English
Related papers

Related papers: Neural Coreference Resolution for Arabic

200 papers

Seq2seq coreference models have introduced a new paradigm for coreference resolution by learning to generate text corresponding to coreference labels, without requiring task-specific parameters. While these models achieve new…

Computation and Language · Computer Science 2025-10-17 Matt Grenander , Shay B. Cohen , Mark Steedman

Despite significant recent progress in coreference resolution, the quality of current state-of-the-art systems still considerably trails behind human-level performance. Using the CoNLL-2012 and PreCo datasets, we dissect the best…

Computation and Language · Computer Science 2021-09-10 Zhaofeng Wu , Matt Gardner

This paper describes our approach to the CRAC 2022 Shared Task on Multilingual Coreference Resolution. Our model is based on a state-of-the-art end-to-end coreference resolution system. Apart from joined multilingual training, we improved…

Computation and Language · Computer Science 2022-09-27 Ondřej Pražák , Miloslav Konopík

Entity Coreference Resolution is the task of resolving all mentions in a document that refer to the same real world entity and is considered as one of the most difficult tasks in natural language understanding. It is of great importance for…

Computation and Language · Computer Science 2020-12-10 Nikolaos Stylianou , Ioannis Vlahavas

Previous attempts to incorporate a mention detection step into end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention span data as well as other entity information. This paper presents a…

Computation and Language · Computer Science 2023-09-22 Yilun Zhu , Siyao Peng , Sameer Pradhan , Amir Zeldes

Coreference resolution, the task of identifying expressions in text that refer to the same entity, is a critical component in various natural language processing applications. This paper presents a novel end-to-end neural coreference…

Computation and Language · Computer Science 2024-12-30 Ondřej Pražák , Miloslav Konopík , Pavel Král

We present ARETA, an automatic error type annotation system for Modern Standard Arabic. We design ARETA to address Arabic's morphological richness and orthographic ambiguity. We base our error taxonomy on the Arabic Learner Corpus (ALC)…

Computation and Language · Computer Science 2021-09-17 Riadh Belkebir , Nizar Habash

We apply BERT to coreference resolution, achieving strong improvements on the OntoNotes (+3.9 F1) and GAP (+11.5 F1) benchmarks. A qualitative analysis of model predictions indicates that, compared to ELMo and BERT-base, BERT-large is…

Computation and Language · Computer Science 2019-12-24 Mandar Joshi , Omer Levy , Daniel S. Weld , Luke Zettlemoyer

Singleton mentions, i.e.~entities mentioned only once in a text, are important to how humans understand discourse from a theoretical perspective. However previous attempts to incorporate their detection in end-to-end neural coreference…

Computation and Language · Computer Science 2024-03-27 Yilun Zhu , Siyao Peng , Sameer Pradhan , Amir Zeldes

This paper presents the design and development of multi-dialect automatic speech recognition for Arabic. Deep neural networks are becoming an effective tool to solve sequential data problems, particularly, adopting an end-to-end training of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-30 Abbas Raza Ali

One of the major challenges in coreference resolution is how to make use of entity-level features defined over clusters of mentions rather than mention pairs. However, coreferent mentions usually spread far apart in an entire text, which…

Computation and Language · Computer Science 2023-07-25 Lu Liu , Zhenqiao Song , Xiaoqing Zheng , Jun He

The introduction of pretrained language models has reduced many complex task-specific NLP models to simple lightweight layers. An exception to this trend is coreference resolution, where a sophisticated task-specific model is appended to a…

Computation and Language · Computer Science 2021-06-01 Yuval Kirstain , Ori Ram , Omer Levy

Language-specific pre-trained models have proven to be more accurate than multilingual ones in a monolingual evaluation setting, Arabic is no exception. However, we found that previously released Arabic BERT models were significantly…

Recent coreference resolution models rely heavily on span representations to find coreference links between word spans. As the number of spans is $O(n^2)$ in the length of text and the number of potential links is $O(n^4)$, various pruning…

Computation and Language · Computer Science 2022-04-12 Vladimir Dobrovolskii

The recognition of unconstrained handwriting continues to be a difficult task for computers despite active research for several decades. This is because handwritten text offers great challenges such as character and word segmentation,…

Neural and Evolutionary Computing · Computer Science 2013-01-22 Yusuf Perwej

Current work on automatic coreference resolution has focused on the OntoNotes benchmark dataset, due to both its size and consistency. However many aspects of the OntoNotes annotation scheme are not well understood by NLP practitioners,…

Computation and Language · Computer Science 2021-12-21 Amir Zeldes

In recent years, we witnessed great progress in different tasks of natural language understanding using machine learning. Question answering is one of these tasks which is used by search engines and social media platforms for improved user…

Computation and Language · Computer Science 2022-06-06 Mohammed ElKomy , Amany M. Sarhan

Neural machine translation has become a major alternative to widely used phrase-based statistical machine translation. We notice however that much of research on neural machine translation has focused on European languages despite its…

Computation and Language · Computer Science 2016-06-09 Amjad Almahairi , Kyunghyun Cho , Nizar Habash , Aaron Courville

Handwritten character recognition has been the center of research and a benchmark problem in the sector of pattern recognition and artificial intelligence, and it continues to be a challenging research topic. Due to its enormous application…

Computer Vision and Pattern Recognition · Computer Science 2022-09-09 Akm Ashiquzzaman , Abdul Kawsar Tushar , Md Ashiqur Rahman

We present ArabicNumBench, a comprehensive benchmark for evaluating large language models on Arabic number reading tasks across Eastern Arabic-Indic numerals (0-9 in Arabic script) and Western Arabic numerals (0-9). We evaluate 71 models…

Computation and Language · Computer Science 2026-02-24 Anas Alhumud , Abdulaziz Alhammadi , Muhammad Badruddin Khan