2018/05/06 by Andrey Kutuzov, Kutuzov, Andrey · 1 citation
Computer Science · Engineering · #Artificial intelligence #Cluster analysis #Computation and Language (cs.CL) #Computer science #Embedding #Engineering #FOS: Computer and information sciences #Linguistics #Mainstream #Natural Language Processing Techniques #Natural language processing #Task (project management) #Text Readability and Simplification #Topic Modeling #Word (group theory) #Word embedding #cs.CL
paper · pdf · doi:10.48550/arxiv.1805.02258
published in arXiv (Cornell University) (Cornell University) · Proceedings of the 24rd International Conference on Computational Linguistics and Intellectual Technologies (Dialogue-2018)
arxiv created 2018/05/06 · openalex publication_date 2018/05/06 · arxiv updated 2018/05/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
The paper reports our participation in the shared task on word sense induction and disambiguation for the Russian language (RUSSE-2018). Our team was ranked 2nd for the wiki-wiki dataset (containing mostly homonyms) and 5th for the bts-rnc and active-dict datasets (containing mostly polysemous words) among all 19 participants. The method we employed was extremely naive. It implied representing contexts of ambiguous words as averaged word embedding vectors, using off-the-shelf pre-trained distributional models. Then, these vector representations were clustered with mainstream clustering techniques, thus producing the groups corresponding to the ambiguous word senses. As a side result, we show that word embedding models trained on small but balanced corpora can be superior to those trained on large but noisy data - not only in intrinsic evaluation, but also in downstream tasks like word sense induction.