English
Related papers

Related papers: Smaller Text Classifiers with Discriminative Clust…

200 papers

In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair encoding (BPE) and its variants are the predominant approach…

Computation and Language · Computer Science 2018-10-23 Elizabeth Salesky , Andrew Runge , Alex Coda , Jan Niehues , Graham Neubig

In data dominated systems and applications, a concept of representing words in a numerical format has gained a lot of attention. There are a few approaches used to generate such a representation. An interesting issue that should be…

Computation and Language · Computer Science 2020-12-08 Shahin Atakishiyev , Marek Z. Reformat

Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen…

Computation and Language · Computer Science 2016-09-27 Parminder Bhatia , Robert Guthrie , Jacob Eisenstein

We compare the performance of different clustering algorithms applied to the task of unsupervised text categorization. We consider agglomerative clustering algorithms, principal direction divisive partitioning and (for the first time)…

Disordered Systems and Neural Networks · Physics 2007-05-23 D. Volk , M. G. Stepanov

We study an interesting problem in training neural network-based models for natural language generation tasks, which we call the \emph{representation degeneration problem}. We observe that when training a model for natural language…

Computation and Language · Computer Science 2019-07-30 Jun Gao , Di He , Xu Tan , Tao Qin , Liwei Wang , Tie-Yan Liu

The internal structure and operation mechanism of large-scale language models are analyzed theoretically, especially how Transformer and its derivative architectures can restrict computing efficiency while capturing long-term dependencies.…

Machine Learning · Computer Science 2024-05-21 Taiyuan Mei , Yun Zi , Xiaohan Cheng , Zijun Gao , Qi Wang , Haowei Yang

This work presents a new and simple approach for fine-tuning pretrained word embeddings for text classification tasks. In this approach, the class in which a term appears, acts as an additional contextual variable during the fine tuning…

Computation and Language · Computer Science 2019-12-17 Amr Al-Khatib , Samhaa R. El-Beltagy

It has been shown that word embeddings derived from large corpora tend to incorporate biases present in their training data. Various methods for mitigating these biases have been proposed, but recent work has demonstrated that these methods…

Computation and Language · Computer Science 2023-06-27 Hailey Joren , David Alvarez-Melis

An essential part of monitoring machine learning models in production is measuring input and output data drift. In this paper, we present a system for measuring distributional shifts in natural language data and highlight and investigate…

Computation and Language · Computer Science 2023-12-06 Gyandev Gupta , Bashir Rastegarpanah , Amalendu Iyer , Joshua Rubin , Krishnaram Kenthapadi

This paper evaluates existing and newly proposed answer selection methods based on pre-trained word embeddings. Word embeddings are highly effective in various natural language processing tasks and their integration into traditional…

Information Retrieval · Computer Science 2017-08-16 Rishav Chakravarti , Jiri Navratil , Cicero Nogueira dos Santos

Word embeddings are an essential component in a wide range of natural language processing applications. However, distributional semantic models are known to struggle when only a small number of context sentences are available. Several…

Computation and Language · Computer Science 2019-10-02 Jeroen Van Hautte , Guy Emerson , Marek Rei

Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work…

Machine Learning · Computer Science 2023-02-09 Yuhui Zhang , Jeff Z. HaoChen , Shih-Cheng Huang , Kuan-Chieh Wang , James Zou , Serena Yeung

Cluster workload allocation often requires complex configurations, creating a usability gap. This paper introduces a semantic, intent-driven scheduling paradigm for cluster systems using Natural Language Processing. The system employs a…

Artificial Intelligence · Computer Science 2026-02-23 Leszek Sliwko , Jolanta Mizeria-Pietraszko

Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…

Computation and Language · Computer Science 2021-12-13 Elizabeth Salesky , David Etter , Matt Post

Clustering a lexicon of words is a well-studied problem in natural language processing (NLP). Word clusters are used to deal with sparse data in statistical language processing, as well as features for solving various NLP tasks (text…

Computation and Language · Computer Science 2018-08-17 Effi Levi , Saggy Herman , Ari Rappoport

Despite recent advances in neural text generation, encoding the rich diversity in human language remains elusive. We argue that the sub-optimal text generation is mainly attributable to the imbalanced token distribution, which particularly…

Computation and Language · Computer Science 2020-10-06 Byung-Ju Choi , Jimin Hong , David Keetae Park , Sang Wan Lee

We introduce adaptive input representations for neural language modeling which extend the adaptive softmax of Grave et al. (2017) to input representations of variable capacity. There are several choices on how to factorize the input and…

Computation and Language · Computer Science 2019-02-26 Alexei Baevski , Michael Auli

In recent years, word embeddings have been surprisingly effective at capturing intuitive characteristics of the words they represent. These vectors achieve the best results when training corpora are extremely large, sometimes billions of…

Computation and Language · Computer Science 2017-12-06 Willie Boag , Hassan Kané

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

Ensembling word embeddings to improve distributed word representations has shown good success for natural language processing tasks in recent years. These approaches either carry out straightforward mathematical operations over a set of…

Computation and Language · Computer Science 2018-08-14 James O' Neill , Danushka Bollegala