English
Related papers

Related papers: Understanding Domain Learning in Language Models T…

200 papers

Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only…

Computation and Language · Computer Science 2018-08-30 Fréderic Godin , Kris Demuynck , Joni Dambre , Wesley De Neve , Thomas Demeester

The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data…

Computer Vision and Pattern Recognition · Computer Science 2016-08-23 Konstantinos Bousmalis , George Trigeorgis , Nathan Silberman , Dilip Krishnan , Dumitru Erhan

Deep neural networks excel at learning from labeled data and achieve state-of-the-art resultson a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a…

Computation and Language · Computer Science 2020-10-29 Alan Ramponi , Barbara Plank

We introduce a technique based on the singular vector canonical correlation analysis (SVCCA) for measuring the generality of neural network layers across a continuously-parametrized set of tasks. We illustrate this method by studying…

Machine Learning · Statistics 2018-07-03 Martin Magill , Faisal Qureshi , Hendrick W. de Haan

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…

Machine Learning · Computer Science 2020-02-10 Garrett Wilson , Diane J. Cook

Classical machine learning assumes that the training and test sets come from the same distributions. Therefore, a model learned from the labeled training data is expected to perform well on the test data. However, This assumption may not…

Machine Learning · Computer Science 2020-10-12 Abolfazl Farahani , Sahar Voghoei , Khaled Rasheed , Hamid R. Arabnia

We present an approach for assessing how multilingual large language models (LLMs) learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent and dependency structures by casting parsing as sequence…

Computation and Language · Computer Science 2023-09-21 Alberto Muñoz-Ortiz , David Vilares , Carlos Gómez-Rodríguez

The scarcity of labeled training data often prohibits the internationalization of NLP models to multiple languages. Recent developments in cross-lingual understanding (XLU) has made progress in this area, trying to bridge the language…

Computation and Language · Computer Science 2019-09-23 Guokun Lai , Barlas Oguz , Yiming Yang , Veselin Stoyanov

Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a…

Learned joint representations of images and text form the backbone of several important cross-domain tasks such as image captioning. Prior work mostly maps both domains into a common latent representation in a purely supervised fashion.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Shweta Mahajan , Iryna Gurevych , Stefan Roth

Most natural language processing systems based on machine learning are not robust to domain shift. For example, a state-of-the-art syntactic dependency parser trained on Wall Street Journal sentences has an absolute drop in performance of…

Computation and Language · Computer Science 2013-12-17 Edouard Grave , Guillaume Obozinski , Francis Bach

Contextual embedding-based language models trained on large data sets, such as BERT and RoBERTa, provide strong performance across a wide range of tasks and are ubiquitous in modern NLP. It has been observed that fine-tuning these models on…

Computation and Language · Computer Science 2021-09-16 Vin Sachidananda , Jason S. Kessler , Yi-an Lai

This work connects language model adaptation with concepts of machine learning theory. We consider a training setup with a large out-of-domain set and a small in-domain set. We derive how the benefit of training a model on either set…

Computation and Language · Computer Science 2022-03-23 David Grangier , Dan Iter

Large protein language models are adept at capturing the underlying evolutionary information in primary structures, offering significant practical value for protein engineering. Compared to natural language models, protein amino acid…

Computation and Language · Computer Science 2023-10-27 Yang Tan , Mingchen Li , Pan Tan , Ziyi Zhou , Huiqun Yu , Guisheng Fan , Liang Hong

Large language models (LLMs) have showcased their capability with few-shot inference known as in-context learning. However, in-domain demonstrations are not always readily available in real scenarios, leading to cross-domain in-context…

Computation and Language · Computer Science 2023-11-21 Quanyu Long , Wenya Wang , Sinno Jialin Pan

Supervised models of NLP rely on large collections of text which closely resemble the intended testing setting. Unfortunately matching text is often not available in sufficient quantity, and moreover, within any domain of text, data is…

Computation and Language · Computer Science 2019-06-10 Yitong Li , Timothy Baldwin , Trevor Cohn

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

Machine Learning · Computer Science 2022-05-12 Antonio-Javier Gallego , Jorge Calvo-Zaragoza , Robert B. Fisher

Domain adaptation is a popular paradigm in modern machine learning which aims at tackling the problem of divergence (or shift) between the labeled training and validation datasets (source domain) and a potentially large unlabeled dataset…

Machine Learning · Computer Science 2023-11-10 Evgeny M Mirkes , Jonathan Bac , Aziz Fouché , Sergey V. Stasenko , Andrei Zinovyev , Alexander N. Gorban

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

Computation and Language · Computer Science 2024-08-28 Shannon Zejiang Shen , Hunter Lang , Bailin Wang , Yoon Kim , David Sontag

Domain classification is the task of mapping spoken language utterances to one of the natural language understanding domains in intelligent personal digital assistants (IPDAs). This is a major component in mainstream IPDAs in industry.…

Machine Learning · Computer Science 2019-05-06 Han Li , Jihwan Lee , Sidharth Mudgal , Ruhi Sarikaya , Young-Bum Kim