<\/a> endpoint.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The second phase revolves around integrating a set of freely available Italian linguistic resources with the Knowledge Base. <\/p>\n\n\n\n<h4 class=\"wp-block-heading\">Lexical Resources<\/h4>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary>CompL-it<\/summary>\n<p class=\"wp-block-paragraph\">Computational Lexicon for Italian. See <a href=\"http:\/\/hdl.handle.net\/20.500.11752\/ILC-1007\" data-type=\"link\" data-id=\"http:\/\/hdl.handle.net\/20.500.11752\/ILC-1007\">http:\/\/hdl.handle.net\/20.500.11752\/ILC-1007<\/a> for more details on the resource. View: (<a href=\"https:\/\/dspace-clarin-it.ilc.cnr.it\/repository\/xmlui\/handle\/20.500.11752\/ILC-1007\">https:\/\/dspace-clarin-it.ilc.cnr.it\/repository\/xmlui\/handle\/20.500.11752\/ILC-1007<\/a>), download ttl (<a href=\"https:\/\/dspace-clarin-it.ilc.cnr.it\/repository\/xmlui\/bitstream\/handle\/20.500.11752\/ILC-1007\/complit.ttl.gz?sequence=1&amp;isAllowed=y\">https:\/\/dspace-clarin-it.ilc.cnr.it\/repository\/xmlui\/bitstream\/handle\/20.500.11752\/ILC-1007\/complit.ttl.gz?sequence=1&amp;isAllowed=y<\/a>). <br><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n<\/details>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary>Vocabolario della Lingua Parmigiana<br><\/summary>\n<p class=\"wp-block-paragraph\">A bilingual lexicon having Italian entries and the corresponding translations in Parmigiano, edited by Umberto Pavarini and Gruppo di Lavoro Memento Mori. View: (<a href=\"https:\/\/liita.it\/data\/id\/DialettoParmigiano\/lemma\/LemmaBank.html\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/liita.it\/data\/id\/DialettoParmigiano\/lemma\/LemmaBank.html<\/a>), download ttl (<a href=\"https:\/\/github.com\/LiITA-LOD\/LocalVarieties\/tree\/main\/Parmigiano\" target=\"_blank\" rel=\"noreferrer noopener\">linkhttps:\/\/github.com\/LiITA-LOD\/LocalVarieties\/tree\/main\/Parmigiano<\/a>).<\/p>\n<\/details>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary>Sicilian-Italian Lexicon<\/summary>\n<p class=\"wp-block-paragraph\">A Sicilian-Italian lexicon extracted from&nbsp;<a href=\"https:\/\/scn.wiktionary.org\/wiki\/P%C3%A0ggina_principali\">wikizziunariu<\/a>.<br>View: <a href=\"https:\/\/liita.it\/data\/id\/LexicalResources\/DialettoSiciliano\/Wikizziunariu.html\">https:\/\/liita.it\/data\/id\/LexicalResources\/DialettoSiciliano\/Wikizziunariu.html<\/a><br>Download ttl: <a href=\"https:\/\/github.com\/LiITA-LOD\/LocalVarieties\/tree\/main\/Siciliano\">https:\/\/github.com\/LiITA-LOD\/LocalVarieties\/tree\/main\/Siciliano<\/a>.<\/p>\n<\/details>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary>Sentix<br><\/summary>\n<p class=\"wp-block-paragraph\">Sentix is an&nbsp;<strong>affective lexicon for the Italian language<\/strong>, incorporating <strong>63,660 entries<\/strong>, with associated&nbsp;<strong>polarity scores<\/strong>&nbsp;(ranging from -1 to +1) and&nbsp;<strong>categorical polarity classifications<\/strong>&nbsp;(Positive, Neutral, Negative).<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n<\/details>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary>ELIta<\/summary>\n<p class=\"wp-block-paragraph\"><strong>Emotion Lexicon for Italian<\/strong>, where words are annotated for basic emotions with scores from 0 to 1 and the emotion dimensions from 1 to 9.<\/p>\n<\/details>\n\n\n\n<h4 class=\"wp-block-heading\">Textual Resources<\/h4>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary>Luigi Pirandello&#8217;s Novellas<\/summary>\n<p class=\"wp-block-paragraph\">This corpus contains a series of <strong>short stories<\/strong> by <strong>Luigi Pirandello<\/strong>. The texts have been <strong>tokenised<\/strong>, <strong>pos-tagged<\/strong> and <strong>lemmatised<\/strong> specifically for linking to the LiITA Knowledge Base. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">View: <a href=\"https:\/\/liita.it\/data\/id\/corpora\/Pirandello\/id\/corpus.html\">https:\/\/liita.it\/data\/id\/corpora\/Pirandello\/id\/corpus.html<\/a><\/p>\n<\/details>\n\n\n\n<h3 class=\"wp-block-heading\">Milestone 3: Developing Tools<\/h3>\n\n\n\n<p class=\"has-text-align-left wp-block-paragraph\">The project&#8217;s third phase brings forth the development of a tool that empowers resource providers to automatically connect their data to the Lemma Bank. Coupled with the project&#8217;s commitment to utilising established vocabularies for knowledge representation as LOD, this tool promotes an open-ended approach. As a result, the knowledge base becomes readily extensible and adaptable for future enrichment and expansion.<\/p>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary><strong>\u00a0NL2SPARQL<\/strong><\/summary>\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/github.com\/tonazzog\/nl2sparql\" target=\"_blank\" rel=\"noopener\">https:\/\/github.com\/tonazzog\/nl2sparql<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A Retrieval-Augmented Generation system for querying LiITA in natural language: semantic retrieval over few-shot examples guides an LLM to generate SPARQL queries, with syntax validation, execution, and automatic error correction. Includes an agentic (ReAct-based) variant and an MCP server for integration with external clients.<\/p>\n<\/details>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary><strong>PRISMA<\/strong><\/summary>\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/github.com\/tonazzog\/prisma-per-liita\" target=\"_blank\" rel=\"noopener\">https:\/\/github.com\/tonazzog\/prisma-per-liita<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A natural-language interface to LiITA where an LLM is used only to classify user intent, while SPARQL generation is fully deterministic and template-based, ensuring transparent and structurally correct queries.<\/p>\n<\/details>\n\n\n\n<details class=\"wp-block-details is-layout-flow wp-block-details-is-layout-flow\"><summary><strong>MoSAIC<\/strong><\/summary>\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/github.com\/tonazzog\/mosaic-liita\" target=\"_blank\" rel=\"noopener\">https:\/\/github.com\/tonazzog\/mosaic-liita<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A block-based system that assembles SPARQL queries over LiITA from reusable pattern components, offering both a fully deterministic rule-based mode and an agentic mode where an LLM decomposes the query into structured operations.<\/p>\n<\/details>\n","protected":false},"excerpt":{"rendered":"<p>Milestone 1: Building the Lemma Bank The first phase of the LiITA: Linking Italian project focusses on building a Lemma Bank from existing Italian lemma sets that will be meticulously selected and compared. The Lemma Bank is available as Linked Open Data, adhering to the widely accepted vocabulary outlined in the OntoLex-Lemon model for describing [&hellip;]<\/p>\n","protected":false},"author":4,"featured_media":165,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-69","page","type-page","status-publish","has-post-thumbnail","hentry"],"_links":{"self":[{"href":"https:\/\/www.liita.it\/index.php?rest_route=\/wp\/v2\/pages\/69","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.liita.it\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.liita.it\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.liita.it\/index.php?rest_route=\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/www.liita.it\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=69"}],"version-history":[{"count":26,"href":"https:\/\/www.liita.it\/index.php?rest_route=\/wp\/v2\/pages\/69\/revisions"}],"predecessor-version":[{"id":287,"href":"https:\/\/www.liita.it\/index.php?rest_route=\/wp\/v2\/pages\/69\/revisions\/287"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.liita.it\/index.php?rest_route=\/wp\/v2\/media\/165"}],"wp:attachment":[{"href":"https:\/\/www.liita.it\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=69"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}