We present LessLex, a novel multilingual lexical resource. Different from the vast majority of existing approaches, we ground our embeddings on a sense inventory made available from the BabelNet semantic network. In this setting, multilingual access is governed by the mapping of terms onto their underlying sense descriptions, such that all vectors co-exist in the same semantic space. As a result, for each term we have thus the ‘blended’ terminological vector along with those describing all senses associated to that term. LessLex has been tested on three tasks relevant to lexical semantics: conceptual similarity, contextual similarity, and semantic text similarity: we experimented over the principal data sets for such tasks in their multilingual and cross-lingual variants, improving on or closely approaching state-of-the-art results. We conclude by arguing that LessLex vectors may be relevant for practical applications and for research on conceptual and lexical access and competence.

中文翻译：

---

LESSLEX：将多语言嵌入链接到词法项的 Sense 表示

我们展示了 LessLex，一种新颖的多语言词汇资源。与绝大多数现有方法不同，我们将嵌入基于 BabelNet 语义网络提供的感知库存。在这种情况下，多语言访问受术语到其底层语义描述的映射的控制，因此所有向量共存于同一语义空间中。因此，对于每个术语，我们都有“混合”术语向量以及描述与该术语相关的所有含义的术语向量。LessLex 已经在三个与词汇语义相关的任务上进行了测试：概念相似性、上下文相似性和语义文本相似性：我们在多语言和跨语言变体中对此类任务的主要数据集进行了试验，改进或接近状态- 最先进的结果。