English
Related papers

Related papers: Finding Experts in Transformer Models

200 papers

Knowledge-enhanced pre-trained models for language representation have been shown to be more effective in knowledge base construction tasks (i.e.,~relation extraction) than language models such as BERT. These knowledge-enhanced language…

Computation and Language · Computer Science 2022-10-25 Jiacheng Li , Yannis Katsis , Tyler Baldwin , Ho-Cheol Kim , Andrew Bartko , Julian McAuley , Chun-Nan Hsu

The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity. However, with trillions of parameters, MoE is hard to be deployed on cloud or mobile…

Machine Learning · Computer Science 2022-06-03 Tianyu Chen , Shaohan Huang , Yuan Xie , Binxing Jiao , Daxin Jiang , Haoyi Zhou , Jianxin Li , Furu Wei

The emergence of Pre-trained Language Models (PLMs) has achieved tremendous success in the field of Natural Language Processing (NLP) by learning universal representations on large corpora in a self-supervised manner. The pre-trained models…

Information Retrieval · Computer Science 2023-09-14 Peng Liu , Lemei Zhang , Jon Atle Gulla

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific level of linguistic unit, which cause great inconvenience when being confronted with handling multiple…

Computation and Language · Computer Science 2020-09-11 Yian Li , Hai Zhao

Having a unified, coherent taxonomy is essential for effective knowledge representation in domain-specific applications as diverse terminologies need to be mapped to underlying concepts. Traditional manual approaches to taxonomy alignment…

Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest…

Computation and Language · Computer Science 2020-11-06 Jingyi He , KC Tsiolis , Kian Kenyon-Dean , Jackie Chi Kit Cheung

Machine learning models are routinely trained on a mixture of different data domains. Different domain weights yield very different downstream performances. We propose the Soup-of-Experts, a novel architecture that can instantiate a model…

Machine Learning · Computer Science 2025-02-05 Pierre Ablin , Angelos Katharopoulos , Skyler Seto , David Grangier

Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic…

Computation and Language · Computer Science 2019-04-29 Nelson F. Liu , Matt Gardner , Yonatan Belinkov , Matthew E. Peters , Noah A. Smith

This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level…

Computation and Language · Computer Science 2021-10-15 Kelvin Lo , Yuan Jin , Weicong Tan , Ming Liu , Lan Du , Wray Buntine

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is,…

Computation and Language · Computer Science 2020-10-07 Marius Mosbach , Anna Khokhlova , Michael A. Hedderich , Dietrich Klakow

Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these…

Computation and Language · Computer Science 2018-12-21 Walid Shalaby , Wlodek Zadrozny , Hongxia Jin

Efficient inference is a critical challenge in deep generative modeling, particularly as diffusion models grow in capacity and complexity. While increased complexity often improves accuracy, it raises compute costs, latency, and memory…

Machine Learning · Computer Science 2025-09-24 Siu Hang Ho , Prasad Ganesan , Nguyen Duong , Daniel Schlabig

Recent research suggests that the feed-forward module within Transformers can be viewed as a collection of key-value memories, where the keys learn to capture specific patterns from the input based on the training examples. The values then…

Computation and Language · Computer Science 2023-10-25 Sunit Bhattacharya , Ondrej Bojar

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn…

Computer Vision and Pattern Recognition · Computer Science 2014-02-20 Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian Goodfellow , Rob Fergus

Multilingual language models (MLLMs) have demonstrated remarkable abilities to transfer knowledge across languages, despite being trained without explicit cross-lingual supervision. We analyze the parameter spaces of three MLLMs to study…

Computation and Language · Computer Science 2025-06-03 Frederick Riemenschneider , Anette Frank

Machine Learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption by the level of trust that models afford users. Human vs. machine performance…

Machine learning (ML) practitioners are increasingly tasked with developing models that are aligned with non-technical experts' values and goals. However, there has been insufficient consideration on how practitioners should translate…

Machine Learning · Computer Science 2022-07-19 Valerie Chen , Umang Bhatt , Hoda Heidari , Adrian Weller , Ameet Talwalkar

Language models (LMs) increasingly drive real-world applications that require world knowledge. However, the internal processes through which models turn data into representations of knowledge and beliefs about the world, are poorly…

Computation and Language · Computer Science 2025-09-04 Daniela Gottesman , Alon Gilae-Dotan , Ido Cohen , Yoav Gur-Arieh , Marius Mosbach , Ori Yoran , Mor Geva

Task arithmetic refers to editing the pre-trained model by adding a weighted sum of task vectors, each of which is the weight update from the pre-trained model to fine-tuned models for certain tasks. This approach recently gained attention…

Machine Learning · Computer Science 2025-05-27 Hongkang Li , Yihua Zhang , Shuai Zhang , Meng Wang , Sijia Liu , Pin-Yu Chen

We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the…

Machine Learning · Computer Science 2024-10-31 Mingze Wang , Weinan E