Integrating WordNet for Multiple Sense Embeddings in Vector Semantics
نویسندگان
چکیده
Popular distributional approaches to semantics allow for only a single embedding of any particular word. A single embedding per word conflates the distinct meanings of the word and their appropriate contexts, irrespective of whether those usages are related or completely disjoint. We compare models that use the graph structure of the knowledge base WordNet as a post-processing step to improve vectorspace models with multiple sense embeddings for each word, and explore the application to word sense disambiguation.
منابع مشابه
Ontologically Grounded Multi-sense Representation Learning for Semantic Vector Space Models
Words are polysemous. However, most approaches to representation learning for lexical semantics assign a single vector to every surface word type. Meanwhile, lexical ontologies such as WordNet provide a source of complementary knowledge to distributional information, including a word sense inventory. In this paper we propose two novel and general approaches for generating sense-specific word em...
متن کاملAutoExtend: Combining Word Embeddings with Semantic Resources
We present AutoExtend, a system that combines word embeddings with semantic resources by learning embeddings for non-word objects like synsets and entities and learning word embeddings which incorporate the semantic information from the resource. The method is based on encoding and decoding the word embeddings and is flexible in that it can take any word embeddings as input and does not need an...
متن کاملAutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes
We present AutoExtend, a system to learn embeddings for synsets and lexemes. It is flexible in that it can take any word embeddings as input and does not need an additional training corpus. The synset/lexeme embeddings obtained live in the same vector space as the word embeddings. A sparse tensor formalization guarantees efficiency and parallelizability. We use WordNet as a lexical resource, bu...
متن کاملMultilingual Wordnet sense Ranking using nearest context
In this paper, we combine methods to estimate sense rankings from raw text with recent work on word embeddings to provide sense ranking estimates for the entries in the Open Multilingual Wordnet (OMW).The existing Word2Vec Polyglot2 pre-trained models are only built for single word entries, we, therefore, re-train them with multiword expressions from the wordnets, so that multiword expressions ...
متن کاملExtending and Improving Wordnet via Unsupervised Word Embeddings
This work presents an unsupervised approach for improving WordNet that builds upon recent advances in document and sense representation via distributional semantics. We apply our methods to construct Wordnets in French and Russian, languages which both lack good manual constructions.1 These are evaluated on two new 600-word test sets for word-to-synset matching and found to improve greatly upon...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016