TAMI
====

.. py:module:: topmost.models.crosslingual.InfoCTM.TAMI



Module Contents
---------------



.. autoapisummary::


   topmost.models.crosslingual.InfoCTM.TAMI.TAMI





.. py:class:: TAMI(temperature, weight_MI, pos_threshold, trans_e2c, pretrain_word_embeddings_en, pretrain_word_embeddings_cn)

   Bases: :py:obj:`torch.nn.Module`


   InfoCTM: A Mutual Information Maximization Perspective of Cross-lingual Topic Modeling. AAAI 2023

   Xiaobao Wu, Xinshuai Dong, Thong Nguyen, Chaoqun Liu, Liangming Pan, Anh Tuan Luu


   .. py:attribute:: temperature


   .. py:attribute:: weight_MI


   .. py:attribute:: pos_threshold


   .. py:attribute:: pretrain_word_embeddings_en


   .. py:attribute:: pretrain_word_embeddings_cn


   .. py:attribute:: trans_e2c


   .. py:attribute:: trans_c2e


   .. py:attribute:: pos_trans_mask_en


   .. py:attribute:: pos_trans_mask_cn


   .. py:attribute:: neg_trans_mask_en


   .. py:attribute:: neg_trans_mask_cn


   .. py:method:: build_CVL_mask(embeddings)


   .. py:method:: translation_mask(mask, trans_dict_matrix)


   .. py:method:: compute_pos_neg(pretrain_word_embeddings_en, pretrain_word_embeddings_cn, trans_e2c, trans_c2e)


   .. py:method:: MutualInfo(anchor_feature, contrast_feature, mask, neg_mask)


   .. py:method:: forward(fea_en, fea_cn)