.. _fwflag_embedding_word_aggregation:
==============================
--embedding_word_aggregation
==============================
Switch
======

--embedding_word_aggregation AGG [AGG ...]

Description
===========

How to aggregate sub-word token embeddings back up to the word level, when extracting features with :doc:`fwflag_add_bert`/:doc:`fwflag_add_emb` (e.g. ``mean`` or ``concatenate``). Aliased as ``--word_aggregation``, ``--bert_word_aggregation``.

Argument and Default Value
==========================

One or more aggregation-method strings. Default: ``['mean']`` (``dlac.DEF_TRANS_WORD_AGGREGATION``).

Details
=======

Verified: ran successfully with ``concatenate`` as part of a full embedding-extraction command (the run got past feature computation and failed later only due to the unrelated :doc:`fwflag_embedding_keep_msg` SQLite issue — see the Known issue there).

Other Switches
==============

Required Switches:

* :doc:`fwflag_add_bert` or :doc:`fwflag_add_emb`

Example Commands
================

.. code-block:: bash

	dlatkInterface.py -d dla_tutorial -t msgs -c user_id --add_bert --embedding_word_aggregation concatenate