Challenge: a new method for text classification ignores strong non-linguistic similarities like homophily . authors are typically represented via their linguistic profiles, i.e. information avail-able in the text .
Approach: They use homophily cues to retrofit text-based author representations with non-linguistic information and introduce a trade-off parameter.
Outcome: The proposed method improves on two author-attribute prediction tasks with large labels.

Similar Papers

Interpretable Text Embeddings and Text Similarity Explanation: A Survey (2025.emnlp-main)

Copied to clipboard

Challenge: Text embeddings are a fundamental component in many NLP tasks, but their interpretation and explanation remain challenging.
Approach: They propose a framework for interpretable text embeddings and text similarity explanation . they characterize the main ideas, approaches, and trade-offs and discuss lessons learned .
Outcome: The proposed methods are compared with existing models and compare them with existing ones.
Co-Evolving LLMs and Embedding Models via Density-Guided Preference Optimization for Text Clustering (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for text clustering use static pseudo-oracles, i.e., unidirectionally querying them for similarity assessment or data augmentation.
Approach: They propose a training framework that enables bidirectional refinement between LLMs and embedding models by using task-aware prompts to guide the LLM in generating interpretations for the input texts.
Outcome: Experiments on 14 benchmark datasets across 5 tasks demonstrate the effectiveness of the proposed training framework.
A Retrofitting Model for Incorporating Semantic Relations into Word Embeddings (2020.coling-main)

Copied to clipboard

Challenge: Existing word embedding models mix semantic similarity with other types of relatedness.
Approach: They propose a model that leverages relational knowledge available in a knowledge resource to improve word embeddings.
Outcome: The proposed model improves word embeddings on synonymy, antonymy and hypernymy relations in WordNet and significantly improves lexical entailment detection task.
Adversarial Removal of Demographic Attributes from Text Data (D18-1)

Copied to clipboard

Challenge: Recent advances in Representation Learning and Adversarial Training remove unwanted features from the learned representation.
Approach: They show that demographic information of authors is encoded in the intermediate representations learned by text-based neural classifiers.
Outcome: The proposed approach achieves higher accuracies on the same dataset, the authors show . they show that the proposed approach is effective in removing unwanted features from the learned representations.
The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure (2025.emnlp-main)

Copied to clipboard

Challenge: Embedding-based similarity metrics can be influenced by content dimensions and spurious attributes like the text’s source or language.
Approach: They propose a debiasing algorithm that removes observed confounders from encoder representations and removes them from the encoder.
Outcome: The proposed method improves on out-of-distribution benchmarks and on benchmarks, but performance is not affected.
Joint Embedding of Words and Labels for Text Classification (P18-1)

Copied to clipboard

Challenge: Existing approaches to text classification use word embeddings to capture semantic regularities between words.
Approach: They propose to view text classification as a label-word joint embedding problem . they use a framework that measures compatibility between text sequences and labels .
Outcome: The proposed framework outperforms the state-of-the-art methods on large text datasets.
Leveraging the Structure of Pre-trained Embeddings to Minimize Annotation Effort (2024.naacl-long)

Copied to clipboard

Challenge: Current approaches for text classification are based on fine-tuning the representations computed by large language models.
Approach: They propose to exploit structural properties of pre-trained embeddings to spread information . they use a semisupervised strategy to train models with minimal annotation effort .
Outcome: The proposed method outperforms self-training and random walk labels on different datasets.
Fusing Label Embedding into BERT: An Efficient Improvement for Text Classification (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods to improve text classification performance of pre-trained models have been used to improve their performance.
Approach: They propose a method for improving BERT's performance by using a label embedding technique while keeping almost the same computational cost.
Outcome: The proposed method improves BERT's performance on six text classification benchmark datasets while keeping almost the same computational cost.
Embedding Meta-Textual Information for Improved Learning to Rank (2020.coling-main)

Copied to clipboard

Challenge: a neural representation learning approach has not been extended to meta-textual information that is readily available for many IR tasks.
Approach: They propose a framework that learns embeddings for meta-textual categories and optimizes a pairwise ranking objective for improved matching based on combined embedds of textual and meta-tactile information.
Outcome: The proposed framework improves cross-lingual retrieval in the Wikipedia domain and Patent domain.
Improving Text Embeddings with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for obtaining text embeddings require complex training pipelines . authors leverage proprietary LLMs to generate diverse synthetic data for text embeds based on 93 languages .
Approach: They propose a method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.
Outcome: The proposed method achieves strong performance on competitive text embedding benchmarks without using any labeled data.

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