Disambiguated skip-gram model (D18-1)

Copied to clipboard

Challenge: Disambiguated skip-gram is a neural-probabilistic model for learning multi-sense word embeddings.
Approach: They propose a model that is end-to-end differentiable and can be interpreted as a feed-forward neural network.
Outcome: The proposed model improves state-of-the-art in word sense induction benchmarks.

Similar Papers

Embedding Words as Distributions with a Bayesian Skip-gram Model (C18-1)

Copied to clipboard

Challenge: Rather than assuming that word embeddings are fixed across the entire text collection, we generate them from word-specific prior densities for each word.
Approach: They propose a method for embedding words as probability densities in a low-dimensional space from a word-specific prior density for each occurrence of a given word.
Outcome: The proposed method can encode word as a distribution on a range of benchmarks and is comparable to Gaussian embeddings.
Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings (N18-2)

Copied to clipboard

Challenge: Existing word embedding models are limited by semantic resources, which are hard to obtain or annotate.
Approach: They propose a directional skip-gram model that explicitly distinguishes between left and right contexts in word prediction.
Outcome: The proposed model outperforms other models on different datasets in semantic and syntactic evaluations.
Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation (P19-1)

Copied to clipboard

Challenge: Contextual embeddings address the problem of meaning conflation hampering word embeddables.
Approach: They propose a method that creates sense-level embeddings with full-coverage of WordNet without recourse to explicit sense distributions or task-specific modelling.
Outcome: The proposed method surpasses previous systems using powerful models and is robust when ignoring part-of-speech and lemma features.
Probabilistic FastText for Multi-Sense Word Embeddings (P18-1)

Copied to clipboard

Challenge: Probabilistic FastText model for word embeddings captures word senses, sub-word structure, and uncertainty information.
Approach: They propose a model for word embeddings that captures multiple word senses . they represent each word with a Gaussian mixture density, with each vector representing an n-gram .
Outcome: The proposed model outperforms dictionary-level probabilistic embeddings on word-similarity benchmarks.
Word Sense Disambiguation for 158 Languages using Word Embeddings Only (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods of disambiguation of word senses are based on knowledge bases, taxonomies, and other externally built resources.
Approach: They propose a method that takes a pre-trained word embedding model and induces a fully-fledged word sense inventory for 158 languages.
Outcome: The proposed model is based on a pre-trained word embedding model and induces a fully-fledged word sense inventory in 158 languages.
Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations (D19-1)

Copied to clipboard

Challenge: Contextualized word representations are effective in downstream tasks such as question answering, named entity recognition, and sentiment analysis.
Approach: They propose to integrate pre-trained contextualized word representations into a neural network that captures the whole sentence and the word representation in the sentence.
Outcome: The proposed approach outperforms the state-of-the-art approach that makes use of non-contextualized word embeddings on multiple benchmark WSD datasets.
One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words (2020.lrec-1)

Copied to clipboard

Challenge: Existing word-specific classifiers lack the ability to generalize across words and require limited sense-annotated data for every word.
Approach: They propose to learn a single model that derives sense representations and enforces congruence between a word instance and its right sense by using both sense-annotated data and lexical resources.
Outcome: Empirical evaluation shows the proposed model outperforms classifier-based models by 1.7%, 2.5% and 3.8% in F1-score on GloVe, ELMo and BERT word embeddings respectively.
Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders (2020.acl-main)

Copied to clipboard

Challenge: Existing models for Word Sense Disambiguation are not uniformly distributed on rare or unseen senses.
Approach: They propose a bi-encoder model that embeds the target word with its context and the dictionary definition, or gloss, of each sense.
Outcome: The proposed model outperforms previous state-of-the-art models on English all-words WSD, with a 31.1% error reduction on less frequent senses over prior work.
Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies have shown that neural machine translation models rely heavily on source sentence information when resolving lexical ambiguity.
Approach: They propose a method for the prediction of disambiguation errors based on statistical data properties and propose 'a simple adversarial attack strategy' that minimally perturbs sentences to elicit disambiguations errors.
Outcome: The proposed method shows that disambiguation robustness varies substantially between domains and different models trained on the same data are vulnerable to different attacks.
A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images (D18-1)

Copied to clipboard

Challenge: Existing approaches combine language and perception to infer word embeddings . however, the embeddables produced by such models do not reflect the actual word representations.
Approach: They propose a probabilistic model that integrates linguistic and perceptual inputs to explain observed word-context pairs in a text corpus.
Outcome: The proposed model achieves competitive or stronger results on tasks of assessing pairwise word similarity and image/caption retrieval compared to other state-of-the-art models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations