Challenge: Recent training-free methods suggest that accuracy can be improved without fine-tuning.
Approach: They propose a method for correcting errors in trained contrastive image-text retrieval models with no additional training, called Nearest Neighbor Normalization.
Outcome: The proposed method improves retrieval metrics for all contrastive models and datasets and does not require training on the reference database.

Similar Papers

Normalized Contrastive Learning for Text-Video Retrieval (2022.emnlp-main)

Copied to clipboard

Challenge: Cross-modal contrastive learning suffers from incorrect normalization of the sum retrieval probabilities of each text or video instance.
Approach: They propose a normalized contrastive learning algorithm that normalizes the sum retrieval probabilities of each instance so that every text and video instance is fairly represented.
Outcome: Empirical results show that NCL brings significant gains in text-video retrieval on different model architectures without any architecture engineering.
Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text Classification (2022.acl-short)

Copied to clipboard

Challenge: Existing methods for multi-label text classification neglect the knowledge from the existing similar instances when predicting labels of a specific text.
Approach: They propose a k nearest neighbor mechanism which retrieves several neighbor instances and interpolates the model output with their labels.
Outcome: Extensive experiments show that the proposed method can bring significant performance improvements to multiple MLTC models including state-of-the-art pretrained and non-pretrained ones.
On Retrieval Augmentation and the Limitations of Language Model Training (2024.naacl-short)

Copied to clipboard

Challenge: Recent efforts to improve the performance of language models (LMs) have focused on scaling up model and training data size, though with steep accompanying energy and compute resource costs.
Approach: They propose to augment a language model with k-nearest neighbors retrieval on its training data to reduce its perplexity.
Outcome: The proposed model reduces storage costs by over 25x compared to traditional retrieval methods for GPT-2 and Mistral 7B .
Contrastive Fine-tuning Improves Robustness for Neural Rankers (2021.findings-acl)

Copied to clipboard

Challenge: Current state-of-the-art neural rankers can deteriorate when exposed to noisy inputs or applied to a new domain.
Approach: They propose a contrastive loss and ranking loss method for fine-tuning rankers that combine ranking loss and rank loss to improve their robustness to query reformulations and noise perturbations.
Outcome: The proposed method outperforms data augmentation for robustifying rankers on four passage ranking datasets.
Learning Decoupled Retrieval Representation for Nearest Neighbour Neural Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to integrate external corpus are sparse in practical applications, and noises in low similarity retrieval could lead to severe performance degradation.
Approach: They propose a method to integrate external corpus into k-nearest neighbor machine translation (kNNMT) instead of storing discrete word sequence, kNN-MT uses a pre-trained NMT model to force decoding the external corpi.
Outcome: The proposed approach improves retrieval accuracy and BLEU score on five domains compared to vanilla kNNMT.
Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings (2022.emnlp-main)

Copied to clipboard

Challenge: Prior work relies on discrete citation relations to generate contrast samples, but discrete ones enforce a hard cut-off to similarity.
Approach: They propose to use nearest neighbor sampling to learn continuous similarity and to sample hard-to-learn negatives and positives by controlling the sampling margin between them.
Outcome: The proposed method outperforms the state-of-the-art on the SciDocs benchmark and can train (or tune) language models sample-efficiently.
Contrastive Data and Learning for Natural Language Processing (2022.naacl-tutorials)

Copied to clipboard

Challenge: Current NLP models heavily rely on effective representation learning algorithms.
Approach: This tutorial introduces contrastive learning and provides an introduction to the techniques.
Outcome: This tutorial provides an introduction to the fundamentals of contrastive learning approaches and the theory behind them.
Exploiting Pseudo Image Captions for Multimodal Summarization (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to multimodal summarization with multimodal output (MSMO) lack reference images for training, and exposure of image captions during training is inconsistent with MSMO’s task settings.
Approach: They propose a coarse-to-fine image-text alignment mechanism to identify the most relevant sentence of each image in a document, resembling the role of image captions in capturing visual knowledge.
Outcome: The proposed method sets up state-of-the-art on all intermodality and intramodality metrics and improves on image recommendation precision.
Nearest Neighbour Few-Shot Learning for Cross-lingual Classification (2021.emnlp-main)

Copied to clipboard

Challenge: Existing pre-trained models can cause over-fitting when limited data are available.
Approach: They propose to use a nearest-neighbor few-shot technique to improve cross-lingual adaptation using 16 distinct languages across two NLP tasks.
Outcome: The proposed approach improves fine-tuning using only a handful of labeled samples in target locales and also generalizes across tasks.
Efficient Nearest Neighbor Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Non-parametric neural language models (NLMs) learn text distributions by memorizing training data points.
Approach: They propose to use an external datastore to learn from a non-parametric language model.
Outcome: The proposed methods achieve up to a 6x speed-up in inference speed while retaining comparable performance.

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