English
Related papers

Related papers: CABACE: Injecting Character Sequence Information a…

200 papers

Acronym Disambiguation (AD) is crucial for natural language understanding on various sources, including biomedical reports, scientific papers, and search engine queries. However, existing acronym disambiguation benchmarks and tools are…

Computation and Language · Computer Science 2023-03-15 Lihu Chen , Gaël Varoquaux , Fabian M. Suchanek

Named Entity Recognition (NER) is a machine learning task that traditionally relies on supervised learning and annotated data. Acquiring such data is often a challenge, particularly in specialized fields like medical, legal, and financial…

Computation and Language · Computer Science 2026-04-01 Arthur Elwing Torres , Edleno Silva de Moura , Altigran Soares da Silva , Mario A. Nascimento , Filipe Mesquita

Entity synonyms discovery is crucial for entity-leveraging applications. However, existing studies suffer from several critical issues: (1) the input mentions may be out-of-vocabulary (OOV) and may come from a different semantic space of…

Artificial Intelligence · Computer Science 2021-04-02 Yiying Yang , Xi Yin , Haiqin Yang , Xingjian Fei , Hao Peng , Kaijie Zhou , Kunfeng Lai , Jianping Shen

Pre-training large-scale neural language models on raw texts has made a significant contribution to improving transfer learning in natural language processing (NLP). With the introduction of transformer-based language models, such as…

Computation and Language · Computer Science 2024-05-08 Shoya Wada , Toshihiro Takeda , Shiro Manabe , Shozo Konishi , Jun Kamohara , Yasushi Matsumura

Retrieving answer passages from long documents is a complex task requiring semantic understanding of both discourse and document context. We approach this challenge specifically in a clinical scenario, where doctors retrieve cohorts of…

Information Retrieval · Computer Science 2021-08-03 Paul Grundmann , Sebastian Arnold , Alexander Löser

Document-level relation extraction (DocRE) involves identifying relations between entities distributed in multiple sentences within a document. Existing methods focus on building a heterogeneous document graph to model the internal…

Computation and Language · Computer Science 2023-10-31 Chonggang Lu , Richong Zhang , Kai Sun , Jaein Kim , Cunwang Zhang , Yongyi Mao

This paper presents a publicly available corpus of French encyclopedic history texts annotated according to the Berkeley FrameNet formalism. The main difference in our approach compared to previous works on semantic parsing with FrameNet is…

Computation and Language · Computer Science 2018-12-20 Gabriel Marzinotto , Jeremy Auguste , Frederic Bechet , Géraldine Damnati , Alexis Nasr

Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable…

Computation and Language · Computer Science 2017-11-27 Liyuan Liu , Jingbo Shang , Frank F. Xu , Xiang Ren , Huan Gui , Jian Peng , Jiawei Han

Recent studies on open-domain question answering have achieved prominent performance improvement using pre-trained language models such as BERT. State-of-the-art approaches typically follow the "retrieve and read" pipeline and employ…

Computation and Language · Computer Science 2020-03-02 Yuyu Zhang , Ping Nie , Xiubo Geng , Arun Ramamurthy , Le Song , Daxin Jiang

Recognition of biomedical entities from literature is a challenging research focus, which is the foundation for extracting a large amount of biomedical knowledge existing in unstructured texts into structured formats. Using the sequence…

Computation and Language · Computer Science 2021-05-18 Cong Sun , Zhihao Yang , Lei Wang , Yin Zhang , Hongfei Lin , Jian Wang

Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been…

Computation and Language · Computer Science 2019-06-24 Emily Alsentzer , John R. Murphy , Willie Boag , Wei-Hung Weng , Di Jin , Tristan Naumann , Matthew B. A. McDermott

In this article, we present the BTransformer18 model, a deep learning architecture designed for multi-label relation extraction in French texts. Our approach combines the contextual representation capabilities of pre-trained language models…

Computation and Language · Computer Science 2025-02-24 Ngoc Luyen Le , Gildas Tagny Ngompé

Large Language Models (LLMs) offer transformative solutions across many domains, but healthcare integration is hindered by strict data privacy constraints. Clinical narratives are dense with ambiguous acronyms, misinterpretation these…

Computation and Language · Computer Science 2026-03-26 Manjushree B. Aithal , Ph. D. , Alexander Kotz , James Mitchell , Ph. D

Most existing named entity recognition (NER) approaches are based on sequence labeling models, which focus on capturing the local context dependencies. However, the way of taking one sentence as input prevents the modeling of non-sequential…

Computation and Language · Computer Science 2021-06-03 Zanbo Wang , Wei Wei , Xianling Mao , Shanshan Feng , Pan Zhou , Zhiyong He , Sheng Jiang

Recently, Natural Language Processing (NLP) has witnessed an impressive progress in many areas, due to the advent of novel, pretrained contextual representation models. In particular, Devlin et al. (2019) proposed a model, called BERT…

Computation and Language · Computer Science 2020-03-09 Debora Nozza , Federico Bianchi , Dirk Hovy

Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP. However, while there is no dearth of pretrained embeddings, the distinct lack of systematic…

Computation and Language · Computer Science 2019-06-05 Benjamin Heinzerling , Michael Strube

This paper proposes OCR++, an open-source framework designed for a variety of information extraction tasks from scholarly articles including metadata (title, author names, affiliation and e-mail), structure (section headings and body text,…

Span extraction, aiming to extract text spans (such as words or phrases) from plain texts, is a fundamental process in Information Extraction. Recent works introduce the label knowledge to enhance the text representation by formalizing the…

Computation and Language · Computer Science 2021-11-02 Pan Yang , Xin Cong , Zhenyun Sun , Xingwu Liu

We hypothesize that large language models (LLMs) based on the transformer architecture can enable automated detection of clinical phenotype terms, including terms not documented in the HPO. In this study, we developed two types of models:…

Quantitative Methods · Quantitative Biology 2023-11-10 Jingye Yang , Cong Liu , Wendy Deng , Da Wu , Chunhua Weng , Yunyun Zhou , Kai Wang

Many Proper Names (PNs) are Out-Of-Vocabulary (OOV) words for speech recognition systems used to process diachronic audio data. To help recovery of the PNs missed by the system, relevant OOV PNs can be retrieved out of the many OOVs by…

Computation and Language · Computer Science 2016-03-02 Imran Sheikh , Irina Illina , Dominique Fohr , Georges Linarès