Classifying and completing word analogies by machine learning
| Autor: | Henri Prade, Suryani Lim, Gilles Richard |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Word embedding
Computer science business.industry Applied Mathematics Analogy Of the form 02 engineering and technology Machine learning computer.software_genre Theoretical Computer Science Set (abstract data type) Artificial Intelligence 020204 information systems 0202 electrical engineering electronic engineering information engineering Embedding 020201 artificial intelligence & image processing Artificial intelligence business computer Parallelogram Software Word (computer architecture) Natural language |
| Zdroj: | International Journal of Approximate Reasoning. 132:1-25 |
| ISSN: | 0888-613X |
| DOI: | 10.1016/j.ijar.2021.02.002 |
| Popis: | Analogical proportions are statements of the form ‘a is to b as c is to d’, formally denoted a : b : : c : d . They are the basis of analogical reasoning which is often considered as an essential ingredient of human intelligence. For this reason, recognizing analogies in natural language has long been a research focus within the Natural Language Processing (NLP) community. With the emergence of word embedding models, a lot of progress has been made in NLP, essentially assuming that a word analogy like m a n : k i n g : : w o m a n : q u e e n is an instance of a parallelogram within the underlying vector space. In this paper, we depart from this assumption to adopt a machine learning approach, i.e., learning a substitute of the parallelogram model. To achieve our goal, we first review the formal modeling of analogical proportions, highlighting the properties which are useful from a machine learning perspective. For instance, the postulates supposed to govern such proportions entail that when a : b : : c : d holds, then seven permutations of a , b , c , d still constitute valid analogies. From a machine learning perspective, this provides guidelines to build training sets of positive and negative examples. Taking into account these properties for augmenting the set of positive and negative examples, we first implement word analogy classifiers using various machine learning techniques, then we approximate by regression an analogy completion function, i.e., a way to compute the missing word when we have the three other ones. Using a GloVe embedding, classifiers show very high accuracy when recognizing analogies, improving state of the art on word analogy classification. Also, the regression processes usually lead to much more successful analogy completion than the ones derived from the parallelogram assumption. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect