paper-with-me

Papers

Word2Bits - Quantized Word Vectors

2018-03-15 · Maximilian Lam

Word vectors require significant amounts of memory and storage, posing issues to resource limited devices like mobile phones and GPUs. We show that high quality quantized word vectors using 1-2 bits per parameter can be learned by introducing a quantization function into Word2Vec. We furthermore show that training with the quantization function acts as a regularizer. We train word vectors on English Wikipedia (2017) and evaluate them on standard word similarity and analogy tasks and on question answering (SQuAD). Our quantized word vectors not only take 8-16x less space than full precision (32 bit) word vectors but also outperform them on word similarity tasks and question answering.

📄 PDF Abstract BibTeX arXiv:1803.05651

Code (1)

agnusmaximus/Word2Bits

Tasks

QuantizationQuestion AnsweringWord Similarity

Similar Papers 제목 키워드 기반

Low-bit quantization and quantization-aware training for small-footprint keyword spotting

2018-10-19 · Yuriy Mishchenko, Yusuf Goren, Ming Sun, Chris Beauchene 외

We investigate low-bit quantization to reduce computational cost of deep neural network (DNN) based keyword spotting (KWS). We propose approaches to further reduce quantization bits via integrating quantization into keyw…

Keyword SpottingQuantizationSmall-Footprint Keyword Spotting

Personalized word representations Carrying Personalized Semantics Learned from Social Network Posts

2017-10-29 · Zih-Wei Lin, Tzu-Wei Sung, Hung-Yi Lee, Lin-shan Lee

Distributed word representations have been shown to be very useful in various natural language processing (NLP) application tasks. These word vectors learned from huge corpora very often carry both semantic and syntactic…

SentenceSentence Completion

A Quantum-Like Approach to Word Sense Disambiguation

2019-09-01 · RANLP 2019 9 · Fabio Tamburini

This paper presents a novel algorithm for Word Sense Disambiguation (WSD) based on Quantum Probability Theory. The Quantum WSD algorithm requires concepts representations as vectors in the complex domain and thus we have…

SentenceSentence EmbeddingsWord Sense Disambiguation

Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks

2020-12-14 · Herman Kamper, Benjamin van Niekerk

We investigate segmenting and clustering speech into low-bitrate phone-like sequences without supervision. We specifically constrain pretrained self-supervised vector-quantized (VQ) neural networks so that blocks of cont…

ClusteringSegmentation

Parameter Free Hierarchical Graph-Based Clustering for Analyzing Continuous Word Embeddings

2017-08-01 · WS 2017 8 · Thomas Alex Trost, er, Dietrich Klakow

Word embeddings are high-dimensional vector representations of words and are thus difficult to interpret. In order to deal with this, we introduce an unsupervised parameter free method for creating a hierarchical graphic…

ClusteringDimensionality ReductionWord Embeddings