English
Related papers

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

200 papers

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-12 Xuan Shi , Chang Zeng , Tiantian Feng , Shih-Heng Wang , Jianbo Ma , Shrikanth Narayanan

Universal language representation is the holy grail in machine translation (MT). Thanks to the new neural MT approach, it seems that there are good perspectives towards this goal. In this paper, we propose a new architecture based on…

Computation and Language · Computer Science 2018-10-16 Carlos Escolano , Marta R. Costa-jussà , José A. R. Fonollosa

Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perplexity. We propose Continuous Concept Mixing (CoCoMix), a…

Machine Learning · Computer Science 2025-02-13 Jihoon Tack , Jack Lanchantin , Jane Yu , Andrew Cohen , Ilia Kulikov , Janice Lan , Shibo Hao , Yuandong Tian , Jason Weston , Xian Li

Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-24 Anup Singh , Kris Demuynck , Vipul Arora

The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanilla MLM, the virtual tokens, [MASK]s, act as placeholders and…

Computation and Language · Computer Science 2022-11-16 Baohao Liao , David Thulke , Sanjika Hewavitharana , Hermann Ney , Christof Monz

A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the…

Computation and Language · Computer Science 2019-08-02 Muthuraman Chidambaram , Yinfei Yang , Daniel Cer , Steve Yuan , Yun-Hsuan Sung , Brian Strope , Ray Kurzweil

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

Computation and Language · Computer Science 2021-06-11 Christos Baziotis , Ivan Titov , Alexandra Birch , Barry Haddow

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

Computation and Language · Computer Science 2019-11-12 Zhuosheng Zhang , Rui Wang , Kehai Chen , Masao Utiyama , Eiichiro Sumita , Hai Zhao

Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is potentially a problem if…

Computation and Language · Computer Science 2018-12-27 Xinwei Geng , Longyue Wang , Xing Wang , Bing Qin , Ting Liu , Zhaopeng Tu

We present a multi-task learning framework for cross-lingual abstractive summarization to augment training data. Recent studies constructed pseudo cross-lingual abstractive summarization data to train their neural encoder-decoders.…

Computation and Language · Computer Science 2020-10-16 Sho Takase , Naoaki Okazaki

Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from depth estimation, and reasoning about 2D object…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Mahtab Bigverdi , Zelun Luo , Cheng-Yu Hsieh , Ethan Shen , Dongping Chen , Linda G. Shapiro , Ranjay Krishna

In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training. Specifically, we present two pre-training tasks, namely multilingual replaced token detection, and translation replaced token detection. Besides,…

Computation and Language · Computer Science 2022-04-20 Zewen Chi , Shaohan Huang , Li Dong , Shuming Ma , Bo Zheng , Saksham Singhal , Payal Bajaj , Xia Song , Xian-Ling Mao , Heyan Huang , Furu Wei

Multilingual pre-trained models could leverage the training data from a rich source language (such as English) to improve performance on low resource languages. However, the transfer quality for multilingual Machine Reading Comprehension…

Computation and Language · Computer Science 2020-05-11 Fei Yuan , Linjun Shou , Xuanyu Bai , Ming Gong , Yaobo Liang , Nan Duan , Yan Fu , Daxin Jiang

Prior work on pretrained sentence embeddings and benchmarks focus on the capabilities of stand-alone sentences. We propose DiscoEval, a test suite of tasks to evaluate whether sentence representations include broader context information. We…

Computation and Language · Computer Science 2019-11-11 Mingda Chen , Zewei Chu , Kevin Gimpel

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Sibo Song , Jianqiang Wan , Zhibo Yang , Jun Tang , Wenqing Cheng , Xiang Bai , Cong Yao

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a…

Computation and Language · Computer Science 2017-07-28 Zhe Gan , Yunchen Pu , Ricardo Henao , Chunyuan Li , Xiaodong He , Lawrence Carin

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

Computation and Language · Computer Science 2025-06-10 Jaturong Kongmanee

Extracting sentence embeddings from large language models (LLMs) is a promising direction, as LLMs have demonstrated stronger semantic understanding capabilities. Previous studies typically focus on prompt engineering to elicit sentence…

Computation and Language · Computer Science 2025-07-04 Yuchen Fu , Zifeng Cheng , Zhiwei Jiang , Zhonghui Wang , Yafeng Yin , Zhengliang Li , Qing Gu

What makes a universal sentence encoder universal? The notion of a generic encoder of text appears to be at odds with the inherent contextualization and non-permanence of language use in a dynamic world. However, mapping sentences into…

Computation and Language · Computer Science 2020-02-21 Jamie Kiros

We introduce semantic form mid-tuning, an approach for transferring semantic knowledge from semantic meaning representations into transformer-based language encoders. In mid-tuning, we learn to align the text of general sentences -- not…

Computation and Language · Computer Science 2021-10-15 Mohammad Umair , Francis Ferraro