1 |
Detecting Text Formality: A Study of Text Classification Approaches ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Taxonomy Enrichment with Text and Graph Vector Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Documents Representation via Generalized Coupled Tensor Chain with the Rotation Group constraint ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
RUSSE'2020: Findings of the First Taxonomy Enrichment Task for the Russian language ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Word Sense Disambiguation for 158 Languages using Word Embeddings Only ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Studying Taxonomy Enrichment on Diachronic WordNet Versions ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
A Comparative Study of Lexical Substitution Approaches based on Neural Language Models ...
|
|
|
|
Abstract:
Lexical substitution in context is an extremely powerful technology that can be used as a backbone of various NLP applications, such as word sense induction, lexical relation extraction, data augmentation, etc. In this paper, we present a large-scale comparative study of popular neural language and masked language models (LMs and MLMs), such as context2vec, ELMo, BERT, XLNet, applied to the task of lexical substitution. We show that already competitive results achieved by SOTA LMs/MLMs can be further improved if information about the target word is injected properly, and compare several target injection methods. In addition, we provide analysis of the types of semantic relations between the target and substitutes generated by different models providing insights into what kind of words are really generated or given by annotators as substitutes. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2006.00031 https://dx.doi.org/10.48550/arxiv.2006.00031
|
|
BASE
|
|
Hide details
|
|
9 |
Making Fast Graph-based Algorithms with Graph Metric Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Hypernyms extracted from a large text corpus using Hearst lexical-syntactic patterns ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Hypernyms extracted from a large text corpus using Hearst lexical-syntactic patterns ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Datasets for Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Datasets for Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
HHMM at SemEval-2019 Task 2: Unsupervised frame induction using contextualized word embeddings
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Watset: Local-global graph clustering with applications in sense and frame induction
|
|
|
|
BASE
|
|
Show details
|
|
19 |
RUSSE'2018: A Shared Task on Word Sense Induction for the Russian Language ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|