English
Related papers

Related papers: Partially Shuffling the Training Data to Improve L…

200 papers

Recent studies have shown that language models pretrained and/or fine-tuned on randomly permuted sentences exhibit competitive performance on GLUE, putting into question the importance of word order information. Somewhat…

Computation and Language · Computer Science 2022-03-22 Vinit Ravishankar , Mostafa Abdou , Artur Kulmizev , Anders Søgaard

We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner. Recent pre-training methods in NLP focus on learning either bottom or top-level…

Computation and Language · Computer Science 2020-11-02 Haejun Lee , Drew A. Hudson , Kangwook Lee , Christopher D. Manning

Training code-switched language models is difficult due to lack of data and complexity in the grammatical structure. Linguistic constraint theories have been used for decades to generate artificial code-switching sentences to cope with this…

Computation and Language · Computer Science 2019-09-19 Genta Indra Winata , Andrea Madotto , Chien-Sheng Wu , Pascale Fung

Multilingual pre-training significantly improves many multilingual NLP tasks, including machine translation. Most existing methods are based on some variants of masked language modeling and text-denoising objectives on monolingual data.…

Computation and Language · Computer Science 2023-06-02 Alireza Salemi , Amirhossein Abaskohi , Sara Tavakoli , Yadollah Yaghoobzadeh , Azadeh Shakery

Shuffling strategies for stochastic gradient descent (SGD), including incremental gradient, shuffle-once, and random reshuffling, are supported by rigorous convergence analyses for arbitrary within-epoch permutations. In particular, random…

Machine Learning · Computer Science 2026-04-02 Lam M. Nguyen , Dzung T. Phan , Jayant Kalagnanam

We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time. The model represents words and contexts by latent trajectories in an embedding space. At each moment in…

Machine Learning · Statistics 2017-07-19 Robert Bamler , Stephan Mandt

Spoken Language Models (SLMs) aim to learn linguistic competence directly from speech using discrete units, widening access to Natural Language Processing (NLP) technologies for languages with limited written resources. However, progress…

Computation and Language · Computer Science 2026-02-23 Adel Moumen , Guangzhi Sun , Philip C. Woodland

Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…

Computation and Language · Computer Science 2017-05-02 Meng Fang , Trevor Cohn

Scheduled sampling is a technique for avoiding one of the known problems in sequence-to-sequence generation: exposure bias. It consists of feeding the model a mix of the teacher forced embeddings and the model predictions from the previous…

Computation and Language · Computer Science 2019-06-28 Tsvetomila Mihaylova , André F. T. Martins

The skip-gram (SG) model learns word representation by predicting the words surrounding a center word from unstructured text data. However, not all words in the context window contribute to the meaning of the center word. For example, less…

Computation and Language · Computer Science 2021-02-18 Dongjae Kim , Jong-Kook Kim

Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no…

Computation and Language · Computer Science 2021-06-25 Christiaan Jacobs , Herman Kamper

Word meaning change can be inferred from drifts of time-varying word embeddings. However, temporal data may be too sparse to build robust word embeddings and to discriminate significant drifts from noise. In this paper, we compare three…

Computation and Language · Computer Science 2019-09-05 Syrielle Montariol , Alexandre Allauzen

Despite the known limitations, most machine translation systems today still operate on the sentence-level. One reason for this is, that most parallel training data is only sentence-level aligned, without document-level meta information…

Computation and Language · Computer Science 2023-10-20 Frithjof Petrick , Christian Herold , Pavel Petrushkov , Shahram Khadivi , Hermann Ney

Natural Language Processing (NLP) systems commonly leverage bag-of-words co-occurrence techniques to capture semantic and syntactic word relationships. The resulting word-level distributed representations often ignore morphological…

Computation and Language · Computer Science 2015-06-12 Andrew Trask , David Gilmore , Matthew Russell

Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…

Computation and Language · Computer Science 2023-11-14 Fatema Hasan , Yulong Li , James Foulds , Shimei Pan , Bishwaranjan Bhattacharjee

Data plays a fundamental role in the training of Large Language Models (LLMs). While attention has been paid to the collection and composition of datasets, determining the data sampling strategy in training remains an open question. Most…

Computation and Language · Computer Science 2024-06-04 Yunfan Shao , Linyang Li , Zhaoye Fei , Hang Yan , Dahua Lin , Xipeng Qiu

Data augmentation methods for neural machine translation are particularly useful when limited amount of training data is available, which is often the case when dealing with low-resource languages. We introduce a novel augmentation method,…

Computation and Language · Computer Science 2023-11-07 Attila Nagy , Dorina Lakatos , Botond Barta , Judit Ács

As learning models continue to grow in size, enabling on-device local training of these models has emerged as a critical challenge in federated learning. A popular solution is sub-model training, where the server only distributes randomly…

Machine Learning · Computer Science 2025-11-11 Yuyang Deng , Fuli Qiao , Mehrdad Mahdavi

Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is…

Machine Learning · Computer Science 2018-12-11 Avishek Anand , Megha Khosla , Jaspreet Singh , Jan-Hendrik Zab , Zijian Zhang

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…

Computation and Language · Computer Science 2018-09-12 Ruochen Xu , Yiming Yang , Naoki Otani , Yuexin Wu
‹ Prev 1 2 3 10 Next ›