methodology-2

Learning Word Embeddings

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in learning-word-embeddings-7

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find learning-word-embeddings-7 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech

James R. Glass, Yu-An Chung•Thu Mar 22 2018

The proposed Speech2Vec model, a novel deep neural network architecture for learning fixed-length vector representations of audio segments excised from a speech corpus, is based on a RNN Encoder-Decoder framework, and borrows the methodology of skipgrams or continuous bag-of-words for training.

187

Content

0

Paper Graph

One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Noah A. Smith, Hongjin Su, Yizhong Wang, Wen-tau Yih, Luke Zettlemoyer, Mari Ostendorf, Tao Yu, Jungo Kasai, Weijia Shi, Yushi Hu•Sun Dec 18 2022

INSTRUCTOR is a single embedder that can generate text embeddings tailored to different downstream tasks and domains, without any further training, and achieves state-of-the-art performance.

408 0

Paper Graph

WordRank: Learning Word Embeddings via Robust Ranking

Hyokun Yun, Pinar Yanardag, S. Vishwanathan, Shihao Ji, Shin Matsushima•Mon Jun 08 2015

This paper argues that word embedding can be naturally viewed as a ranking problem due to the ranking nature of the evaluation metrics, and proposes a novel framework WordRank that efficiently estimates word representations via robust ranking, in which the attention mechanism and robustness to noise are readily achieved via the DCG-like ranking losses.

39 0

Paper Graph

Neural Graph Embedding Methods for Natural Language Processing

Shikhar Vashishth•Thu Nov 07 2019

GCNs are utilized for Document Timestamping problem and for learning word embeddings using dependency context of a word instead of sequential context and two limitations of existing GCN models are addressed.

9 0

Paper Graph

Skip-gram word embeddings in hyperbolic space

Matthias Leimeister, Benjamin J. Wilson•Wed Aug 29 2018

The results demonstrate the potential of hyperbolic word embeddings, particularly in low dimensions, though without clear superiority over their Euclidean counterparts, and discuss problems in the formulation of the analogy task resulting from the curvature ofhyperbolic space.

50 0

Paper Graph

MorphTE: Injecting Morphology in Tensorized Embeddings

Benyou Wang, P. Zhang, Guobing Gan, Sunzhu Li, Xiuqing Lu•Wed Oct 26 2022

Experimental results on four translation datasets of different languages show that MorphTE can compress word embedding parameters by about 20 times without performance loss and significantly outperforms related embedding compression methods.

8 0

Paper Graph

Improving Lexical Embeddings with Semantic Knowledge

Mark Dredze, Mo Yu•Sat May 31 2014

This work proposes a new learning objective that incorporates both a neural language model objective (Mikolov et al., 2013) and prior knowledge from semantic resources to learn improved lexical semantic embeddings.

314 0

Paper Graph

How to Train good Word Embeddings for Biomedical NLP

A. Korhonen, Sampo Pyysalo, Billy Chiu, Gamal K. O. Crichton•Sun Jul 31 2016

A comprehensive study of how the quality of embeddings changes according to hyper-parameter settings is presented, and it is observed that bigger corpora do not necessarily produce better biomedical domain word embedDings.

352 0

Paper Graph

The Mixing method: low-rank coordinate descent for semidefinite programming with diagonal constraints

J. Z. Kolter, Po-Wei Wang, Wei-Cheng Chang•Wed May 31 2017

This work shows that with a step size, the Mixing method converges to the global optimum of the semidefinite program almost surely in a locally linear rate under random initialization, and is the first low-rank semideFinite programming method to achieve a global optimum on the spherical manifold without assumption.

34 0

Paper Graph

Dict2vec : Learning Word Embeddings using Lexical Dictionaries

Amaury Habrard, Julien Tissier, C. Gravier•Wed Sep 06 2017

Dict2vec builds new word pairs from dictionary entries so that semantically-related words are moved closer, and negative sampling filters out pairs whose words are unrelated in dictionaries.

101 0

Paper Graph

Adding a benchmark result helps the community track progress.