21 |
How much does a word weigh? Weighting word embeddings for word sense induction ...
|
|
|
|
BASE
|
|
Show details
|
|
22 |
Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
23 |
RUSSE: The First Workshop on Russian Semantic Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
24 |
An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
25 |
Enriching Frame Representations with Distributionally Induced Senses ...
|
|
|
|
BASE
|
|
Show details
|
|
27 |
An unsupervised word sense disambiguation system for under-resourced languages
|
|
|
|
BASE
|
|
Show details
|
|
28 |
RUSSE'2018 : a shared task on word sense induction for the Russian language
|
|
|
|
BASE
|
|
Show details
|
|
29 |
Negative Sampling Improves Hypernymy Extraction Based on Projection Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
30 |
Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation ...
|
|
|
|
BASE
|
|
Show details
|
|
31 |
Negative Sampling Improves Hypernymy Extraction Based on Projection Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
32 |
A Framework for Enriching Lexical Semantic Resources with Distributional Semantics ...
|
|
|
|
BASE
|
|
Show details
|
|
34 |
Watset: Automatic Induction of Synsets from a Graph of Synonyms ...
|
|
|
|
Abstract:
This paper presents a new graph-based approach that induces synsets using synonymy dictionaries and word embeddings. First, we build a weighted graph of synonyms extracted from commonly available resources, such as Wiktionary. Second, we apply word sense induction to deal with ambiguous words. Finally, we cluster the disambiguated version of the ambiguous input graph into synsets. Our meta-clustering approach lets us use an efficient hard clustering algorithm to perform a fuzzy clustering of the graph. Despite its simplicity, our approach shows excellent results, outperforming five competitive state-of-the-art methods in terms of F-score on three gold standard datasets for English and Russian derived from large-scale manually constructed lexical resources. ... : 12 pages, 3 figures, 6 tables, accepted to ACL 2017 ...
|
|
Keyword:
68T50; Computation and Language cs.CL; FOS Computer and information sciences; I.2.6; I.5.3; I.2.4
|
|
URL: https://arxiv.org/abs/1704.07157 https://dx.doi.org/10.48550/arxiv.1704.07157
|
|
BASE
|
|
Hide details
|
|
35 |
Human and Machine Judgements for Russian Semantic Relatedness ...
|
|
|
|
BASE
|
|
Show details
|
|
36 |
Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl ...
|
|
|
|
BASE
|
|
Show details
|
|
37 |
Unsupervised does not mean uninterpretable : the case for word sense induction and disambiguation
|
|
|
|
BASE
|
|
Show details
|
|
38 |
Unsupervised, knowledge-free, and interpretable word sense disambiguation
|
|
|
|
BASE
|
|
Show details
|
|
39 |
The ContrastMedium algorithm : taxonomy induction from noisy knowledge graphs with just a few links
|
|
|
|
BASE
|
|
Show details
|
|
40 |
Negative sampling improves hypernymy extraction based on projection learning
|
|
|
|
BASE
|
|
Show details
|
|
|
|