This study proposes the bilingual segmented topic model (BiSTM), which hierarchically models
documents by treating each document as a set of segments, eg, sections. While previous …

The cross-lingual topic analysis aims at extracting latent topics from corpora of different
languages. Early approaches rely on high-cost multilingual resources (eg, a parallel corpus), …

… cross-language topic modeling, such as with Bi-LSTM (Li 2017), bilingual context-citation
embedding (Tang 2014), BiLDA (Mimno 2009), and BiSTM (Bilingual Segmented Topic Model)…

… Tang 2014), BiLDA (Mimno 2009), and BiSTM (Bilingual Segmented Topic Model), which
makes use of aligned segments within documents (Tamura 2016). These methods could be …

In my welcome to participants in this year’s conference handbook, I especially welcomed
those for which it was their first ACL. I expressed the hope that the conference fulfilled their …

Deep representation learning of domain topics was used to build a topic alignment model (TAM)
with integrated bilingual word embedding. The semantic alignment lexicon was …

… Abstract: This paper proposes the bilingual segmented topic model (BiSTM), which
hierarchically models documents by treating each document as a set of segments, eg, sections. …

: 在主题深度表示学习的基础上, 该文提出了一种融合双语词嵌入的主题对齐模型(topic alignment
model, TAM), 通过双语词嵌入扩充语义对齐词汇词典, 在传统双语主题模型基础上设计辅助…