- Title
- Solving word analogies: A machine learning perspective
- Creator
- Lim, Suryani; Prade, Henri; Richard, Gilles
- Date
- 2019
- Type
- Text; Book chapter
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/183876
- Identifier
- vital:16382
- Identifier
-
https://doi.org/10.1007/978-3-030-29765-7_20
- Identifier
- ISBN:0302-9743
- Abstract
- Analogical proportions are statements of the form ‘a is to b as c is to d’, formally denoted . This means that the way a and b (resp. b and a) differ is the same as c and d (resp. d and c) differ, as revealed by their logical modeling. The postulates supposed to govern such proportions entail that when holds, then seven permutations of a, b, c, d still constitute valid analogies. It can also be derived that does not hold except if a=b. From a machine learning perspective, this provides guidelines to build training sets of positive and negative examples. We then suggest improved methods to classify word-analogies and also to solve analogical equations. Viewing words as vectors in a multi-dimensional space, we depart from the traditional parallelogram view of analogy to adopt a purely machine-learning approach. In some sense, we learn a functional definition of analogical proportions without assuming any pre-existing formulas. We mainly use the logical properties of proportions to define our training sets and to design proper neural networks, approximating the hidden relations. Using a GloVe embedding, the results we get show high accuracy and improve state of the art on words analogy-solving problems
- Publisher
- Cham: Springer International Publishing
- Relation
- Symbolic and Quantitative Approaches to Reasoning with Uncertainty Chapter 7 p. 238-250
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright Springer
- Reviewed
- Hits: 244
- Visitors: 237
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|