Challenge: Existing word embedding methods for distributed semantic models require limited examples to learn a high quality representation.
Approach: They propose a memory-based embedding learning method capable of acquiring word representations from limited context.
Outcome: The proposed method delivers impressive performance on two challenging few-shot word similarity tasks.

Similar Papers

Few-Shot Representation Learning for Out-Of-Vocabulary Words (P19-1)

Copied to clipboard

Challenge: Existing methods for learning word embedding assume there are enough occurrences for each word in the corpus to accurately estimate the representation of words.
Approach: They propose to fit a representation function to predict an oracle embedding vector based on limited contexts.
Outcome: The proposed model outperforms existing methods in constructing an accurate embedding for OOV words and improves downstream tasks when the embeddable is utilized.
Tiny Word Embeddings Using Globally Informed Reconstruction (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for word embedding reconstruction use only local information of subwords and pre-trained word embeds.
Approach: They propose a global loss function that uses words other than the target word to improve word embedding reconstruction by a factor of 200.
Outcome: The proposed method reduces the model size of pre-trained word embeddings by a factor of 200 while preserving its quality.
Using dependency parsing for few-shot learning in distributional semantics (2022.acl-srw)

Copied to clipboard

Challenge: Existing methods for few-shot learning use dependency parsing information to learn meaning of rare words based on limited amount of context sentences.
Approach: They propose dependency parsing for few-shot learning to learn meaning of rare words . they use word embedding models as background spaces for few shot learning .
Outcome: The proposed methods enhance the additive baseline model by using dependencies.
How to represent a word and predict it, too: Improving tied architectures for language modelling (D18-1)

Copied to clipboard

Challenge: Recent state-of-the-art models use word embeddings as input and output mappings instead of tied models.
Approach: They propose to decouple hidden state from word embedding prediction . they extend their proposed modification to word2vec models .
Outcome: The proposed architectures achieve comparable or better results compared to previous models without tying . the proposed architecture reduces parameters, enabling more compact models and faster learning.
Subword-based Compact Reconstruction of Word Embeddings (N19-1)

Copied to clipboard

Challenge: Existing word-based word embeddings are based on subword information and memory-shared embeddables.
Approach: They propose a method for reconstructing pre-trained word embeddings using subword information using memory-shared embedds and a variant of the key-value-query self-attention mechanism.
Outcome: The proposed method can imitate well-trained word embeddings in a small fixed space while preventing quality degradation across several linguistic benchmark datasets.
Advances in Pre-Training Distributed Word Representations (L18-1)

Copied to clipboard

Challenge: Pre-trained word representations are a building block of many Natural Language Processing and Machine Learning applications.
Approach: They propose to combine known tricks and a set of publicly available pre-trained word vector representations to train high-quality representations.
Outcome: The proposed models outperform the current state of the art on a number of tasks while maintaining a high training speed to scale to massive amount of data.
Bad Form: Comparing Context-Based and Form-Based Few-Shot Learning in Distributional Semantic Models (D19-61)

Copied to clipboard

Challenge: Word embeddings are an essential component of many natural language processing applications.
Approach: They propose 3 new tasks to obtain higher-quality vectors for word embeddings . they use word forms in training data that are related to word forms themselves .
Outcome: The proposed methods improve the performance of both baseline and advanced models on 4 out of 6 tasks.
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to few-shot text classification require domain expertise and an understanding of the language model's abilities to define the mapping between words and labels.
Approach: They propose a method that converts textual inputs to cloze questions that contain some form of task description and processes them with a pretrained language model to map the predicted words to labels.
Outcome: The proposed approach performs almost as well as hand-crafted label-to-word mappings for a number of tasks with small amounts of training data.
Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing approaches to named entity recognition are domain specific and require a domain specific architecture.
Approach: They propose a retrieval augmented large language model for Named Entity Recognition . the model uses word-embedding over sentence-level embedding to fine tune .
Outcome: The proposed model outperforms existing models on the CrossNER dataset.
Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for word sense disambiguation (WSD) lack large annotated datasets with sufficient coverage of words . performance of such methods lags behind fully-supervised methods . a meta-learning model is proposed to solve this problem .
Approach: They propose a model of semantic memory for supervised word sense disambiguation using meta-learning.
Outcome: The proposed model improves performance in few-shot WSD and produces meaning prototypes that capture similar senses of distinct words.

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