Translingual Document Representations from Discriminative Projections

By John C. Platt, Kristina Toutanova, Wen-tau Yih. 2010

118 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jianfeng Gao
2. Li Deng
3. Yoshua Bengio
4. Xiaodong He
5. Wen-tau Yih
6. Zhe Gan
7. Mohit Bansal
8. Dong Yu

Citations in the corpus

• Multi-Relational Latent Semantic Analysis (2013, background): “…a wide variety of NLP and IR applications, such as document clustering (Xu et al., 2003) and cross-lingual document retrieval (Dumais et al., 1997; Platt et al., 2010) at the document level and sentential semantics (Guo and Diab, 2012; Guo and Diab, 2013) and syntactic parsing (Socher et al.,…”
• Learning Continuous Phrase Representations for Translation Modeling (2014, background): “…variants of such models for cross-lingual scenarios have been proposed so that words in different languages are projected into the shared latent vector space (Dumais et al. 1997; Platt et al. 2010; Vinokourov et al. 2002; Yih et al. 2011; Gao et al. 2011; Huang et al. 2013; Zou et al. 2013).”
• Modeling Interestingness with Deep Neural Networks (2014, neutral): “Recently, these models have been extended to handle cross-lingual cases, where there are pairs of corresponding documents in different languages (e.g., Dumais et al. 1997; Gao et al. 2011; Platt et al. 2010; Yih et al. 2011).”
• Learning Semantic Representations for the Phrase Translation Model (2013, background): “As a result, variants of such models for crosslingual scenarios have been proposed [7, 9, 22, 26] where documents in different languages are projected into the shared latent concept space.”
• A framework for analyzing semantic change of words across time (2014, methodology): “Following [23], we compute the term-term correlation matrix C where each term is a conjunction of word w and the decade i.”
• Learning Discriminative Projections for Text Similarity Measures (2011, methodology): “Our approach is compared with most methods studied in (Platt et al., 2010), including the best per-”
• Learning deep structured semantic models for web search using clickthrough data (2013, background): “Latent semantic models such as latent semantic analysis (LSA) are able to map a query to its relevant documents at the semantic level where lexical matching often fails (e.g., [6][15][2][8][21]).”
• A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval (2014, background): “For example, latent semantic models such as latent semantic analysis (LSA) are able to map a query to its relevant documents at the semantic level where lexical matching often fails (e.g., [9][10][31]).”
• Polarity Inducing Latent Semantic Analysis (2012, methodology): “Because LSA is closely related to principle component analysis (PCA), extensions of PCA such as canonical correlation analysis (CCA) and oriented principle component analysis (OPCA) can leverage the labeled data and produce the projection matrix through general eigen-decomposition (Platt et al., 201”
• Clickthrough-based latent semantic models for web search (2011, background): “This section reviews previous approaches to bridging the lexical gap between queries and documents for IR.”