> For the complete documentation index, see [llms.txt](https://tracer.gitbook.io/manual/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://tracer.gitbook.io/manual/beta/babelnet-api.md).

# BabelNet API

As well as using WordNets for synonym look-up, we can use the [BabelNet API](http://babelnet.org/) to generate lists of hyponyms, cohyponyms and hypernyms.

The BabelNet look-up script can be started with the following command:

```
java -Xmx70g -cp tracer.jar eu.etrap.tracer.preprocessing.external.semantic.BabelNetTestMain ../lemma-list.txt EN >babelnet-queries.log
```

Where:

* `-Xmx70g` defines the memory to be used on the server; with a 70 gigabyte memory the BabelNet API look-up can take up to three days to compute.
* `lemma-list.txt` (a better file name might be `lemma-babelnet.txt`) is a modified version of TRACER's `lemma.txt` file containing only the base-form of every word in the text and its PoS tag (so, a two column file separated by a TAB). Place the `lemma-list.txt` in the TRACER's `data/corpora/...` directory and define its path in the command above.
* `babelnet-queries.log` is the log.

The script crunches two parameters: the `lemma-list.txt` and the language code (e.g. `EN` if you are working with English texts, `DE` if you are working with German texts, etc.). All generated files will be placed in the TRACER directory.

With `cat babelnet-queries.log | grep "PROCESSING WORD" | wc -l` you see the total number of processed words out of the total number of base-forms in `lemma-list.txt`.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://tracer.gitbook.io/manual/beta/babelnet-api.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.