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.

Similar Papers

PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing word embeddings assume fixed finite-size vocabularies, hindering their ability to provide useful word representations for out-of-vocaulary words.
Approach: They propose a model that generalizes word embeddings without extra contextual information . they use the spellings of words to model subword segmentation and compute subword-based compositional word embeds.
Outcome: The proposed model can generate meaningful subword segmentations without any source of explicit morphological knowledge.
A Systematic Study of Leveraging Subword Information for Learning Word Representations (N19-1)

Copied to clipboard

Challenge: Existing word representation models for morphologically rich languages use subword-level information, but their systematic comparative analysis across typologically diverse languages and tasks is still missing.
Approach: They propose a framework for learning subword-informed word representations that allows for easy experimentation with different segmentation and composition components.
Outcome: The proposed framework allows for easy experimentation with different segmentation and composition components, as well as advanced techniques based on position embeddings and self-attention.
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.
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.
Embeddings in Natural Language Processing (2020.coling-tutorials)

Copied to clipboard

Challenge: Embeddings have been a key topic of interest in NLP for the past decade . a quick warm-up introduction to NLP and why it is important to have a semantic comprehension of texts .
Approach: This tutorial will provide a high-level synthesis of the main embedding techniques in NLP . it will start with word embedds and then move to other types of embeddable vectors .
Outcome: This tutorial will provide a high-level synthesis of the main embedding techniques in NLP . it will start with word embedds and move to other types of embeddable representations .
Subword Attention and Post-Processing for Rare and Unknown Contextualized Embeddings (2024.findings-naacl)

Copied to clipboard

Challenge: Word embeddings are useful, but struggle on rare and unknown words.
Approach: They propose a rare/unknown embedding architecture that focuses on contextualized representations.
Outcome: The proposed architecture improves performance in most intrinsic and downstream tasks.
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.
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.
Reusing Weights in Subword-Aware Neural Language Models (N18-1)

Copied to clipboard

Challenge: a statistical language model assigns a probability to a sequence of words . data sparsity is a major problem in building traditional n-gram language models .
Approach: They propose several ways to reuse subword embeddings and other weights in subword-aware neural language models.
Outcome: The proposed techniques do not benefit a competitive character-aware model . but they show significant reductions in model sizes and performance.
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.

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