Combining Heterogeneous Models for Measuring Relational Similarity

By Alisa Zhila, Wen-tau Yih, Christopher Meek, Geoffry Zweig, Tomas Mikolov. 2013

57 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

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

In Natural Language Processing

1. Jianfeng Gao
2. Yoav Goldberg
3. Zhiyuan Liu
4. Mohit Bansal
5. Maosong Sun
6. Wen-tau Yih
7. Omer Levy
8. Luke S. Zettlemoyer

In Representation & Self-Supervised Learning

1. Yoav Goldberg
2. Omer Levy
3. Mohammad Taher Pilehvar
4. Zhiyuan Liu
5. Jianfeng Gao
6. Maosong Sun
7. José Camacho-Collados
8. Li Deng

Citations in the corpus

• Distributed Representations of Sentences and Documents (2014, neutral): “…language processing tasks such as language modeling (Bengio et al., 2006; Mikolov, 2012), natural language understanding (Collobert & Weston, 2008; Zhila et al., 2013), statistical machine translation (Mikolov et al., 2013b; Zou et al., 2013), image understanding (Frome et al., 2013) and…”
• Efficient Estimation of Word Representations in Vector Space (2013, methodology): “The publicly available RNN vectors were used together with other techniques to achieve over 50% increase in Spearman’s rank correlation over the previous best result [28].”
• Multi-Relational Latent Semantic Analysis (2013, background): “Similarly, to measure whether two word pairs have the same relation, Zhila et al. (2013) proposed to combine heterogeneous models, which achieved state-of-the-art performance.”
• Linguistic Regularities in Sparse and Explicit Word Representations (2014, methodology): “…of king , man and woman : queen ≈ king − man + woman The recovery of relational similarities using vector arithmetic on RNN-embedded vectors was evaluated on many relations, achieving state-of-the-art results in relational similarity identification tasks (Mikolov et al., 2013c; Zhila et al., 2013).”
• Learning Semantic Representations for the Phrase Translation Model (2013, background): “2011), the byproduct of these models, the low-dimensional realvalued vector of each word, also captures both syntactic and semantic regularities in languages (Mikolov et al. 2013; Zhila et al. 2013).”
• SensEmbed: Learning Sense Embeddings for Word and Relational Similarity (2015, methodology): “Finally, we show the performance of Com (Zhila et al., 2013), a system that combines Word2vec, lexical patterns, and knowledge base information.”
• Question Answering Using Enhanced Lexical Semantic Models (2013, methodology): “panion paper (Zhila et al., 2013), where a subset of the data is to measure the degree of two words having a class-inclusion relation.”
• Quantifying Similarity between Relations with Fact Distribution (2019, methodology): “For identifying correlation and distinction between different semantic relations so as to support learning semantic similarity, various methods have attempted to measure relational similarity (Turney, 2005, 2006; Zhila et al., 2013; Pedersen, 2012; Rink and Harabagiu, 2012; Mikolov et al., 2013b,a).”