English
Related papers

Related papers: An Attribution Method for Siamese Encoders

200 papers

Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most existing techniques are designed for encoder-based architectures and rely on linear…

Computation and Language · Computer Science 2026-04-16 Vishal Pramanik , Maisha Maliha , Nathaniel D. Bastian , Sumit Kumar Jha

We consider statistical inference for a finite-dimensional parameter in a regular semiparametric model under a distributed setting with blockwise missingness, where entire blocks of variables are unavailable at certain sites and sharing…

Methodology · Statistics 2025-08-26 Jingyue Huang , Huiyuan Wang , Yuqing Lei , Yong Chen

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on…

Computation and Language · Computer Science 2026-04-21 Jonathan Kamp , Roos Bakker , Dominique Blok

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input hyperparameters which are often randomly set or empirically…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Naman Bansal , Chirag Agarwal , Anh Nguyen

Embedding learning has found widespread applications in recommendation systems and natural language modeling, among other domains. To learn quality embeddings efficiently, adaptive learning rate algorithms have demonstrated superior…

Machine Learning · Computer Science 2021-11-24 Yan Li , Dhruv Choudhary , Xiaohan Wei , Baichuan Yuan , Bhargav Bhushanam , Tuo Zhao , Guanghui Lan

We present a simple sequential sentence encoder for multi-domain natural language inference. Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and fine-tuning of word embeddings. The overall supervised model…

Computation and Language · Computer Science 2017-11-29 Yixin Nie , Mohit Bansal

As deep vision models' popularity rapidly increases, there is a growing emphasis on explanations for model predictions. The inherently explainable attribution method aims to enhance the understanding of model behavior by identifying the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-07 Xianren Zhang , Dongwon Lee , Suhang Wang

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Computation and Language · Computer Science 2025-02-21 Lukas Stankevičius , Mantas Lukoševičius

In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM). SAAM works on top of traditional neural networks and is designed to address the problem of multi-aspect sentiment classification and…

Computation and Language · Computer Science 2020-12-16 Yifan Zhang , Fan Yang , Marjan Hosseinia , Arjun Mukherjee

We introduce a family of pairwise stochastic gradient estimators for gradients of expectations, which are related to the log-derivative trick, but involve pairwise interactions between samples. The simplest example of our new estimator,…

Machine Learning · Computer Science 2022-04-21 Christian J. Walder , Paul Roussel , Richard Nock , Cheng Soon Ong , Masashi Sugiyama

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions…

Computation and Language · Computer Science 2021-02-26 Yaru Hao , Li Dong , Furu Wei , Ke Xu

As deep learning (DL) efficacy grows, concerns for poor model explainability grow also. Attribution methods address the issue of explainability by quantifying the importance of an input feature for a model prediction. Among various methods,…

Machine Learning · Computer Science 2022-07-01 Daniel Lundstrom , Tianjian Huang , Meisam Razaviyayn

This article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings. By incorporating the embeddings of neighboring tokens in text corpora, it continuously updates the representation of…

Computation and Language · Computer Science 2025-04-22 Mario M. Kubek , Shiraj Pokharel , Thomas Böhme , Emma L. McDaniel , Herwig Unger , Armin R. Mikler

Recently, neural network approaches for parsing have largely automated the combination of individual features, but still rely on (often a larger number of) atomic features created from human linguistic intuition, and potentially omitting…

Computation and Language · Computer Science 2016-06-22 James Cross , Liang Huang

Spatial transcriptomics (ST) has revolutionized biomedical research by enabling high resolution gene expression profiling within tissues. However, the high cost and scarcity of high resolution ST data remain significant challenges. We…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Yaoyu Fang , Jiahe Qian , Xinkun Wang , Lee A. Cooper , Bo Zhou

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Machine Learning · Computer Science 2025-01-31 Charles O'Neill , Alim Gumran , David Klindt

Feature attribution scores are used for explaining the prediction of a text classifier to users by highlighting a k number of tokens. In this work, we propose a way to determine the number of optimal k tokens that should be displayed from…

Computation and Language · Computer Science 2023-11-06 Jonathan Kamp , Lisa Beinborn , Antske Fokkens

In supervised learning with distributional inputs in the two-stage sampling setup, relevant to applications like learning-based medical screening or causal learning, the inputs (which are probability distributions) are not accessible in the…

Machine Learning · Computer Science 2026-01-22 Christian Fiedler

Parameter inference is a fundamental problem in data-driven modeling. Given observed data that is believed to be a realization of some parameterized model, the aim is to find parameter values that are able to explain the observed data. In…

Data Structures and Algorithms · Computer Science 2016-04-20 Carlo Albert , Simone Ulzega , Ruedi Stoop

Feature attribution methods are a popular approach to explain the behavior of machine learning models. They assign importance scores to each input feature, quantifying their influence on the model's prediction. However, evaluating these…

Machine Learning · Computer Science 2025-06-02 Magamed Taimeskhanov , Damien Garreau