English
Related papers

Related papers: Seamlessly Integrating Tree-Based Positional Embed…

200 papers

Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task. Recent advances in latent tree learning have made it possible to recover moderately high quality tree structures by training…

Computation and Language · Computer Science 2019-09-24 Phu Mon Htut , Kyunghyun Cho , Samuel R. Bowman

Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to…

Computation and Language · Computer Science 2022-11-14 Yixuan Zhou , Changhe Song , Jingbei Li , Zhiyong Wu , Yanyao Bian , Dan Su , Helen Meng

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Computation and Language · Computer Science 2025-03-27 James Blades , Frederick Somerfield , William Langley , Susan Everingham , Maurice Witherington

Source code representations are key in applying machine learning techniques for processing and analyzing programs. A popular approach in representing source code is neural source code embeddings that represents programs with…

Machine Learning · Computer Science 2022-06-17 Md Rafiqul Islam Rabin , Arjun Mukherjee , Omprakash Gnawali , Mohammad Amin Alipour

Program representation learning is a fundamental task in software engineering applications. With the availability of "big code" and the development of deep learning techniques, various program representation learning models have been…

Software Engineering · Computer Science 2021-09-17 Siqi Han , DongXia Wang , Wanting Li , Xuesong Lu

Transformer-based models have demonstrated state-of-the-art performance in many intelligent coding tasks such as code comment generation and code completion. Previous studies show that deep learning models are sensitive to the input…

Software Engineering · Computer Science 2025-06-10 Yaoxian Li , Shiyi Qi , Cuiyun Gao , Yun Peng , David Lo , Zenglin Xu , Michael R. Lyu

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…

Computation and Language · Computer Science 2025-03-26 Meiquan Dong , Haoran Liu , Yan Huang , Zixuan Feng , Jianhong Tang , Ruoxi Wang

We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guarantee of not losing…

Machine Learning · Computer Science 2024-05-17 Tsuyoshi Idé , Jokin Labaien , Pin-Yu Chen

We introduce a new construction of embeddings of arbitrary recursive data structures into high dimensional vectors. These embeddings provide an interpretable model for the latent state vectors of transformers. We demonstrate that these…

Machine Learning · Computer Science 2023-11-22 Joshua Maher

While large language models like BERT demonstrate strong empirical performance on semantic tasks, whether this reflects true conceptual competence or surface-level statistical association remains unclear. I investigate whether BERT encodes…

Computation and Language · Computer Science 2025-06-16 Cole Gawin

Bidirectional Encoder Representations from Transformers (BERT) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how…

Computation and Language · Computer Science 2019-09-06 Yang Liu , Mirella Lapata

We propose a new technique for computational language representation called elementwise embedding, in which a material (semantic unit) is abstracted into a horizontal concatenation of lower-dimensional element (character) embeddings. While…

Computation and Language · Computer Science 2023-02-28 Dunam Kim , Jeeeun Kim

Recently, deep neural networks have expanded the state-of-art in various scientific fields and provided solutions to long standing problems across multiple application domains. Nevertheless, they also suffer from weaknesses since their…

Machine Learning · Computer Science 2023-05-03 Felipe Kenji Nakano , Konstantinos Pliakos , Celine Vens

Transformer architectures rely on explicit position encodings in order to preserve a notion of word order. In this paper, we argue that existing work does not fully utilize position information. For example, the initial proposal of a…

Computation and Language · Computer Science 2020-09-30 Zhiheng Huang , Davis Liang , Peng Xu , Bing Xiang

Pre-trained language models have been shown to encode linguistic structures, e.g. dependency and constituency parse trees, in their embeddings while being trained on unsupervised loss functions like masked language modeling. Some doubts…

Computation and Language · Computer Science 2023-10-17 Haoyu Zhao , Abhishek Panigrahi , Rong Ge , Sanjeev Arora

Language model approaches have recently been integrated into binary analysis tasks, such as function similarity detection and function signature recovery. These models typically employ a two-stage training process: pre-training via Masked…

Software Engineering · Computer Science 2024-12-24 Hanxiao Lu , Hongyu Cai , Yiming Liang , Antonio Bianchi , Z. Berkay Celik

Using the pre-trained language models to understand source codes has attracted increasing attention from financial institutions owing to the great potential to uncover financial risks. However, there are several challenges in applying these…

Artificial Intelligence · Computer Science 2022-10-12 Rong Liang , Tiehua Zhang , Yujie Lu , Yuze Liu , Zhen Huang , Xin Chen

Recent advancements in transformer-based models have greatly improved time series analysis, providing robust solutions for tasks such as forecasting, anomaly detection, and classification. A crucial element of these models is positional…

Machine Learning · Computer Science 2026-05-07 Habib Irani , Vangelis Metsis

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation…

Computation and Language · Computer Science 2021-09-13 Haoran Xu , Benjamin Van Durme , Kenton Murray

Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…

Computation and Language · Computer Science 2020-11-10 Çağla Aksoy , Alper Ahmetoğlu , Tunga Güngör