Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Dependency parsing with bottom-up Hierarchical Pointer Networks

  • Fernández González, Daniel
  • Gómez Rodríguez, Carlos
Dependency parsing is a crucial step towards deep language understanding and, therefore, widely demanded by numerous Natural Language Processing applications. In particular, left-to-right and top-down transition-based algorithms that rely on Pointer Networks are among the most accurate approaches for performing dependency parsing. Additionally, it has been observed for the top-down algorithm that Pointer Networks’ sequential decoding can be improved by implementing a hierarchical variant, more adequate to model dependency structures. Considering all this, we develop a bottom-up oriented Hierarchical Pointer Network for the left-to-right parser and propose two novel transition-based alternatives: an approach that parses a sentence in right-to-left order and a variant that does so from the outside in. We empirically test the proposed neural architecture with the different algorithms on a wide variety of languages, outperforming the original approach in practically all of them and setting new state-of-the-art results on the English and Chinese Penn Treebanks for non-contextualized and BERT-based embeddings., Agencia Estatal de Investigación | Ref. PID2020-113230RB-C21, Xunta de Galicia | Ref. ED431C 2020/11, Xunta de Galicia | Ref. ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publication Artículo científico (JournalArticle)

Dependency parsing with bottom-up Hierarchical Pointer Networks

  • Fernández-González, Daniel
  • Gómez-Rodríguez, Carlos
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract] Dependency parsing is a crucial step towards deep language understanding and, therefore, widely demanded by numerous Natural Language Processing applications. In particular, left-to-right and top-down transition-based algorithms that rely on Pointer Networks are among the most accurate approaches for performing dependency parsing. Additionally, it has been observed for the top-down algorithm that Pointer Networks’ sequential decoding can be improved by implementing a hierarchical variant, more adequate to model dependency structures. Considering all this, we develop a bottom-up oriented Hierarchical Pointer Network for the left-to-right parser and propose two novel transition-based alternatives: an approach that parses a sentence in right-to-left order and a variant that does so from the outside in. We empirically test the proposed neural architecture with the different algorithms on a wide variety of languages, outperforming the original approach in practically all of them and setting new state-of-the-art results on the English and Chinese Penn Treebanks for non-contextualized and BERT-based embeddings., Ministerio de Ciencia e Innovación;PID2020-113230RB-C21, Xunta de Galicia;ED431C2020/11, European Regional Developmet Fund;ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publication Artículo científico (JournalArticle)

Contrasting Linguistic Patterns in Human and LLM-Generated News Text

  • Muñoz-Ortiz, Alberto
  • Gómez-Rodríguez, Carlos
  • Vilares, David
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, The data analyzed on this article has been obtained using the New York Times Archive API (https://developer.nytimes.com/docs/archive-product/1/overview), gathering all the available articles from the 1st of October, 2023 to the 24th of January, 2024. We released the code and the used data on: https://zenodo.org/records/11186264., [Abstract]: We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from six different LLMs that cover three different families and four sizes in total. Our analysis spans several measurable linguistic dimensions, including morphological, syntactic, psychometric, and sociolinguistic aspects. The results reveal various measurable differences between human and AI-generated texts. Human texts exhibit more scattered sentence length distributions, more variety of vocabulary, a distinct use of dependency and constituent types, shorter constituents, and more optimized dependency distances. Humans tend to exhibit stronger negative emotions (such as fear and disgust) and less joy compared to text generated by LLMs, with the toxicity of these models increasing as their size grows. LLM outputs use more numbers, symbols and auxiliaries (suggesting objective language) than human texts, as well as more pronouns. The sexist bias prevalent in human text is also expressed by LLMs, and even magnified in all of them but one. Differences between LLMs and humans are larger than between LLMs., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. We acknowledge the European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615); SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033; Xunta de Galicia (ED431C 2020/11); GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and by ERDF, EU; Grant PRE2021-097001 funded by MICIU/AEI/10.13039/501100011033 and by ESF+ (predoctoral training grant associated to project PID2020–113230RB-C21); and Centro de Investigación de Galicia “CITIC”, funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS). Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2020/11
RUC. Repositorio da Universidade da Coruña
Publication Artículo científico (JournalArticle)

Unveiling factors influencing judgment variation in sentiment analysis with natural language processing and statistics

  • Kellert, Olga
  • Gómez-Rodríguez, Carlos
  • Zaman, Mahmud Uz
[Abstract]: TripAdvisor reviews and comparable data sources play an important role in many tasks in Natural Language Processing (NLP), providing a data basis for the identification and classification of subjective judgments, such as hotel or restaurant reviews, into positive or negative polarities. This study explores three important factors influencing variation in crowdsourced polarity judgments, focusing on TripAdvisor reviews in Spanish. Three hypotheses are tested: the role of Part Of Speech (POS), the impact of sentiment words such as “tasty”, and the influence of neutral words like “ok” on judgment variation. The study’s methodology employs one-word titles, demonstrating their efficacy in studying polarity variation of words. Statistical tests on mean equality are performed on word groups of our interest. The results of this study reveal that adjectives in one-word titles tend to result in lower judgment variation compared to other word types or POS. Sentiment words contribute to lower judgment variation as well, emphasizing the significance of sentiment words in research on polarity judgments, and neutral words are associated with higher judgment variation as expected. However, these effects cannot be always reproduced in longer titles, which suggests that longer titles do not represent the best data source for testing the ambiguity of single words due to the influence on word polarity by other words like negation in longer titles. This empirical investigation contributes valuable insights into the factors influencing polarity variation of words, providing a foundation for NLP practitioners that aim to capture and predict polarity judgments in Spanish and for researchers that aim to understand factors influencing judgment variation., European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615), MICIU/AEI/10.13039/501100011033 (SCANNER-UDC, PID2020-113230RB-C21), Xunta de Galicia (ED431C 2020/11), and Centro de Investigación de Galicia “CITIC”, funded by Xunta de Galicia and the European Union (ERDF - Galicia 2014–2020 Program), by grant ED431G 2019/01., Xunta de Galicia; ED431C 2020/11, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publication Artículo científico (JournalArticle)

SynNER: Syntax-infused Named Entity Recognition in the Biomedical Domain

  • Imran, Muhammad
  • Zamaraeva, Olga
  • Gómez-Rodríguez, Carlos
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG The code and other resources developed for this work are available in our GitHub repository at: https://github.com/chimran135/SynNER. The datasets used in this study are publicly available from third-party sources. The MTSamples and VAERS datasets can be downloaded from: https://github.com/BIDS-Xu-Lab/Clinical_Entity_Recognition_Using_GPT_models. The NCBI-Disease, BC2GM, and JNLPBA datasets can be downloaded from: https://github.com/cambridgeltl/MTL-Bioinformatics-2016. Supplementary material is available at JAMIA Open online, [Abstract]: Named Entity Recognition (NER) is a technology that helps computers automatically find and classify important terms in text, such as names of diseases, drugs, or medical procedures. This is especially valuable in the biomedical field, where researchers and clinicians need to process large volumes of text from scientific articles, clinical notes, or patient records. In this work, we present SynNER, a system that improves the accuracy of NER by teaching computers to pay attention not only to the words themselves, but also to syntax, ie, the internal structure of sentences. For example, recognizing how words are connected in a sentence (which parts of the sentence are subjects, objects or modifiers) can make it easier to correctly identify medical terms, even when they appear in complex contexts. We tested our method on five different collections of biomedical texts. The results showed that incorporating grammatical knowledge significantly boosted accuracy. Our SynNER system outperformed previous state-of-the-art methods on three of the five datasets. Our results show that using syntax can help researchers and healthcare professionals more reliably and quickly extract vital information from a vast amount of text, which could ultimately help improve biomedical research and clinical decision support tools., We acknowledge the European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615), SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033, LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF (EU), Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR under grant TSI-100925-2023-1, Xunta de Galicia (ED431C 2024/02), and Galician Research Center “CITIC”, funded by Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS). Furthermore, this research was supported by the International, Interdisciplinary and Intersectoral Information and Communications Technology PhD programme (3-i ICT) granted to CITIC and supported by the European Union through the Horizon 2020 research and innovation programme under a Marie Skłodowska-Curie agreement (H2020-MSCA-COFUND), GA 101034261. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2024/02
RUC. Repositorio da Universidade da Coruña
Publication Artículo científico (JournalArticle)

A Syntax-Injected Approach for Faster and More Accurate Sentiment Analysis

  • Imran, Muhammad
  • Kellert, Olga
  • Gómez-Rodríguez, Carlos
The following information was supplied regarding data availability: The OpeNERen, OpeNERes, UD_English-EWT and UD_Spanish-AnCora datasets are available at Zenodo: Muhammad Imran. (2025). chimran135/syntax-injected-sentimentanalysis: Syntax-injected Sentiment Analysis (1.0.0). Zenodo. https://doi.org/10.5281/zenodo.15323755. The Rest-Mex 2023 shared task website provides access to the training data for registered participants. The data are held privately for assessment purposes and can be obtained from Rest-Mex 2023 organizers https://sites.google.com/cimat.mx/rest-mex2023 by contacting Miguel Ángel Álvarez Carmona at miguel.alvarez@cimat.mx. The Rest-Mex 2023 dataset was used under license for this study., [Abstract]: Sentiment Analysis (SA) is a crucial aspect of Natural Language Processing (NLP), focusing on identifying and interpreting subjective assessments in textual content. Syntactic parsing is useful in SA as it improves accuracy and provides explainability; however, it often becomes a computational bottleneck due to slow parsing algorithms. This article proposes a solution to this bottleneck by using a Sequence Labeling Syntactic Parser (SELSP) to integrate syntactic information into SA via a rule-based sentiment analysis pipeline. By reformulating dependency parsing as a sequence labeling task, we significantly improve the efficiency of syntax-based SA. SELSP is trained and evaluated on a ternary polarity classification task, demonstrating greater speed and accuracy compared to conventional parsers like Stanza and heuristic approaches such as Valence Aware Dictionary and sEntiment Reasoner (VADER). The combination of speed and accuracy makes SELSP especially attractive for sentiment analysis applications in both academic and industrial contexts. Moreover, we compare SELSP with Transformer-based models trained on a 5-label classification task. In addition, we evaluate multiple sentiment dictionaries with SELSP to determine which yields the best performance in polarity prediction. The results show that dictionaries accounting for polarity judgment variation outperform those that ignore it. Furthermore, we show that SELSP outperforms Transformer-based models in terms of speed for polarity prediction., The European Research Council (ERC) funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No. 101100615), SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033, LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF (EU), project GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF (EU), Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR under grant TSI-100925-2023-1, Xunta de Galicia (ED431C 2024/02), and Galician Research Center “CITIC”, funded by Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS). Furthermore, this research was supported by the International, Interdisciplinary and Intersectoral Information and Communications Technology PhD programme (3-i ICT) granted to CITIC and supported by the European Union through the Horizon 2020 research and innovation programme under a Marie Skłodowska-Curie agreement (H2020-MSCA-COFUND), GA 101034261. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript., Xunta de Galicia; ED431C 2024/02
RUC. Repositorio da Universidade da Coruña
Publication Artículo científico (JournalArticle)

Discontinuous grammar as a foreign language

  • Fernández-González, Daniel
  • Gómez-Rodríguez, Carlos
[Abstract] In order to achieve deep natural language understanding, syntactic constituent parsing is a vital step, highly demanded by many artificial intelligence systems to process both text and speech. One of the most recent proposals is the use of standard sequence-to-sequence models to perform constituent parsing as a machine translation task, instead of applying task-specific parsers. While they show a competitive performance, these text-to-parse transducers are still lagging behind classic techniques in terms of accuracy, coverage and speed. To close the gap, we here extend the framework of sequence-to-sequence models for constituent parsing, not only by providing a more powerful neural architecture for improving their performance, but also by enlarging their coverage to handle the most complex syntactic phenomena: discontinuous structures. To that end, we design several novel linearizations that can fully produce discontinuities and, for the first time, we test a sequence-to-sequence model on the main discontinuous benchmarks, obtaining competitive results on par with task-specific discontinuous constituent parsers and achieving state-of-the-art scores on the (discontinuous) English Penn Treebank., Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431C 2020/11, We acknowledge the European Research Council (ERC), which has funded this research under the European Union’s Horizon 2020 research and innovation programme (FASTPARSE, grant agreement No 714150) and the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615), ERDF/ MICINN-AEI (SCANNER-UDC, PID2020-113230RB-C21), Xunta de Galicia (ED431C 2020/11), and Centro de Investigación de Galicia ‘‘CITIC”, funded by Xunta de Galicia and the European Union (ERDF - Galicia 2014–2020 Program), by grant ED431G 2019/01. Funding for open access charge: Universidade da Coruña/CISUG.