Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
project:hds_out_of_the_box [2016/07/04 12:43] – [Named Entity Recognition] joschne | project:hds_out_of_the_box [2016/07/04 15:12] (current) – [Exploring bibliographic enrichment with OpenRefine] pmau | ||
---|---|---|---|
Line 1: | Line 1: | ||
===== Historical Dictionary of Switzerland Out of the Box ===== | ===== Historical Dictionary of Switzerland Out of the Box ===== | ||
- | The [[http:// | + | The [[http:// |
- | The HDS digital edition comprises about XXXX articles organized in 4 main headword groups: \\ | + | The HDS digital edition comprises about 36.000 |
- Biographies, | - Biographies, | ||
- Families, \\ | - Families, \\ | ||
- | - Geographical | + | - Geographical |
- Thematical contributions. | - Thematical contributions. | ||
- | Beyond the encyclopaedic description of entities/ | + | Beyond the encyclopaedic description of entities/ |
Line 17: | Line 17: | ||
We have the following data:\\ | We have the following data:\\ | ||
- | - [[http:// | + | |
- | - [[http:// | + | * bibliographic references of HDS articles\\ |
- | - bibliographic references of HDS articles\\ | + | * article titles\\ |
+ | * [[http:// | ||
| | ||
===== Goals ===== | ===== Goals ===== | ||
- | Our projects revolve around **Linking | + | Our projects revolve around **linking |
- | + | ||
- | ** 1. Entity Linking towards HDS** | + | |
- | + | ||
- | The objective is to link named entity mentions discovered in historical Swiss newspapers to their correspondant HDS articles. | + | |
- | ** 2. Exploring reference citation of HDS articles** | + | - **Entity linking towards |
- | The objective is to reconcile HDS bibliographic data with SwissBib. | + | - **Exploring reference citation of HDS articles**\\ |
Line 52: | Line 50: | ||
- working with a more refined NER output which comprises information about name components (first, middle,last names)\\ | - working with a more refined NER output which comprises information about name components (first, middle,last names)\\ | ||
+ | === Some statistics === | ||
+ | In the 23.622 articles of the year 1914 in «Le Temps digital archive» we linked 90.603 entities pointing to 1.417 articles of the «Historical Dictionary of Switzerland». | ||
- | === Showing Linked Named Entities | + | {{: |
+ | |||
+ | |||
+ | === Web Interface | ||
We developed a simple web interface for searching in the corpus and displaying the texts with the links.\\ | We developed a simple web interface for searching in the corpus and displaying the texts with the links.\\ | ||
+ | It consists of 3 views: | ||
+ | |||
- | {{ : | + | 1. Home\\ |
- | {{ : | + | {{: |
- | {{ : | + | \\ |
+ | 2. Search\\ | ||
+ | {{: | ||
+ | \\ | ||
+ | 3. Article with links to HDS, Wikipedia and dbpedia\\ | ||
+ | {{: | ||
+ | \\ | ||
+ | === Further works === | ||
Further works would include:\\ | Further works would include:\\ | ||
- evaluate and improve method.\\ | - evaluate and improve method.\\ | ||
Line 67: | Line 79: | ||
- | ===== Bibliographic | + | ===== Bibliographic |
We work on the list of references in all articles of the HDS, with three goals: | We work on the list of references in all articles of the HDS, with three goals: | ||
- | - Finding all the sources which are cited in the HDS (several sources are cited multiple times). | + | - Finding all the sources which are cited in the HDS (several sources are cited multiple times) |
- | - Link all the sources with the SwissBib catalog, if possible. | + | - Link all the sources with the SwissBib catalog, if possible |
- | - Interactively explore the citation | + | - Interactively explore the citation |
- | The dataset: lists of references in every HDS article: | + | The dataset |
{{: | {{: | ||
Line 193: | Line 205: | ||
(note that the parentheses around " | (note that the parentheses around " | ||
+ | |||
+ | === Further works === | ||
+ | This is only the first step of a more general work inside the HDS:\\ | ||
+ | * identify precisely each notice in an article (ID attribute to generate)\\ | ||
+ | * collect references with a separation by language\\ | ||
+ | * clean and refine the collected data\\ | ||
+ | * setup a querying workflow that keeps the ID of the matched target in a reference catalog\\ | ||
+ | * replace each matching occurence in the HDS article by a reference to an external catalog\\ | ||
+ | |||
===== Team ===== | ===== Team ===== | ||