Magnus Sahlgren
Magnus Sahlgren is a person.
- See: Word-Space Model, Gavagai.
References
2010
- Magnus Sahlgren. https://www.sics.se/~mange/research.html
- QUOTE: My research is focused on how semantic knowledge is acquired and represented in man and machine. In particular, I study the distributional approach to semantic knowledge acquisition, in which semantic information is extracted from cooccurrence statistics. The underlying idea is that meanings are correlated with the distributional patterns of linguistic entities. This idea has its theoretical foundations in the structuralist movement.
My research concerns both the theoretical underpinnings of distributional semantics, and the practical implementations, and uses of the theories. On the theoretical side, I am interested in the concept of meaning, and in how meaning resides in language and in the mind. I am particularly fascinated by the works of Wittgenstein and Saussure, and by the more recent works of Lakoff and Johnson.
On the practical side, I am interested in the use of vector space models as tools for acquiring and representing the distributional information. Well known models include Latent Semantic Analysis (LSA) / Latent Semantic Indexing (LSI) and Hyperspace Analogue to Language (HAL). As an alternative to these established models, we have at SICS developed a technique called Random Indexing, which is based on Pentti Kanerva's research on sparse distributed representations. The technique is both computationally advantageous - it is scalable, efficient and adaptable - and cognitively justified. For an introduction to Random Indexing, consult the Random Indexing page. For reports on experiments using Random Indexing, consult the publications list.
- QUOTE: My research is focused on how semantic knowledge is acquired and represented in man and machine. In particular, I study the distributional approach to semantic knowledge acquisition, in which semantic information is extracted from cooccurrence statistics. The underlying idea is that meanings are correlated with the distributional patterns of linguistic entities. This idea has its theoretical foundations in the structuralist movement.
2006
- (Sahlgren, 2006) ⇒ Magnus Sahlgren. (2006). “The Word-Space Model: Using Distributional Analysis to Represent Syntagmatic and Paradigmatic Relations Between Words in High-dimensional Vector Spaces." PhD. Thesis, Stockholm: Institutionen för Lingvistik
2005
- (Sahlgren, 2005) ⇒ Magnus Sahlgren. (2005). “An Introduction to Random Indexing.” In: Methods and Applications of Semantic Indexing Workshop at the 7th International Conference on Terminology and Knowledge Engineering.