Can LSTM Learn to Capture Agreement? The Case of Basque
This work addresses the challenge of modeling complex grammatical phenomena in NLP, proposing Basque as a benchmark for language learning models, but it is incremental as it builds on existing agreement prediction research.
The study investigated whether sequential neural networks can implicitly learn hierarchical structures in human language by testing agreement prediction in Basque, finding they perform worse than expected based on prior English results and rely on local heuristics.
Sequential neural networks models are powerful tools in a variety of Natural Language Processing (NLP) tasks. The sequential nature of these models raises the questions: to what extent can these models implicitly learn hierarchical structures typical to human language, and what kind of grammatical phenomena can they acquire? We focus on the task of agreement prediction in Basque, as a case study for a task that requires implicit understanding of sentence structure and the acquisition of a complex but consistent morphological system. Analyzing experimental results from two syntactic prediction tasks -- verb number prediction and suffix recovery -- we find that sequential models perform worse on agreement prediction in Basque than one might expect on the basis of a previous agreement prediction work in English. Tentative findings based on diagnostic classifiers suggest the network makes use of local heuristics as a proxy for the hierarchical structure of the sentence. We propose the Basque agreement prediction task as challenging benchmark for models that attempt to learn regularities in human language.