Related papers: Explaining and Improving Model Behavior with k Nea…
We introduce $k$-nearest-neighbor machine translation ($k$NN-MT), which predicts tokens with a nearest neighbor classifier over a large datastore of cached examples, using representations from a neural translation model for similarity…
Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the…
Non-parametric, k-nearest-neighbor algorithms have recently made inroads to assist generative models such as language models and machine translation decoders. We explore whether such non-parametric models can improve machine translation…
K-Nearest Neighbor Neural Machine Translation (kNN-MT) successfully incorporates external corpus by retrieving word-level representations at test time. Generally, kNN-MT borrows the off-the-shelf context representation in the translation…
The $k$-nearest neighbor ($k$-NN) algorithm is one of the most popular methods for nonparametric classification. However, a relevant limitation concerns the definition of the number of neighbors $k$. This parameter exerts a direct impact on…
Graph Neural Networks (GNNs) are widely used for node classification, yet their opaque decision-making limits trust and adoption. While local explanations offer insights into individual predictions, global explanation methods, those that…
k Nearest Neighbor (kNN) method is a simple and popular statistical method for classification and regression. For both classification and regression problems, existing works have shown that, if the distribution of the feature vector has…
Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore, which allows them to learn through explicitly memorizing the training datapoints. While effective, these models often…
Nonparametric learning is a fundamental concept in machine learning that aims to capture complex patterns and relationships in data without making strong assumptions about the underlying data distribution. Owing to simplicity and…
The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the underexplored task of Natural Language Inference (NLI), since…
Recent language models have been improved by the addition of external memory. Nearest neighbor language models retrieve similar contexts to assist in word prediction. The addition of locality levels allows a model to learn how to weight…
Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate this opacity by providing explanations for…
Machine learning (ML) model explainability has received growing attention, especially in the area related to model risk and regulations. In this paper, we reviewed and compared some popular ML model explainability methodologies, especially…
Neural machine translation has achieved promising results on many translation tasks. However, previous studies have shown that neural models induce a non-smooth representation space, which harms its generalization results. Recently, kNN-MT…
k-Nearest-Neighbor Machine Translation (kNN-MT) becomes an important research direction of NMT in recent years. Its main idea is to retrieve useful key-value pairs from an additional datastore to modify translations without updating the NMT…
In Natural Language Processing (NLP), finding data augmentation techniques that can produce high-quality human-interpretable examples has always been challenging. Recently, leveraging kNN such that augmented examples are retrieved from…
As Transformers have become state-of-the-art models for natural language processing (NLP) tasks, the need to understand and explain their predictions is increasingly apparent. Especially in unsupervised applications, such as information…
Given the increasingly prominent role NLP models (will) play in our lives, it is important for human expectations of model behavior to align with actual model behavior. Using Natural Language Inference (NLI) as a case study, we investigate…
Previous knowledge graph embedding approaches usually map entities to representations and utilize score functions to predict the target entities, yet they typically struggle to reason rare or emerging unseen entities. In this paper, we…
Speech recognition performance varies by language, domain, and speaker characteristics such as accent, but fine-tuning a model on any of these categories may lead to catastrophic forgetting. Token-level $k$ nearest neighbor search ($k$NN),…