English
Related papers

Related papers: CONE: Embeddings for Complex Numerical Data Preser…

200 papers

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Accurate representation of building semantics, encompassing both generic object types and specific subtypes, is essential for effective AI model training in the architecture, engineering, construction, and operation (AECO) industry.…

Artificial Intelligence · Computer Science 2026-02-18 Suhyung Jang , Ghang Lee , Jaekun Lee , Hyunjun Lee

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Mouxiao Huang , Borui Jiang , Dehua Zheng , Hailin Hu , Kai Han , Xinghao Chen

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

Computation and Language · Computer Science 2025-09-09 Manuel Frank , Haithem Afli

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

We introduce SONAR, a new multilingual and multimodal fixed-size sentence embedding space. Our single text encoder, covering 200 languages, substantially outperforms existing sentence embeddings such as LASER3 and LabSE on the xsim and…

Computation and Language · Computer Science 2023-08-24 Paul-Ambroise Duquenne , Holger Schwenk , Benoît Sagot

Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…

Computation and Language · Computer Science 2024-07-25 Yun Zhu , Yaoke Wang , Haizhou Shi , Siliang Tang

The state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We explore a setting where many different predictions are made on a single piece of text.…

Computation and Language · Computer Science 2020-04-30 Jingfei Du , Myle Ott , Haoran Li , Xing Zhou , Veselin Stoyanov

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Computation and Language · Computer Science 2023-05-26 Francesco Fusco , Diego Antognini

Cross-Lingual Word Embeddings (CLWEs) encode words from two or more languages in a shared high-dimensional space in which vectors representing words with similar meaning (regardless of language) are closely located. Existing methods for…

Computation and Language · Computer Science 2022-01-25 Xutan Peng , Chenghua Lin , Mark Stevenson

Pretrained language models (LMs) are prone to arithmetic errors. Existing work showed limited success in probing numeric values from models' representations, indicating that these errors can be attributed to the inherent unreliability of…

Computation and Language · Computer Science 2025-10-27 Marek Kadlčík , Michal Štefánik , Timothee Mickus , Michal Spiegel , Josef Kuchař

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman

Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.…

Computation and Language · Computer Science 2020-10-13 Brian Lester , Daniel Pressel , Amy Hemmeter , Sagnik Ray Choudhury , Srinivas Bangalore

Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks. While dense embeddings have dominated related research, we introduce the first lexicon-based embeddings (LENS) leveraging…

Computation and Language · Computer Science 2026-03-20 Yibin Lei , Tao Shen , Yu Cao , Andrew Yates

Transformer models learn to encode and decode an input text, and produce contextual token embeddings as a side-effect. The mapping from language into the embedding space maps words expressing similar concepts onto points that are close in…

Computation and Language · Computer Science 2025-09-03 Vivi Nastase , Paola Merlo

Retrieval-augmented language models such as Fusion-in-Decoder are powerful, setting the state of the art on a variety of knowledge-intensive tasks. However, they are also expensive, due to the need to encode a large number of retrieved…

Computation and Language · Computer Science 2023-06-06 Michiel de Jong , Yury Zemlyanskiy , Nicholas FitzGerald , Joshua Ainslie , Sumit Sanghai , Fei Sha , William Cohen

Detecting communities has long been popular in the research on networks. It is usually modeled as an unsupervised clustering problem on graphs, based on heuristic assumptions about community characteristics, such as edge density and node…

Social and Information Networks · Computer Science 2018-04-24 Carl Yang , Hanqing Lu , Kevin Chen-Chuan Chang

Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be…

Computation and Language · Computer Science 2023-11-07 James Y. Huang , Wenlin Yao , Kaiqiang Song , Hongming Zhang , Muhao Chen , Dong Yu

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

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

Computation and Language · Computer Science 2021-08-13 Zi-Yi Dou , Graham Neubig