section 3.3 in paper about crosslingualcontextualemb HOT 4 CLOSED

Hi,
footnote 3 is more a technical detail that doesn't necessarily refer to different "meanings". I admit that the text there is a bit confusing, sorry.
Regarding the intuition of figure 2, you are correct about the structure of the dictionary. The intuition is, the way I see it (and supported by some qualitative examples), that the anchor of "bear" translates to around the center of the translations of the different "meanings". Due to the orthogonality of the alignment matrix, the internal relations (in the same language) between the contextual incidents are preserved, resulting in point clouds related to the contextual embeddings that are aligned with the "meanings" of the translations.
You should also take into account the overall space of embeddings (e.g. clustering animals and verbs separately) and the objective of the alignment that tries to reduce the distance between word pairs translations (e.g. pairs of animals translations and pairs of verbs translations).

You can also check out the slides and video from the conference for some visualizations.

from crosslingualcontextualemb.

Appreciate your detailed response.

from crosslingualcontextualemb.

can you specify how the dictionary was created for the supervised anchored alignment process?

from crosslingualcontextualemb.

Hi,
We used the dictionary from facebook's MUSE repo. It was created using some Facebook internal tools.

from crosslingualcontextualemb.