English
Related papers

Related papers: AICC: Parse HTML Finer, Make Models Better -- A 7.…

200 papers

We deal with the problem of localized in-video taxonomic human annotation in the video content moderation domain, where the goal is to identify video segments that violate granular policies, e.g., community guidelines on an online video…

Machine Learning · Computer Science 2022-10-19 Meghana Deodhar , Xiao Ma , Yixin Cai , Alex Koes , Alex Beutel , Jilin Chen

Language models (LMs) exhibit impressive performance and generalization capabilities. However, LMs struggle with the persistent challenge of catastrophic forgetting, which undermines their long-term sustainability in continual learning…

Machine Learning · Computer Science 2024-10-08 Wenyu Du , Shuang Cheng , Tongxu Luo , Zihan Qiu , Zeyu Huang , Ka Chun Cheung , Reynold Cheng , Jie Fu

Extracting main content from web pages provides primary informative blocks that remove a web page's minor areas like navigation menu, ads, and site templates. The main content extraction has various applications: information retrieval,…

Information Retrieval · Computer Science 2022-01-26 Geunseong Jung , Sungjae Han , Hansung Kim , Kwanguk Kim , Jaehyuk Cha

We train several language models for Icelandic, including IceBERT, that achieve state-of-the-art performance in a variety of downstream tasks, including part-of-speech tagging, named entity recognition, grammatical error detection and…

Large Language Models (LLMs) demonstrate remarkable capabilities in replicating human tasks and boosting productivity. However, their direct application for data extraction presents limitations due to a prioritisation of fluency over…

Computation and Language · Computer Science 2024-06-13 Aman Ahluwalia , Suhrud Wani

Large-scale content analysis is increasingly limited by the absence of observable ground truth or gold-standard labels, as creating such benchmarks through extensive human coding becomes impractical for massive datasets due to high time,…

Computation and Language · Computer Science 2026-03-09 Luis de-Marcos , Manuel Goyanes , Adrián Domínguez-Díaz

Evaluating AI-generated medical image segmentations for clinical acceptability poses a significant challenge, as traditional pixelagreement metrics often fail to capture true diagnostic utility. This paper introduces Hierarchical Clinical…

Image and Video Processing · Electrical Eng. & Systems 2025-06-03 Jiaxi Sheng , Leyi Yu , Haoyue Li , Yifan Gao , Xin Gao

We present a novel iterative extraction model, IterX, for extracting complex relations, or templates (i.e., N-tuples representing a mapping from named slots to spans of text) within a document. Documents may feature zero or more instances…

Computation and Language · Computer Science 2023-05-02 Yunmo Chen , William Gantt , Weiwei Gu , Tongfei Chen , Aaron Steven White , Benjamin Van Durme

A major archetype of artificial intelligence is developing algorithms facilitating temporal efficiency and accuracy while boosting the generalization performance. Even with the latest developments in machine learning, a key limitation has…

Machine Learning · Computer Science 2022-01-31 Meric Yucel , Serdar Bagis , Ahmet Sertbas , Mehmet Sarikaya , Burak Berk Ustundag

Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains unexplored.…

Computation and Language · Computer Science 2025-01-03 Chongjian Yue , Xinrun Xu , Xiaojun Ma , Lun Du , Zhiming Ding , Shi Han , Dongmei Zhang , Qi Zhang

The performance of Large Language Models (LLMs) is substantially influenced by the pretraining corpus, which consists of vast quantities of unsupervised data processed by the models. Despite its critical role in model performance, ensuring…

Computation and Language · Computer Science 2024-10-11 Ranchi Zhao , Zhen Leng Thai , Yifan Zhang , Shengding Hu , Yunqi Ba , Jie Zhou , Jie Cai , Zhiyuan Liu , Maosong Sun

Typically, information extraction (IE) requires a pipeline approach: first, a sequence labeling model is trained on manually annotated documents to extract relevant spans; then, when a new document arrives, a model predicts spans which are…

Computation and Language · Computer Science 2021-10-12 Benjamin Townsend , Eamon Ito-Fisher , Lily Zhang , Madison May

Industrial projects rely heavily on lengthy, complex specification documents, making tedious manual extraction of structured information a major bottleneck. This paper introduces an innovative approach to automate this process, leveraging…

Information Retrieval · Computer Science 2024-03-13 Degaga Wolde Feyisa , Haylemicheal Berihun , Amanuel Zewdu , Mahsa Najimoghadam , Marzieh Zare

Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence…

Computation and Language · Computer Science 2025-07-16 Anders Ledberg , Anna Thalén

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by…

Computation and Language · Computer Science 2025-11-20 Xueying Ding , Xingyue Huang , Mingxuan Ju , Liam Collins , Yozen Liu , Leman Akoglu , Neil Shah , Tong Zhao

Advances in large language models have notably enhanced the efficiency of information extraction from unstructured and semi-structured data sources. As these technologies become integral to various applications, establishing an objective…

The vast majority of non-English corpora are derived from automatically filtered versions of CommonCrawl. While prior work has identified major issues on the quality of these datasets (Kreutzer et al., 2021), it is not clear how this…

Computation and Language · Computer Science 2022-10-27 Mikel Artetxe , Itziar Aldabe , Rodrigo Agerri , Olatz Perez-de-Viñaspre , Aitor Soroa

Recent advances in deep learning, especially deep convolutional neural networks (CNNs), have led to significant improvement over previous semantic segmentation systems. Here we show how to improve pixel-wise semantic segmentation by…

Computer Vision and Pattern Recognition · Computer Science 2018-06-04 Panqu Wang , Pengfei Chen , Ye Yuan , Ding Liu , Zehua Huang , Xiaodi Hou , Garrison Cottrell

Machine translation is highly sensitive to the size and quality of the training data, which has led to an increasing interest in collecting and filtering large parallel corpora. In this paper, we propose a new method for this task based on…

Computation and Language · Computer Science 2021-12-28 Mikel Artetxe , Holger Schwenk

Pre-training data shapes a language model's quality, but raw web text is noisy and demands careful cleaning. Existing large-scale corpora rely on English-centric or language-agnostic pipelines whose heuristics do not capture Thai script or…

‹ Prev 1 4 5 6 7 8 10 Next ›