English
Related papers

Related papers: Rethinking the Value of Transformer Components

200 papers

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Computation and Language · Computer Science 2023-10-25 Piotr Nawrot , Jan Chorowski , Adrian Łańcucki , Edoardo M. Ponti

Transformer-based encoder-decoder models produce a fused token-wise representation after every encoder layer. We investigate the effects of allowing the encoder to preserve and explore alternative hypotheses, combined at the end of the…

Computation and Language · Computer Science 2021-07-23 Mikhail Burtsev , Anna Rumshisky

Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory. In this work, we propose to address this gap by focusing on understanding the…

Computation and Language · Computer Science 2019-09-18 Shilin He , Zhaopeng Tu , Xing Wang , Longyue Wang , Michael R. Lyu , Shuming Shi

Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2…

Transformers are responsible for the vast majority of recent advances in natural language processing. The majority of practical natural language processing applications of these models are typically enabled through transfer learning. This…

Computation and Language · Computer Science 2024-02-02 Vladislav Mosin , Igor Samenko , Alexey Tikhonov , Borislav Kozlovskii , Ivan P. Yamshchikov

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Machine Learning · Computer Science 2026-04-24 Costin-Andrei Oncescu , Depen Morwani , Samy Jelassi , Alexandru Meterez , Mujin Kwun , Sham Kakade

Transformer architectures are the backbone of most modern language models, but understanding the inner workings of these models still largely remains an open problem. One way that research in the past has tackled this problem is by…

Computation and Language · Computer Science 2025-02-04 Utkarsh Tiwari , Aviral Gupta , Michael Hahn

Multilingual machine translation has attracted much attention recently due to its support of knowledge transfer among languages and the low cost of training and deployment compared with numerous bilingual models. A known challenge of…

Computation and Language · Computer Science 2022-01-25 Hongyu Gong , Xian Li , Dmitriy Genzel

Recent psycholinguistic studies have drawn conflicting conclusions about the relationship between the quality of a language model and the ability of its surprisal estimates to predict human reading times, which has been speculated to be due…

Computation and Language · Computer Science 2023-10-24 Byung-Doh Oh , William Schuler

We investigate multi-scale transformer language models that learn representations of text at multiple scales, and present three different architectures that have an inductive bias to handle the hierarchical nature of language. Experiments…

Computation and Language · Computer Science 2020-05-05 Sandeep Subramanian , Ronan Collobert , Marc'Aurelio Ranzato , Y-Lan Boureau

Many deep reinforcement learning algorithms contain inductive biases that sculpt the agent's objective and its interface to the environment. These inductive biases can take many forms, including domain knowledge and pretuned…

Machine Learning · Computer Science 2019-07-08 Matteo Hessel , Hado van Hasselt , Joseph Modayil , David Silver

Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the…

Machine Learning · Computer Science 2025-05-29 Zachary Shinnick , Liangze Jiang , Hemanth Saratchandran , Anton van den Hengel , Damien Teney

Transformers have become the foundational architecture for a broad spectrum of sequence modeling applications, underpinning state-of-the-art systems in natural language processing, vision, and beyond. However, their theoretical limitations…

Computation and Language · Computer Science 2026-02-13 Michelle Yuan , Weiyi Sun , Amir H. Rezaeian , Jyotika Singh , Sandip Ghoshal , Yao-Ting Wang , Miguel Ballesteros , Yassine Benajiba

A recent body of work has demonstrated that Transformer embeddings can be linearly decomposed into well-defined sums of factors, that can in turn be related to specific network inputs or components. There is however still a dearth of work…

Computation and Language · Computer Science 2023-10-12 Timothee Mickus , Raúl Vázquez

Transformer-based language models have achieved impressive success in various natural language processing tasks due to their ability to capture complex dependencies and contextual information using self-attention mechanisms. However, they…

Computation and Language · Computer Science 2023-06-26 Kaushik Roy , Yuxin Zi , Vignesh Narayanan , Manas Gaur , Amit Sheth

Interest in larger-context neural machine translation, including document-level and multi-modal translation, has been growing. Multiple works have proposed new network architectures or evaluation schemes, but potentially helpful context is…

Computation and Language · Computer Science 2019-03-13 Sébastien Jean , Kyunghyun Cho

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

Computation and Language · Computer Science 2022-11-29 Nikolaos Mylonas , Ioannis Mollas , Grigorios Tsoumakas

We consider retrofitting structure-aware Transformer-based language model for facilitating end tasks by proposing to exploit syntactic distance to encode both the phrasal constituency and dependency connection into the language model. A…

Computation and Language · Computer Science 2020-09-17 Hao Fei , Yafeng Ren , Donghong Ji

Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging. In this paper, we present the design and implementation of a visual analytic framework for assisting researchers in such…

Computation and Language · Computer Science 2021-09-01 Raymond Li , Wen Xiao , Lanjun Wang , Hyeju Jang , Giuseppe Carenini

Transformer models have become the dominant backbone for sequence modeling, leveraging self-attention to produce contextualized token representations. These are typically aggregated into fixed-size vectors via pooling operations for…

Machine Learning · Computer Science 2025-10-07 Sofiane Ennadir , Levente Zólyomi , Oleg Smirnov , Tianze Wang , John Pertoft , Filip Cornell , Lele Cao