Challenge: Recent text embedding models often introduce task-induced bias alongside domain knowledge, leading to performance degradation.
Approach: They propose a representation regularization framework that explicitly controls representation shift during embedding pre-finetuning.
Outcome: The proposed framework outperforms standard pre-finetuning and isotropy-oriented post-hoc regularization in most settings.

Similar Papers

ReWE: Regressing Word Embeddings for Regularization of Neural Machine Translation Systems (N19-1)

Copied to clipboard

Challenge: Existing methods to regularize neural machine translation are limited in low-resource settings.
Approach: They propose a method that uses regressing word embeddings to regularize neural machine translation.
Outcome: The proposed system improves on a strong baseline and a state-of-the-art system.
Task-oriented Domain-specific Meta-Embedding for Text Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods neglect domain-specific knowledge and use the same word embedding for each word in all domain-specified datasets.
Approach: They propose a method to incorporate domain-specific and task-oriented information into meta-embeddings by combining pre-trained word embeddings.
Outcome: The proposed method performs well on four text classification datasets and shows that it is compatible with existing methods.
Task-adaptive Pre-training of Language Models with Word Embedding Regularization (2021.findings-acl)

Copied to clipboard

Challenge: Pre-trained language models acquire domain-independent knowledge through pre-training with massive textual resources.
Approach: They propose a task-adaptive pre-training process that makes static embeddings close to the word embedds obtained in the target domain.
Outcome: The proposed process improves on BioASQ and SQuAD when the pre-training corpora were not dominated by indomain data.
FLARE: Task-Agnostic Embedding Model Evaluation via Normalizing Flows (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods based on kernel estimators or Gaussian mixtures fail to model high-dimensional distributions effectively, resulting in unstable rankings.
Approach: They propose a method which uses normalizing flows to estimate information sufficiency in high-dimensional spaces by learning invertible transformations.
Outcome: Experiments on 11 datasets show that FLARE achieves a strong Spearman’s (up to 0.90) with supervised benchmarks, remaining robust even for high-dimensional embeddings (d 3,584).
Domain Adversarial Fine-Tuning as an Effective Regularizer (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing fine-tuning techniques can degrade general-domain representations . however, fine-timing can lead to catastrophic forgetting of knowledge .
Approach: They propose a new regularization technique that complements the task-specific loss used during fine-tuning with an adversarial objective.
Outcome: Empirical results show that AFTER improves performance on various natural language understanding tasks compared to standard fine-tuning.
PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models (2020.tacl-1)

Copied to clipboard

Challenge: PERL is a representation learning model that uses labeled data from the source domain and unlabeled data not necessarily drawn from the target domain.
Approach: They propose a model that extends contextualized word embedding models with pivot-based fine-tuning to address this bottleneck.
Outcome: The proposed model outperforms strong baselines across 22 sentiment classification domain adaptation setups and improves in-domain model performance.
Breaking Boundaries in Retrieval Systems: Unsupervised Domain Adaptation with Denoise-Finetuning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing domain adaptation methods for dense retrieval models use unadapted rerank models, leading to imprecise labels.
Approach: They propose to adapt a rerank model to the target domain before using it for label generation.
Outcome: The proposed model achieves better results across three retrieval datasets.
Text Classification with Few Examples using Controlled Generalization (N19-1)

Copied to clipboard

Challenge: Current training data for text classification is limited, resulting in limited generalization capacity.
Approach: They propose a feed-forward network that can generalize from unlabeled parsed corpora to produce task-specific semantic vectors.
Outcome: The proposed approach is especially effective in low-data scenarios compared to state-of-the-art methods.
Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings (2020.acl-main)

Copied to clipboard

Challenge: Contextualized representations have become the default for downstream NLP applications.
Approach: They propose a method for converting from contextualized representations to static lookup-table embeddings and apply it to 5 popular pretrained models and 9 sets of pretrained weights.
Outcome: The proposed methods show that pooling over many contexts significantly improves representational quality under intrinsic evaluation.
Tokenizer-Aware Cross-Lingual Adaptation of Decoder-Only LLMs through Embedding Relearning and Swapping (2026.eacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been primarily focused on English, leaving the multilingual ability unexplored.
Approach: They propose a technique that creates new tokenizers and tunes embeddings on fixed model weights for target language adaptation.
Outcome: The proposed method is light-weight and performant but has limitations for older models and high resource languages.

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