Abstract
Linguistic information is encoded at varying timescales (subwords, phrases, etc.) and communicative levels, such as syntax and semantics. Contextualized embeddings have analogously been found to capture these phenomena at distinctive layers and frequencies. Leveraging these findings, we develop a fully learnable frequency filter to identify spectral profiles for any given task. It enables vastly more granular analyses than prior handcrafted filters, and improves on efficiency. After demonstrating the informativeness of spectral probing over manual filters in a monolingual setting, we investigate its multilingual characteristics across seven diverse NLP tasks in six languages. Our analyses identify distinctive spectral profiles which quantify cross-task similarity in a linguistically intuitive manner, while remaining consistent across languages—highlighting their potential as robust, lightweight task descriptors.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing |
| Place of Publication | Abu Dhabi, United Arab Emirates |
| Publisher | Association for Computational Linguistics |
| Publication date | Dec 2022 |
| Pages | 7730-7741 |
| Publication status | Published - Dec 2022 |
Keywords
- Linguistic Information
- Contextualized Embeddings
- Frequency Filter
- Spectral Probing
- Multilingual NLP
- Cross-task Similarity
- Syntax and Semantics
- Granular Analyses
- Monolingual Setting
- Robust Task Descriptors