English
Related papers

Related papers: MEXMA: Token-level objectives improve sentence rep…

200 papers

Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the…

Computation and Language · Computer Science 2021-04-15 Alexandra Chronopoulou , Dario Stojanovski , Alexander Fraser

Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for…

Computation and Language · Computer Science 2025-09-08 Shunyu Zhang , Yaobo Liang , Ming Gong , Daxin Jiang , Nan Duan

We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text. In contrast to the standard practice with sentence embeddings, where the meaning of an entire sequence…

Computation and Language · Computer Science 2023-11-09 Sihao Chen , Hongming Zhang , Tong Chen , Ben Zhou , Wenhao Yu , Dian Yu , Baolin Peng , Hongwei Wang , Dan Roth , Dong Yu

Existing large language models (LLMs) for machine translation are typically fine-tuned on sentence-level translation instructions and achieve satisfactory performance at the sentence level. However, when applied to document-level…

Computation and Language · Computer Science 2024-01-17 Yachao Li , Junhui Li , Jing Jiang , Min Zhang

Human vision is able to compensate imperfections in sensory inputs from the real world by reasoning based on prior knowledge about the world. Machine learning has had a significant impact on computer vision due to its inherent ability in…

Artificial Intelligence · Computer Science 2020-12-18 Briti Gangopadhyay , Somnath Hazra , Pallab Dasgupta

The next-token prediction (NTP) objective has been foundational in the development of modern large language models (LLMs), driving advances in fluency and generalization. However, NTP operates at the \textit{token} level, treating…

Computation and Language · Computer Science 2026-01-23 Laya Iyer , Pranav Somani , Alice Guo , Dan Jurafsky , Chen Shani

Automatically generating human-readable text describing the functionality of a program is the intent of source code summarization. Although neural language models achieve significant performance in this field, they are limited by their…

Artificial Intelligence · Computer Science 2024-04-02 Tong Ye , Lingfei Wu , Tengfei Ma , Xuhong Zhang , Yangkai Du , Peiyu Liu , Shouling Ji , Wenhai Wang

In this paper, we elaborate upon recipes for building multilingual representation models that are not only competitive with existing state-of-the-art models but are also more parameter efficient, thereby promoting better adoption in…

Computation and Language · Computer Science 2022-10-27 Barun Patra , Saksham Singhal , Shaohan Huang , Zewen Chi , Li Dong , Furu Wei , Vishrav Chaudhary , Xia Song

We present an effective method for fusing visual-and-language representations for several question answering tasks including visual question answering and visual entailment. In contrast to prior works that concatenate unimodal…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Maxwell Mbabilla Aladago , AJ Piergiovanni

While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated…

Computation and Language · Computer Science 2025-05-20 Xianglong Xu , John Bowen , Rojin Taheri

Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason is the cross-image information leakage, where the model…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Minyoung Lee , Yeji Park , Dongjun Hwang , Yejin Kim , Seong Joon Oh , Junsuk Choe

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…

Computation and Language · Computer Science 2021-09-22 Luyu Gao , Jamie Callan

Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…

Computation and Language · Computer Science 2025-10-14 Hyeonbin Hwang , Byeongguk Jeon , Seungone Kim , Jiyeon Kim , Hoyeon Chang , Sohee Yang , Seungpil Won , Dohaeng Lee , Youbin Ahn , Minjoon Seo

Sentence representation models trained only on language could potentially suffer from the grounding problem. Recent work has shown promising results in improving the qualities of sentence representations by jointly training them with…

Computation and Language · Computer Science 2017-12-05 Kang Min Yoo , Youhyun Shin , Sang-goo Lee

We introduce two pre-trained retrieval focused multilingual sentence encoding models, respectively based on the Transformer and CNN model architectures. The models embed text from 16 languages into a single semantic space using a multi-task…

Despite the effectiveness of recurrent neural network language models, their maximum likelihood estimation suffers from two limitations. It treats all sentences that do not match the ground truth as equally poor, ignoring the structure of…

Computation and Language · Computer Science 2018-05-15 Maha Elbayad , Laurent Besacier , Jakob Verbeek

Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be…

Computation and Language · Computer Science 2020-08-21 Nishant Subramani , Nivedita Suresh

Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…

Computation and Language · Computer Science 2026-01-14 Adrian Cosma , Stefan Ruseti , Emilian Radoi , Mihai Dascalu

In multilingual colloquial settings, it is a habitual occurrence to compose expressions of text or speech containing tokens or phrases of different languages, a phenomenon popularly known as code-switching or code-mixing (CMX). We present…

Computation and Language · Computer Science 2022-11-01 Lekan Raheem , Maab Elrashid

To better support retrieval applications such as web search and question answering, growing effort is made to develop retrieval-oriented language models. Most of the existing works focus on improving the semantic representation capability…

Computation and Language · Computer Science 2022-11-17 Shitao Xiao , Zheng Liu