When is Wall a Pared and when a Muro?: Extracting Rules Governing Lexical Selection

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6911–6929 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 6911 When is Wall a Pared and when a Muro?: Extracting Rules Governing Lexical Selection Aditi Chaudhary†, Kayo Yin†, Antonios Anastasopoulos‡, Graham Neubig† †Carnegie Mellon University, ‡George Mason University {aschaudh,kayoy,gneubig}@cs.cmu.edu antonis@gmu.edu Abstract Learning fine-grained distinctions between vo- cabulary items is a key challenge in learning a new language. For example, the noun “wall” has different lexical manifestations in Spanish – “pared” refers to an indoor wall while “muro” refers to an outside wall. However, this va- riety of lexical distinction may not be obvi- ous to non-native learners unless the distinc- tion is explained in such a way. In this work, we present a method for automatically identi- fying fine-grained lexical distinctions, and ex- tracting concise descriptions explaining these distinctions in a human- and machine-readable format. We confirm the quality of these ex- tracted descriptions in a language learning setup for two languages, Spanish and Greek, where we use them to teach non-native speak- ers when to translate a given ambiguous word into its different possible translations. Code and data are publicly released here.1 1 Introduction With increasing globalization there is a widespread prevalence and need for good materials and tools to help people learn languages. Curating such content manually requires a large time and cost investment which poses a challenge particularly for languages where protection and revival efforts are ongoing (Moline, 2020). One of the most important and challenging processes in learning a new language (L2) is vocabulary acquisition (Ellis, 1996; Moore, 1996), which is generally made easy by associat- ing L2 words with words from the first language (L1) (Hulstijn et al., 1996; Watanabe, 1997). In many cases, L1 words or word senses can be unam- biguously associated with L2 words. For example “linguistics” and “lingüística” essentially form a one-to-one mapping between English and Spanish. However, different languages carve up the seman- tic space of the world in different ways leading 1https://github.com/Aditi138/ LexSelection Es: muro En: wall Es: pared Figure 1: Semantic subdivision for the concept ‘wall’ results in different lexical manifestations in Spanish: ‘muro’ for outside wall and ‘pared’ for inside wall whereas in English both are referred as ‘wall’. to semantic subdivisions, distinctions made in one language not made in another. For example, “wall” in English is manifested differently in Spanish as “pared” or “muro”, as shown in Figure 1, and for an L1 English speaker it may not be immediately obvious when one should be used over the other. A skilled teacher or comprehensive language learn- ing resource may be able to provide explanations that resolve this ambiguity. For example, Robert- son (2020) present word definitions in-context for Finnish learners, while CAVOCA (Groot, 2000) takes a learner through various stages of the word acquisition process including word usage, syntax. In this work, we propose a method to automati- cally discover rules regarding fine-grained lexical distinctions and present L2 learners with concise descriptions derived …

Content truncated to 500 words