Learner corpora have been utilized to examine student production of multi-word units, also known as ‘lexical bundles’ (Chen & Baker, 2010; 2016, Staples et al., 2013). Lexical bundles are strings of three or more words that appear frequently in a given discourse (Biber et al., 1999). This talk presents the results of a register analysis study into the production of lexical bundles by Japanese university students in written essays and spoken monologues taken from two ICNALE corpora (Ishikawa, 2023). First, an overview will be given of key research findings into lexical bundles in learner corpora. Following this, the research study’s methodology will be outlined. The bundles were extracted through Sketch Engine and manually categorized into Biber et al.’s (2004) structural and functional taxonomies. Results show that the two registers are structurally and functionally similar to each other, suggesting that spoken monologues have more in common syntactically with writing than with speech. Also, it was found that native speakers used more noun phrases and prepositional phrases than Japanese learners, and that the latter displayed a greater reliance on verb phrases. Finally, the presenters will consider the study limitations and the possibilities for further research.