| 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. |
Similar Papers
Dynamic Meta-Embeddings for Improved Sentence Representations (D18-1)
Copied to clipboard
| Challenge: | A sprawling literature has emerged about what word embeddings are most useful for which tasks . word embed-ding is a technique that can be used to learn word-level meaning representations for a variety of tasks. |
| Approach: | They propose a method for supervised learning of embedding ensembles that leads to state-of-the-art performance on a variety of tasks. |
| Outcome: | The proposed method leads to state-of-the-art performance on a variety of tasks. |
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. |
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. |
Neural Machine Translation without Embeddings (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing models operate over subword tokens, but byte-based models employ a different approach . a one-hot representation of each byte does not hurt performance, but it improves BLEU scores . |
| Approach: | They propose to represent every computerized text as a sequence of bytes via UTF-8 . this eliminates the need for an embedding layer and improves performance . |
| Outcome: | The proposed model improves BLEU scores on byte-to-byte translation models compared to character-level models . the proposed model does not require an embedding layer and does not drop out of the decoder . |
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. |
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. |
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. |
Improving Neural Machine Translation by Incorporating Hierarchical Subword Features (C18-1)
Copied to clipboard
| Challenge: | Using subwords, we find that the appropriate subword units for the three layers differ depending on the model . incorporating hierarchical subword features improves BLEU scores on the IWSLT evaluation datasets. |
| Approach: | They propose a method that expresses a word by combining "subwords" they propose to incorporate hierarchical subword features into a single embedding layer . |
| Outcome: | The proposed method improves BLEU scores on the IWSLT evaluation datasets. |
Subword-Delimited Downsampling for Better Character-Level Translation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Subword-level models are expensive in terms of time and computation, but character-level model with downsampling component can be used for machine translation. |
| Approach: | They propose a character-level downsampling method which is informed by subwords to improve model performance. |
| Outcome: | The proposed method outperforms existing methods and shows that it can be done without sacrificing quality. |
Embedding Recycling for Language Models (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on embedding recycling have not adequately account for overhead costs. |
| Approach: | They propose to reuse contextualized embeddings from previous runs to speed training and inference of future ones. |
| Outcome: | The proposed technique speeds training and inference with no impact on accuracy. |