English
Related papers

Related papers: Memory-Efficient FastText: A Comprehensive Approac…

200 papers

We introduce a memory-based approach to part of speech tagging. Memory-based learning is a form of supervised learning based on similarity-based reasoning. The part of speech tag of a word in a particular context is extrapolated from the…

cmp-lg · Computer Science 2008-02-03 Walter Daelemans , Jakub Zavrel , Peter Berck , Steven Gillis

Embedding image features into a binary Hamming space can improve both the speed and accuracy of large-scale query-by-example image retrieval systems. Supervised hashing aims to map the original features to compact binary codes in a manner…

Machine Learning · Computer Science 2016-11-17 Guosheng Lin , Chunhua Shen , Anton van den Hengel

Since its introduction, Word2Vec and its variants are widely used to learn semantics-preserving representations of words or entities in an embedding space, which can be used to produce state-of-art results for various Natural Language…

Computation and Language · Computer Science 2016-06-28 Jeroen B. P. Vuurens , Carsten Eickhoff , Arjen P. de Vries

The suffix array is an efficient data structure for in-memory pattern search. Suffix arrays can also be used for external-memory pattern search, via two-level structures that use an internal index to identify the correct block of suffix…

Data Structures and Algorithms · Computer Science 2013-03-27 Simon Gog , Alistair Moffat , J. Shane Culpepper , Andrew Turpin , Anthony Wirth

In this study, we aim to explore Multitask Speech Language Model (SpeechLM) efficient inference via token reduction. Unlike other modalities such as vision or text, speech has unique temporal dependencies, making previous efficient…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-07 Yichen Lu , Jiaqi Song , Chao-Han Huck Yang , Shinji Watanabe

Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive that can improve computational and statistical efficiency.…

Machine Learning · Computer Science 2015-04-01 Paul Mineiro , Nikos Karampatziakis

We propose new static word embeddings optimised for sentence semantic representation. We first extract word embeddings from a pre-trained Sentence Transformer, and improve them with sentence-level principal component analysis, followed by…

Computation and Language · Computer Science 2025-10-01 Takashi Wada , Yuki Hirakawa , Ryotaro Shimizu , Takahiro Kawashima , Yuki Saito

Fast Fourier Transforms (FFT) are widely used to reduce memory and computational costs in deep learning. However, existing implementations, including standard FFT and real FFT (rFFT), cannot achieve true in-place computation. In particular,…

Machine Learning · Computer Science 2025-12-23 Xinyu Ding , Bangtian Liu , Siyu Liao , Zhongfeng Wang

Text classification, as the task consisting in assigning categories to textual instances, is a very common task in information science. Methods learning distributed representations of words, such as word embeddings, have become popular in…

Computation and Language · Computer Science 2020-12-15 Arkaitz Zubiaga

With multilingual machine translation (MMT) models continuing to grow in size and number of supported languages, it is natural to reuse and upgrade existing models to save computation as data becomes available in more languages. However,…

Computation and Language · Computer Science 2023-02-08 Simeng Sun , Maha Elbayad , Anna Sun , James Cross

We study the fundamental question of how efficiently suffix array entries can be accessed when the array cannot be stored explicitly. The suffix array $SA_T[1..n]$ of a text $T$ of length $n$ encodes the lexicographic order of its suffixes…

Data Structures and Algorithms · Computer Science 2025-10-23 Dominik Kempa , Tomasz Kociumaka

Term-based sparse representations dominate the first-stage text retrieval in industrial applications, due to its advantage in efficiency, interpretability, and exact term matching. In this paper, we study the problem of transferring the…

Information Retrieval · Computer Science 2020-10-05 Yang Bai , Xiaoguang Li , Gang Wang , Chaoliang Zhang , Lifeng Shang , Jun Xu , Zhaowei Wang , Fangshan Wang , Qun Liu

In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical…

Computation and Language · Computer Science 2016-11-22 Mikael Kågebäck , Hans Salomonsson

Conventional word embeddings represent words with fixed vectors, which are usually trained based on co-occurrence patterns among words. In doing so, however, the power of such representations is limited, where the same word might be…

Computation and Language · Computer Science 2020-01-10 Hongming Zhang , Jiaxin Bai , Yan Song , Kun Xu , Changlong Yu , Yangqiu Song , Wilfred Ng , Dong Yu

Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be…

Computation and Language · Computer Science 2017-06-22 Massimiliano Mancini , Jose Camacho-Collados , Ignacio Iacobacci , Roberto Navigli

Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets. However, existing mixed-precision methods typically suffer from one of two limitations: they either rely on expensive…

Machine Learning · Computer Science 2026-02-03 Xin Nie , Haicheng Zhang , Liang Dong , Beining Feng , Jinhong Weng , Guiling Sun

In this paper, we present a fast and strong neural approach for general purpose text matching applications. We explore what is sufficient to build a fast and well-performed text matching model and propose to keep three key features…

Computation and Language · Computer Science 2019-08-02 Runqi Yang , Jianhai Zhang , Xing Gao , Feng Ji , Haiqing Chen

In this paper, we present a new data structure called the packed compact trie (packed c-trie) which stores a set $S$ of $k$ strings of total length $n$ in $n \log\sigma + O(k \log n)$ bits of space and supports fast pattern matching queries…

Data Structures and Algorithms · Computer Science 2017-10-11 Takuya Takagi , Shunsuke Inenaga , Kunihiko Sadakane , Hiroki Arimura

Recently, the growing memory demands of embedding tables in Deep Learning Recommendation Models (DLRMs) pose great challenges for model training and deployment. Existing embedding compression solutions cannot simultaneously meet three key…

Machine Learning · Computer Science 2024-03-28 Hailin Zhang , Zirui Liu , Boxuan Chen , Yikai Zhao , Tong Zhao , Tong Yang , Bin Cui

Generating high-performance code for diverse hardware and application domains is challenging. Functional array programming languages with patterns like map and reduce have been successfully combined with term rewriting to define and explore…

Programming Languages · Computer Science 2022-06-06 Thomas Koehler , Phil Trinder , Michel Steuwer