Semantic Shift Stability: Efficient Way to Detect Performance Degradation of Word Embeddings and Pre-trained Language Models (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing methods to detect time-series performance degradation of word embeddings and pre-trained language models are not efficient. |
| Approach: | They propose a way to detect time-series performance degradation by calculating the degree of semantic shift. |
| Outcome: | The proposed method detects time-series performance degradation in Japanese and English datasets. |
Similar Papers
Diachronic word embeddings and semantic shifts: a survey (C18-1)
Copied to clipboard
| Challenge: | Existing methods for tracing time-related semantic shifts with word embedding models lack the cohesion, common terminology and shared practices of more established areas of natural language processing. |
| Approach: | They propose several axes along which these methods can be compared and propose a framework for comparison. |
| Outcome: | The proposed methods are compared with existing methods and outline their main challenges and potential applications. |
Stable Language Model Pre-training by Reducing Embedding Variability (2024.emnlp-main)
Copied to clipboard
| Challenge: | Stable pre-training is essential for achieving better-performing language models, but tracking pre-train stability is impractical due to high computational costs. |
| Approach: | They propose to use Token Embedding Variability as a proxy to estimate pre-training stability. |
| Outcome: | The proposed method improves stability and lowers perplexities even at deeper layer counts. |
Effects of Pre- and Post-Processing on type-based Embeddings in Lexical Semantic Change Detection (2021.eacl-main)
Copied to clipboard
| Challenge: | Lexical semantic change detection is a new and innovative research field. |
| Approach: | They propose to pre-train on large corpora and refine on diachronic target corpors to improve performance. |
| Outcome: | The proposed models improve on large corpora and diachronic target corpors . the proposed models are compared with existing models in a variety of learning scenarios . |
When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation? (N18-2)
Copied to clipboard
| Challenge: | Pre-trained word embeddings have proven to be invaluable for improving performance in natural language analysis tasks where large-scale parallel corpora cannot be obtained. |
| Approach: | They perform five sets of experiments to analyze when pre-trained word embeddings can be useful in NMT tasks. |
| Outcome: | The embeddings provide gains of up to 20 BLEU points in the most favorable setting. |
Sequential Modelling of the Evolution of Word Representations for Semantic Change Detection (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that detect semantically shifted words do not account for its evolution through time. |
| Approach: | They propose three variants of sequential models for detecting semantically shifted words . they demonstrate that temporal modelling of word representations yields a clear-cut advantage . |
| Outcome: | The proposed models account for the changes in word representations over time. |
Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for word embeddings have been used to model semantic relations with word embeds. |
| Approach: | They propose a method that leverages contextual embeddings for diachronic semantic shift detection by generating time specific word representations from BERT embedds. |
| Outcome: | The proposed method performs comparable to the current state-of-the-art without time consuming domain adaptation on large corpora. |
Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency (2022.acl-long)
Copied to clipboard
| Challenge: | Structured pruning has been extensively studied on monolingual pre-trained models . but little attention has been paid to evaluating the effectiveness of structured pruning on multilingual models. |
| Approach: | They investigate settings, algorithms, and efficiency of structured pruning on multilingual models . authors propose a simple approach that allows training the model once and adapting to different model sizes at inference . |
| Outcome: | The proposed approach allows training the model once and adapting to different model sizes at inference. |
Room to Glo: A Systematic Comparison of Semantic Change Detection Approaches with Word Embeddings (D19-1)
Copied to clipboard
| Challenge: | Word embeddings are increasingly used for automatic detection of semantic change, but a robust evaluation and systematic comparison of the choices involved has been lacking. |
| Approach: | They propose a new evaluation framework for semantic change detection using whole time series and a Twitter dataset spanning 5.5 years. |
| Outcome: | The proposed framework shows that using whole time series is preferable over continuously trained embeddings for long time periods and that the reference point matters. |
An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-training large language models is a standard practice in the natural language processing community. |
| Approach: | They propose to use elastic weight consolidation to mitigate catastrophic forgetting when pre-trained large language models are evaluated on generic benchmarks. |
| Outcome: | The proposed model achieves state-of-the-art on out-of domain tasks with minimal pre-training . elastic weight consolidation provides best overall scores yielding only a 0.33% drop in performance across seven generic tasks while remaining competitive in bio-medical tasks. |
Diachronic degradation of language models: Insights from social media (P18-2)
Copied to clipboard
| Challenge: | Existing studies have explored whether and how language models degrade over time, i.e. why they fail to work on contemporary language. |
| Approach: | They investigate the accuracy of pre-trained language models for downstream tasks in machine learning and user profiling. |
| Outcome: | The results show that it is possible to measure diachronic drifts within social media and within the span of a few years. |