Challenge: Contextualized embeddings are expensive and resource-demanding, hence environmentally unfriendly.
Approach: They propose a method to convert contextualized embeddings from pre-trained models into static embeddables using synonym knowledge and weighted vector distribution.
Outcome: The proposed method outperforms baseline embeddings by a large margin through extrinsic and intrinsic tasks.

Similar Papers

Better Word Embeddings by Disentangling Contextual n-Gram Information (N19-1)

Copied to clipboard

Challenge: Pre-trained word vectors are ubiquitous in Natural Language Processing applications.
Approach: They show that word embeddings with bigram and trigram embedds improve unigram embeds . they claim this removes contextual information from unigrammes, resulting in better unigraph embedders .
Outcome: The proposed model outperforms competing models on a wide variety of tasks.
Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring (2021.acl-long)

Copied to clipboard

Challenge: Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embedders.
Approach: They propose an unsupervised mapping approach that fixes fixed embeddings and learns new ones for the source language that are aligned with them.
Outcome: The proposed method outperforms conventional mapping methods on bilingual lexicon induction and obtains competitive results in the downstream XNLI task.
Embedding Words in Non-Vector Space with Unsupervised Graph Learning (2020.emnlp-main)

Copied to clipboard

Challenge: GraphGlove is an unsupervised graph word representations that are learned end-to-end.
Approach: They propose a method to learn weighted graph word representations end-to-end using a weighteable weighte . they adopt a hierarchical graph representation method and modify the GloVe training algorithm to learn graph representations.
Outcome: The proposed method outperforms vector-based methods on word similarity and analogy tasks.
Retrofitting Contextualized Word Embeddings with Paraphrases (D19-1)

Copied to clipboard

Challenge: Contextualized word embeddings can be useful for downstream applications, but they can be over-sensitive to contexts.
Approach: They propose a method to retrofit contextualized word embeddings with paraphrases to minimize the variance of word representations on paraphrased contexts.
Outcome: The proposed method improves on sentence classification and inference tasks.
Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources (2020.acl-srw)

Copied to clipboard

Challenge: In this paper, we present an effective method for semantic specialization of word vector representations.
Approach: They propose a method for semantic specialization of word vector representations using BabelNet.
Outcome: The proposed method improves on word similarity and dialog state tracking tasks.
HG2Vec: Improved Word Embeddings from Dictionary and Thesaurus Based Heterogeneous Graph (2022.coling-1)

Copied to clipboard

Challenge: Existing models that learn word embeddings rely on a large corpus of data . however, these models require massive time and space for data pre-processing and training .
Approach: They propose a model that learns word embeddings utilizing only dictionaries and thesauri . they exploit a new context-focused loss model that models transitive relationships between word pairs .
Outcome: The proposed model reaches the state-of-art on multiple word similarity and relatedness benchmarks.
A Retrofitting Model for Incorporating Semantic Relations into Word Embeddings (2020.coling-main)

Copied to clipboard

Challenge: Existing word embedding models mix semantic similarity with other types of relatedness.
Approach: They propose a model that leverages relational knowledge available in a knowledge resource to improve word embeddings.
Outcome: The proposed model improves word embeddings on synonymy, antonymy and hypernymy relations in WordNet and significantly improves lexical entailment detection task.
Querying Word Embeddings for Similarity and Relatedness (N18-1)

Copied to clipboard

Challenge: Word2Vec embeddings have become popular representations of word meaning . similarity between two words is often assumed to be a direction-less measure, whereas relatedness is inherently directional.
Approach: They propose to use word embeddings to predict asymmetric association between words from a dataset of production norms to generate thematically related words.
Outcome: The proposed model predicts asymmetric association between words from a recently published dataset of production norms.
Generalizing Word Embeddings using Bag of Subwords (D18-1)

Copied to clipboard

Challenge: Existing word embeddings techniques have a fixed vocabulary, i.e., they can only provide vectors over a finite set of common words that appear frequently in a given corpus.
Approach: They propose a subword-level word vector generation model that views words as bags of character n-grams and provides good vectors for rare or unseen words.
Outcome: The proposed model performs state-of-the-art in English word similarity task and in joint prediction of part-of speech tag and morphosyntactic attributes in 23 languages.
COIN – an Inexpensive and Strong Baseline for Predicting Out of Vocabulary Word Embeddings (2022.coling-1)

Copied to clipboard

Challenge: Word embedding models only include terms that occur a sufficient number of times in training corpora.
Approach: They propose a method for predicting word embeddings for out of vocabulary terms using word2vec.
Outcome: The proposed method surpasses several methods on benchmark tasks and is inexpensive to compute.

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