English
Related papers

Related papers: Redundancy, Isotropy, and Intrinsic Dimensionality…

200 papers

Metric data structures (distance oracles, distance labeling schemes, routing schemes) and low-distortion embeddings provide a powerful algorithmic methodology, which has been successfully applied for approximation algorithms \cite{llr},…

Data Structures and Algorithms · Computer Science 2015-04-08 Michael Elkin , Arnold Filtser , Ofer Neiman

We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pretrained…

Computation and Language · Computer Science 2026-05-26 Amirhossein Yousefiramandi , Ciaran Cooney

Learned vector representations of words are useful tools for many information retrieval and natural language processing tasks due to their ability to capture lexical semantics. However, while many such tasks involve or even rely on named…

Computation and Language · Computer Science 2020-02-13 Satya Almasian , Andreas Spitz , Michael Gertz

Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of…

Computation and Language · Computer Science 2019-04-11 Brendan Whitaker , Denis Newman-Griffis , Aparajita Haldar , Hakan Ferhatosmanoglu , Eric Fosler-Lussier

Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest…

Computation and Language · Computer Science 2020-11-06 Jingyi He , KC Tsiolis , Kian Kenyon-Dean , Jackie Chi Kit Cheung

Efficient representation of text documents is an important building block in many NLP tasks. Research on long text categorization has shown that simple weighted averaging of word vectors for sentence representation often outperforms more…

Computation and Language · Computer Science 2019-11-20 Vivek Gupta , Ankit Saw , Pegah Nokhiz , Harshit Gupta , Partha Talukdar

In the era of dense retrieval, document indexing and retrieval is largely based on encoding models that transform text documents into embeddings. The efficiency of retrieval is directly proportional to the number of documents and the size…

Information Retrieval · Computer Science 2024-12-16 Federico Siciliano , Francesca Pezzuti , Nicola Tonellotto , Fabrizio Silvestri

Word embeddings and convolutional neural networks (CNN) have attracted extensive attention in various classification tasks for Twitter, e.g. sentiment classification. However, the effect of the configuration used to train and generate the…

Information Retrieval · Computer Science 2017-03-23 Xiao Yang , Craig Macdonald , Iadh Ounis

Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks. The embedding vectors are typically…

Information Retrieval · Computer Science 2017-07-18 Hamed Zamani , W. Bruce Croft

In recent years, self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data. An intriguing research avenue involves developing…

Machine Learning · Computer Science 2023-10-30 Denis Janiak , Jakub Binkowski , Piotr Bielak , Tomasz Kajdanowicz

Question-answering systems and voice assistants are becoming major part of client service departments of many organizations, helping them to reduce the labor costs of staff. In many such systems, there is always natural language…

Computation and Language · Computer Science 2019-04-02 Aleksandr Perevalov , Daniil Kurushin , Rustam Faizrakhmanov , Farida Khabibrakhmanova

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

Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate verbose thought processes with considerable redundancy, leading to increased inference costs and reduced efficiency. We introduce a…

Artificial Intelligence · Computer Science 2026-02-17 Zeju Li , Jianyuan Zhong , Ziyang Zheng , Xiangyu Wen , Zhijian Xu , Yingying Cheng , Fan Zhang , Qiang Xu

We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps. Models achieve high accuracy even with very small…

Machine Learning · Computer Science 2025-10-22 Brady Bhalla , Honglu Fan , Nancy Chen , Tony Yue YU

A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach has two shortcomings. First, such methods consider single…

Semantic representations of text, i.e. representations of natural language which capture meaning by geometry, are essential for areas such as information retrieval and document grouping. High-dimensional trained dense vectors have received…

Computation and Language · Computer Science 2023-12-01 Beatrix M. G. Nielsen , Lars Kai Hansen

In essence, embedding algorithms work by optimizing the distance between a word and its usual context in order to generate an embedding space that encodes the distributional representation of words. In addition to single words or word…

Computation and Language · Computer Science 2021-04-14 Andres Garcia-Silva , Ronald Denaux , Jose Manuel Gomez-Perez

Both in scientific literature and in industry,, Semantic and context-aware Natural Language Processing-based solutions have been gaining importance in recent years. The possibilities and performance shown by these models when dealing with…

Computation and Language · Computer Science 2022-04-19 Álvaro Huertas-García , Alejandro Martín , Javier Huertas-Tato , David Camacho

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

Computation and Language · Computer Science 2024-06-25 Allmin Balloccu , Jack Zhang

We provide the first extensive evaluation of how using different types of context to learn skip-gram word embeddings affects performance on a wide range of intrinsic and extrinsic NLP tasks. Our results suggest that while intrinsic tasks…

Computation and Language · Computer Science 2017-07-20 Oren Melamud , David McClosky , Siddharth Patwardhan , Mohit Bansal