Add page for Patapsco

generate.py

@@ -396,6 +396,7 @@ def generate_index(out_dir, version, top_level_map):
 <li><a href="https://arxiv.org/pdf/2103.02280.pdf">ir_datasets SIGIR resource paper</a></li>
 <li>Using <kbd>ir_datasets</kbd> with&hellip;
 <a href="pyterrier.html">PyTerrier</a> &middot;
+<a href="patapsco.html">Patapsco</a> &middot;
 <a href="ir-measures.html">ir-measures</a> &middot;
 <a href="trec_eval.html">trec_eval</a> &middot;
 <a href="experimaestro.html">Experimaestro</a>
@@ -615,6 +616,9 @@ def hlb(c):
     template = Template(filename=os.path.join("templates", "pyterrier.html"))
     with page_template('pyterrier.html', out_dir, version, title='PyTerrier &amp; ir_datasets', include_irds_title=False) as out:
         out.write(template.render(hl=hl))
+    template = Template(filename=os.path.join("templates", "patapsco.html"))
+    with page_template('patapsco.html', out_dir, version, title='Patapsco &amp; ir_datasets', include_irds_title=False) as out:
+        out.write(template.render(hl=hl))
     template = Template(filename=os.path.join("templates", "ir-measures.html"))
     with page_template('ir-measures.html', out_dir, version, title='ir_measures &amp; ir_datasets', include_irds_title=False) as out:
         out.write(template.render(hl=hl, hlb=hlb))

templates/patapsco.html

@@ -0,0 +1,74 @@
+<p>
+<a href="https://github.com/hltcoe/patapsco">Patapsco</a> is a framework for running cross-language 
+infomration retrieval (CLIR) experiments developed by <a href="https://hltcoe.jhu.edu/">Human Language 
+Technlogy Center of Excellence (HLTCOE) at Johns Hopkins University. 
+</p>
+
+<p>
+To get started with Patapsco, see <a href="https://github.com/hltcoe/patapsco">this guide</a>.
+</p>
+
+<h2 class="underline">Basic Usage</h2>
+
+<p>
+Patapsco specifies the source of the collection via config files or config dictionaries in Python. 
+Please see <a href="https://github.com/hltcoe/patapsco/blob/master/samples/configs/irds_test.yml"> this 
+example config file</a> for reference. 
+</p>
+
+<p>
+For both <kbd>documents</kbd>, <kbd>topics</kbd> and <kbd>scores</kbd> sections, use <kbd>irds</kbd> 
+as the <kbd>format</kbd> in the <kbd>input</kbd> subsection to tell Pataspco to use <kbd>ir_datasets</kbd> 
+and specify the dataset name at <kbd>path</kbd>. The <kbd>lang</kbd> value has to match the language 
+information provided by <kbd>ir_datasets</kbd> through <kbd>dataset.docs_lang()</kbd> and
+<kbd>dataset.queries_lang()</kbd>. Note that Patapsco uses the 3-letter ISO 639-3 language codes,
+whereas ir_datasets provides two-letter ISO 639-1 language codes.
+</p>
+
+${hl('''
+documents:
+  input:
+    format: irds
+    lang: zho
+    path: clirmatrix/zh/bi139-base/en/dev
+  process:
+    inherit: text
+  output: true
+
+topics:
+  input:
+    format: irds
+    lang: eng
+    source: original
+    encoding: utf8
+    path: clirmatrix/zh/bi139-base/en/dev
+
+score:
+  input:
+    format: irds
+    path: clirmatrix/zh/bi139-base/en/dev
+''')}
+
+<p>
+This YAML config file can also be specified as a Python dictionary. Please refer to the 
+documentation of Pataspco for further information.
+</p>
+
+<table>
+<tr><th>Patapsco's...</th><th>Corresponds to...</th><th>Notes</th></tr>
+<tr><td><kbd>documents</kbd></td><td><kbd>docs</kbd></td><td></td></tr>
+<tr><td><kbd>documents.input.path</kbd></td><td>dataset's ID</td><td></td></tr>
+<tr><td><kbd>documents.input.lang</kbd></td><td><kbd>dataset.docs_lang()</kbd></td><td>Need to convert from ISO 639-1 to ISO 639-3</td></tr>
+<tr><td><kbd>documents.process.inherit</kbd></td><td>the doc's field representing the text to use</td><td></td></tr>
+<tr><td><kbd>topics</kbd></td><td><kbd>queries</kbd></td><td></td></tr>
+<tr><td><kbd>topics.input.path</kbd></td><td>dataset's ID</td><td></td></tr>
+<tr><td><kbd>topics.input.lang</kbd></td><td><kbd>dataset.queries_lang()</kbd></td><td>Need to convert from ISO 639-1 to ISO 639-3</td></tr>
+<tr><td><kbd>score</kbd></td><td><kbd>qrels</kbd></td><td></td></tr>
+<tr><td><kbd>score.input.path</kbd></td><td>dataset's ID</td><td></td></tr>
+</table>
+
+<h2 class="underline">Further Information</h2>
+
+<ul>  
+  <li><a href="https://github.com/hltcoe/patapsco">Patapsco GitHub</a></li>
+</ul>