LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items
نویسندگان
چکیده
منابع مشابه
Multilingual Word Sense Disambiguation and Entity Linking
Nowadays the textual information available online is provided in an increasingly wide range of languages. This language explosion clearly forces researchers to focus on the challenging problem of being able to analyze and understand text written in any language. At the core of this problem lies the lexical ambiguity of language, an issue which is addressed by two key tasks in computational lexi...
متن کاملUnsupervised Word Sense Disambiguation with Multilingual Representations
In this paper we investigate the role of multilingual features in improving word sense disambiguation. In particular, we explore the use of semantic clues derived from context translation to enrich the intended sense and therefore reduce ambiguity. Our experiments demonstrate up to 26% increase in disambiguation accuracy by utilizing multilingual features as compared to the monolingual baseline.
متن کاملBeyond Bilingual: Multi-sense Word Embeddings using Multilingual Context
Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by exploiting crosslingual signals to aid sense identification. We present a multi-view Bayesian non-parametric algorithm which improves multi-sense word embeddings by...
متن کاملMultilingual Word Sense Disambiguation and Entity Linking for Everybody
In this paper we present a Web interface and a RESTful API for our state-of-the-art multilingual word sense disambiguation and entity linking system. The Web interface has been developed, on the one hand, to be user-friendly for non-specialized users, who can thus easily obtain a first grasp on complex linguistic problems such as the ambiguity of words and entity mentions and, on the other hand...
متن کاملMassively Multilingual Word Embeddings
We introduce new methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space. Our estimation methods, multiCluster and multiCCA, use dictionaries and monolingual data; they do not require parallel data. Our new evaluation method, multiQVECCCA, is shown to correlate better than previous ones with two downstream tasks (text categorizat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computational Linguistics
سال: 2020
ISSN: 0891-2017,1530-9312
DOI: 10.1162/coli_a_00375