arXiv subjects

Ricardo Campos

Publications and source records attributed to Ricardo Campos.

At least 37 records · Page 2Linked to original sources

arXiv2024

PD Operads and Explicit Partition Lie Algebras

Infinitesimal deformations are governed by partition Lie algebras. In characteristic $0$, these higher categorical structures are modelled by differential graded Lie algebras, but in characteristic $p$, they are more subtle. We give explicit models for partition Lie algebras over general coherent rings, both in the setting of spectral and derived algebraic geometry. For the spectral case, we refine operadic Koszul duality to a functor from operads to divided power operads, by taking refined linear duals of $Σ_n$-representations. The derived case requires a further refinement of Koszul duality to a more genuine setting.

math.AG↗

arXiv2024

Event Extraction for Portuguese: A QA-driven Approach using ACE-2005

Event extraction is an Information Retrieval task that commonly consists of identifying the central word for the event (trigger) and the event's arguments. This task has been extensively studied for English but lags behind for Portuguese, partly due to the lack of task-specific annotated corpora. This paper proposes a framework in which two separated BERT-based models were fine-tuned to identify and classify events in Portuguese documents. We decompose this task into two sub-tasks. Firstly, we use a token classification model to detect event triggers. To extract event arguments, we train a Question Answering model that queries the triggers about their corresponding event argument roles. Given the lack of event annotated corpora in Portuguese, we translated the original version of the ACE-2005 dataset (a reference in the field) into Portuguese, producing a new corpus for Portuguese event extraction. To accomplish this, we developed an automatic translation pipeline. Our framework obtains F1 marks of 64.4 for trigger classification and 46.7 for argument classification setting, thus a new state-of-the-art reference for these tasks in Portuguese.

cs.CL↗

arXiv2024

ACE-2005-PT: Corpus for Event Extraction in Portuguese

Event extraction is an NLP task that commonly involves identifying the central word (trigger) for an event and its associated arguments in text. ACE-2005 is widely recognised as the standard corpus in this field. While other corpora, like PropBank, primarily focus on annotating predicate-argument structure, ACE-2005 provides comprehensive information about the overall event structure and semantics. However, its limited language coverage restricts its usability. This paper introduces ACE-2005-PT, a corpus created by translating ACE-2005 into Portuguese, with European and Brazilian variants. To speed up the process of obtaining ACE-2005-PT, we rely on automatic translators. This, however, poses some challenges related to automatically identifying the correct alignments between multi-word annotations in the original text and in the corresponding translated sentence. To achieve this, we developed an alignment pipeline that incorporates several alignment techniques: lemmatization, fuzzy matching, synonym matching, multiple translations and a BERT-based word aligner. To measure the alignment effectiveness, a subset of annotations from the ACE-2005-PT corpus was manually aligned by a linguist expert. This subset was then compared against our pipeline results which achieved exact and relaxed match scores of 70.55\% and 87.55\% respectively. As a result, we successfully generated a Portuguese version of the ACE-2005 corpus, which has been accepted for publication by LDC.

cs.CL↗

arXiv2024

TEI2GO: A Multilingual Approach for Fast Temporal Expression Identification

Temporal expression identification is crucial for understanding texts written in natural language. Although highly effective systems such as HeidelTime exist, their limited runtime performance hampers adoption in large-scale applications and production environments. In this paper, we introduce the TEI2GO models, matching HeidelTime's effectiveness but with significantly improved runtime, supporting six languages, and achieving state-of-the-art results in four of them. To train the TEI2GO models, we used a combination of manually annotated reference corpus and developed ``Professor HeidelTime'', a comprehensive weakly labeled corpus of news texts annotated with HeidelTime. This corpus comprises a total of $138,069$ documents (over six languages) with $1,050,921$ temporal expressions, the largest open-source annotated dataset for temporal expression identification to date. By describing how the models were produced, we aim to encourage the research community to further explore, refine, and extend the set of models to additional languages and domains. Code, annotations, and models are openly available for community exploration and use. The models are conveniently on HuggingFace for seamless integration and application.

cs.CL↗

arXiv2024

Indexing Portuguese NLP Resources with PT-Pump-Up

The recent advances in natural language processing (NLP) are linked to training processes that require vast amounts of corpora. Access to this data is commonly not a trivial process due to resource dispersion and the need to maintain these infrastructures online and up-to-date. New developments in NLP are often compromised due to the scarcity of data or lack of a shared repository that works as an entry point to the community. This is especially true in low and mid-resource languages, such as Portuguese, which lack data and proper resource management infrastructures. In this work, we propose PT-Pump-Up, a set of tools that aim to reduce resource dispersion and improve the accessibility to Portuguese NLP resources. Our proposal is divided into four software components: a) a web platform to list the available resources; b) a client-side Python package to simplify the loading of Portuguese NLP resources; c) an administrative Python package to manage the platform and d) a public GitHub repository to foster future collaboration and contributions. All four components are accessible using: https://linktr.ee/pt_pump_up

cs.CL↗

arXiv2024

Operadic Deformation Theory

This is a survey on recent progress in algebraic deformation theory and the application of algebraic operads to its study. We review the classical homotopical tools in the theory of algebraic operads, namely Koszul duality. We give concrete examples of applications of such tools to various flavours of problems related to deformations of algebraic structures. We also study formal moduli problems and related notions from the operadic point of view.

math.AT↗

arXiv2024

Physio: An LLM-Based Physiotherapy Advisor

The capabilities of the most recent language models have increased the interest in integrating them into real-world applications. However, the fact that these models generate plausible, yet incorrect text poses a constraint when considering their use in several domains. Healthcare is a prime example of a domain where text-generative trustworthiness is a hard requirement to safeguard patient well-being. In this paper, we present Physio, a chat-based application for physical rehabilitation. Physio is capable of making an initial diagnosis while citing reliable health sources to support the information provided. Furthermore, drawing upon external knowledge databases, Physio can recommend rehabilitation exercises and over-the-counter medication for symptom relief. By combining these features, Physio can leverage the power of generative models for language processing while also conditioning its response on dependable and verifiable sources. A live demo of Physio is available at https://physio.inesctec.pt.

cs.CL↗

arXiv2023

GPT Struct Me: Probing GPT Models on Narrative Entity Extraction

The importance of systems that can extract structured information from textual data becomes increasingly pronounced given the ever-increasing volume of text produced on a daily basis. Having a system that can effectively extract such information in an interoperable manner would be an asset for several domains, be it finance, health, or legal. Recent developments in natural language processing led to the production of powerful language models that can, to some degree, mimic human intelligence. Such effectiveness raises a pertinent question: Can these models be leveraged for the extraction of structured information? In this work, we address this question by evaluating the capabilities of two state-of-the-art language models -- GPT-3 and GPT-3.5, commonly known as ChatGPT -- in the extraction of narrative entities, namely events, participants, and temporal expressions. This study is conducted on the Text2Story Lusa dataset, a collection of 119 Portuguese news articles whose annotation framework includes a set of entity structures along with several tags and attribute values. We first select the best prompt template through an ablation study over prompt components that provide varying degrees of information on a subset of documents of the dataset. Subsequently, we use the best templates to evaluate the effectiveness of the models on the remaining documents. The results obtained indicate that GPT models are competitive with out-of-the-box baseline systems, presenting an all-in-one alternative for practitioners with limited resources. By studying the strengths and limitations of these models in the context of information extraction, we offer insights that can guide future improvements and avenues to explore in this field.

cs.CL↗

arXiv2023

tieval: An Evaluation Framework for Temporal Information Extraction Systems

Temporal information extraction (TIE) has attracted a great deal of interest over the last two decades, leading to the development of a significant number of datasets. Despite its benefits, having access to a large volume of corpora makes it difficult when it comes to benchmark TIE systems. On the one hand, different datasets have different annotation schemes, thus hindering the comparison between competitors across different corpora. On the other hand, the fact that each corpus is commonly disseminated in a different format requires a considerable engineering effort for a researcher/practitioner to develop parsers for all of them. This constraint forces researchers to select a limited amount of datasets to evaluate their systems which consequently limits the comparability of the systems. Yet another obstacle that hinders the comparability of the TIE systems is the evaluation metric employed. While most research works adopt traditional metrics such as precision, recall, and $F_1$, a few others prefer temporal awareness -- a metric tailored to be more comprehensive on the evaluation of temporal systems. Although the reason for the absence of temporal awareness in the evaluation of most systems is not clear, one of the factors that certainly weights this decision is the necessity to implement the temporal closure algorithm in order to compute temporal awareness, which is not straightforward to implement neither is currently easily available. All in all, these problems have limited the fair comparison between approaches and consequently, the development of temporal extraction systems. To mitigate these problems, we have developed tieval, a Python library that provides a concise interface for importing different corpora and facilitates system evaluation. In this paper, we present the first public release of tieval and highlight its most relevant features.

cs.CL↗

arXiv2023

Lie, associative and commutative quasi-isomorphism

Over a field of characteristic zero, we show that two commutative differential graded (dg) algebras are quasi-isomorphic if and only if they are quasi-isomorphic as associative dg algebras. This answers a folklore problem in rational homotopy theory, showing that the rational homotopy type of a space is determined by its associative dg algebra of rational cochains. We also show a Koszul dual statement, under an additional completeness hypothesis: two homotopy complete dg Lie algebras whose universal enveloping algebras are quasi-isomorphic as associative dg algebras must themselves be quasi-isomorphic. The latter result applies in particular to nilpotent Lie algebras (not differential graded), in which case it says that two nilpotent Lie algebras whose universal enveloping algebras are isomorphic as associative algebras must be isomorphic.

math.RA↗

arXiv2023

Configuration Spaces of Manifolds with Boundary

We study ordered configuration spaces of compact manifolds with boundary. We show that for a large class of such manifolds, the real homotopy type of the configuration spaces only depends on the real homotopy type of the pair consisting of the manifold and its boundary. We moreover describe explicit real models of these configuration spaces using three different approaches. We do this by adapting previous constructions for configuration spaces of closed manifolds which relied on Kontsevich's proof of the formality of the little disks operads. We also prove that our models are compatible with the richer structure of configuration spaces, respectively a module over the Swiss-Cheese operad, a module over the associative algebra of configurations in a collar around the boundary of the manifold, and a module over the little disks operad.

math.AT↗

arXiv2023

FALQU: Finding Answers to Legal Questions

This paper presents a new test collection for Legal IR, FALQU: Finding Answers to Legal Questions, where questions and answers were obtained from Law Stack Exchange (LawSE), a Q&A website for legal professionals, and others with experience in law. Much in line with Stack overflow, Law Stack Exchange has a variety of questions on different topics such as copyright, intellectual property, and criminal laws, making it an interesting source for dataset construction. Questions are also not limited to one country. Often, users of different nationalities may ask questions about laws in different countries and expertise. Therefore, questions in FALQU represent real-world users' information needs thus helping to avoid lab-generated questions. Answers on the other side are given by experts in the field. FALQU is the first test collection, to the best of our knowledge, to use LawSE, considering more diverse questions than the questions from the standard legal bar and judicial exams. It contains 9880 questions and 34,145 answers to legal questions. Alongside our new test collection, we provide different baseline systems that include traditional information retrieval models such as TF-IDF and BM25, and deep neural network search models. The results obtained from the BM25 model achieved the highest effectiveness.

cs.IR↗

arXiv2022

Commutative homotopical algebra embeds into non-commutative homotopical algebra

Over a field of characteristic zero, we show that the forgetful functor from the homotopy category of commutative dg algebras to the homotopy category of dg associative algebras is faithful. In fact, the induced map of derived mapping spaces gives an injection on all homotopy groups at any basepoint. We prove similar results both for unital and non-unital algebras, and also Koszul dually for the universal enveloping algebra functor from dg Lie algebras to dg associative algebras. An important ingredient is a natural model for these derived mapping spaces as Maurer-Cartan spaces of complete filtered dg Lie algebras (or curved Lie algebras, in the unital case).

math.AT↗

arXiv2022

Moduli problems for operadic algebras

A theorem of Pridham and Lurie provides an equivalence between formal moduli problems and Lie algebras in characteristic zero. We prove a generalization of this correspondence, relating formal moduli problems parametrized by algebras over a Koszul operad to algebras over its Koszul dual operad. In particular, when the Lie algebra associated to a deformation problem is induced from a pre-Lie structure it corresponds to a permutative formal moduli problem. As another example we obtain a correspondence between operadic formal moduli problems and augmented operads.

math.AT↗

arXiv2022

A model for configuration spaces of points

We construct a real combinatorial model for the configuration spaces of points of compact smooth oriented manifolds without boundary. We use these models to show that the real homotopy type of configuration spaces of a simply connected such manifold only depends on the real homotopy type of the manifold. Moreover, we show that for framed $D$-dimensional manifolds these models capture a natural right homotopy action of the little $D$-disks operad.

math.QA↗

arXiv2021

Lie algebroids are curved Lie algebras

We show that there is an equivalence of $\infty$-categories between Lie algebroids and certain kinds of curved Lie algebras. For this we develop a method to study the $\infty$-category of curved Lie algebras using the homotopy theory of algebras over a complete operad.

math.AT↗

arXiv2021

Boardman-Vogt resolutions and bar/cobar constructions of (co)operadic (co)bimodules

We develop the combinatorics of leveled trees in order to construct explicit resolutions of (co)operads and (co)operadic (co)bimodules. We build explicit cofibrant resolutions of operads and operadic bimodules in spectra analogous to the ordinary Boardman--Vogt resolutions and we express them as cobar constructions of indecomposable elements. Dually, in the context of CDGAs, we perform similar constructions, and we obtain fibrant resolutions of Hopf cooperads and Hopf cooperadic cobimodules. We also express them as bar constructions of primitive elements.

math.AT↗

arXiv2020

Differential forms on smooth operadic algebras

The classical Hochschild--Kostant--Rosenberg (HKR) theorem computes the Hochschild homology and cohomology of smooth commutative algebras. In this paper, we generalise this result to other kinds of algebraic structures. Our main insight is that producing HKR isomorphisms for other types of algebras is directly related to computing quasi-free resolutions in the category of left modules over an operad; we establish that an HKR-type result follows as soon as this resolution is diagonally pure. As examples we obtain a permutative and a pre-Lie HKR theorem for smooth commutative and smooth brace algebras, respectively. We also prove an HKR theorem for operads obtained from a filtered distributive law, which recovers, in particular, all the aspects of the classical HKR theorem. Finally, we show that this property is Koszul dual to the operadic PBW property defined by V. Dotsenko and the second author (1804.06485).

math.KT↗