--- title: "Peru — research institutions, scientists and papers" description: "Peru: 1 institutions with papers in our library in 1 agglomerations, 0 people with a page, 4 works, 187 citations." canonical: "https://research.elamur.ai/free/en/countries/peru/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/countries/peru/) [home](https://md.research.elamur.ai/free/en/) / [countries](https://md.research.elamur.ai/free/en/countries/) / Peru # Peru Country 1 institution in 1 agglomeration · [all countries](https://md.research.elamur.ai/free/en/countries/) [**1** institution with a page](https://md.research.elamur.ai/free/en/countries/peru/#institutions) · [**1** agglomeration](https://md.research.elamur.ai/free/en/countries/peru/#agglomerations) · [**0** people with a page](https://md.research.elamur.ai/free/en/countries/peru/#authors) · [**4** works in our library](https://md.research.elamur.ai/free/en/countries/peru/#works) · [**187** citations of their works](https://md.research.elamur.ai/free/en/countries/peru/#works) ## About ### Profile Peru appears among the [countries](https://md.research.elamur.ai/free/en/countries/) of this library through a compact body of work in language science. All of the country's research on this site comes from the [Pontificia Universidad Católica del Perú](https://md.research.elamur.ai/free/en/universities/pontificia-universidad-catolica-del-peru/), a university based in [Lima](https://md.research.elamur.ai/free/en/agglomerations/lima/). Lima is therefore the country's only city region here, and the university is the only Peruvian institution with works in the collection. The country's [institutions](https://md.research.elamur.ai/free/en/countries/peru/institutions/) and [agglomerations](https://md.research.elamur.ai/free/en/countries/peru/agglomerations/) can each be browsed separately, but at present both lead to the same place: a Lima university whose papers in our library concern how human languages are structured and how computers can process them. The resulting picture is narrow but coherent. The Peruvian works here deal with text simplification, inflectional morphology across many languages, a syntactic treebank for an Indigenous Amazonian language, and the behaviour of large language models on Quechua. Together they show a research line that moves from general natural language processing toward the languages of Peru itself. The picture depends on what this site holds, and it does not stand for the whole of Peruvian science. ### History The earliest Peruvian work in our library dates from 2017. It is a study of automatic text simplification, led by Fernando Alva-Manchego with Joachim Bingel, Gustavo Paetzold and other co-authors. It belongs to mainstream computational linguistics and concerns English-style simplification corpora rather than any language of Peru. The next work appears in 2022, when the university is linked to the fourth release of UniMorph, a large shared resource for inflectional morphology across many languages, with Khuyagbaatar Batsuren, Omer Goldman and Salam Khalifa named first among its authors. This marks a move from a single task toward building multilingual infrastructure. The most recent works, from 2025 and 2026, turn to Peruvian languages directly. A 2025 paper builds a Universal Dependencies treebank for Amahuaca, and a 2026 paper tests large language models on morphosyntactic changes in Quechua Collao. Read in order, the works suggest a growing focus on low-resource and Indigenous languages, carried out with the tools and standards of international computational linguistics. ### Research profile Three fields are attached to the Peruvian works here: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/), [Machine translation](https://md.research.elamur.ai/free/en/shelves/machine-translation/) and [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/). Linguistics carries the most weight, which fits the descriptive character of the Amahuaca and UniMorph work. The topics attached to the works are [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/), [Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) and [Morphology](https://md.research.elamur.ai/free/en/topics/morphology/). The first strand is text simplification. The 2017 study [Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs](https://md.research.elamur.ai/free/en/papers/manchego-2017-learning-how-simplify-explicit-labeling/) starts from a weakness of end-to-end simplification systems. Such systems learn from aligned pairs of complex and simpler sentences, but they offer no account of what changes they have learned to make. The paper instead labels the edits between the two versions explicitly, so that the operations behind simplification can be studied and modelled. The second strand is morphology at scale. [UniMorph 4.0: Universal Morphology](https://md.research.elamur.ai/free/en/papers/batsuren-2022-unimorph-4/) describes a new release of a multilingual database of inflection tables, the paradigms that show how a word changes form for tense, number, case and similar categories. Resources of this kind support work on morphological analysis and generation, and are especially useful for languages with rich inflection and few digital tools. The third strand is syntactic annotation for Indigenous languages. [Universal Dependencies for Amahuaca](https://md.research.elamur.ai/free/en/papers/angulo-2025-universal-dependencies-amahuaca/), by Candy Angulo, Pilar Valenzuela and Roberto Zariquiey, presents the first treebank for Amahuaca in the Universal Dependencies framework, a cross-linguistic scheme for marking the grammatical relations between words. A treebank of this kind makes an under-documented language available for comparative linguistics and computational tools. The fourth strand evaluates large language models on a low-resource language. [On the Robustness of Morphosyntactic Transformation with Large Language Models: The Case of Quechua Collao](https://md.research.elamur.ai/free/en/papers/pocco-2026-robustness-morphosyntactic-transformation-large-language/), by Pool Pocco and [Arturo Oncevay](https://md.research.elamur.ai/free/en/authors/arturo-oncevay/), asks how reliably such models can change the grammatical form of Quechua sentences. Its main finding is that the design of prompts and tasks shaped the results more than model size did. That conclusion matters for languages where large training sets are hard to find. ### Leading scientists The first person shown for the Pontificia Universidad Católica del Perú is Arturo Oncevay. On this site Oncevay's work with the university is the 2026 study of Quechua Collao, written with Pool Pocco. It combines large language models with the morphosyntax of an agglutinative Andean language and places the model's behaviour under careful testing rather than taking its outputs at face value. The other works name further researchers among their authors. They include Fernando Alva-Manchego, Joachim Bingel and Gustavo Paetzold on simplification; Khuyagbaatar Batsuren, Omer Goldman and Salam Khalifa on UniMorph; and Candy Angulo, Pilar Valenzuela and Roberto Zariquiey on Amahuaca. The site does not specify which of these authors are attached to the Lima university, so they are best read as the collaborators through whom Peruvian research appears here. ### Landmark works The most cited Peruvian work in our library is the 2017 simplification study by Alva-Manchego and colleagues. Many papers in the library cite it, which makes it the main link between Peruvian research and the wider literature on making texts easier to read. Its value lies in treating simplification as a set of visible editing operations rather than an opaque transformation. Close behind is UniMorph 4.0 from 2022, which is also cited by many papers here. As a shared resource, its influence runs through the many studies that use its inflection tables for training and evaluation across languages. The Amahuaca treebank from 2025 has only begun to attract citations here. The 2026 Quechua Collao study is too recent to have gathered any. Both are nonetheless the works most tied to Peru's own linguistic landscape, and they mark the direction the country's research on this site has taken most recently. ### Labs and units No separate departments, laboratories or research groups of the Pontificia Universidad Católica del Perú appear on this site. The university is the single unit through which the country's research is shown. Its works span computational linguistics and descriptive linguistics, so both language technology and documentation of Indigenous languages are represented within the same institution. ### Collaborations Every Peruvian work here is co-authored, and several bring together large author teams. UniMorph 4.0 in particular is a broad multilingual effort, and its listed lead authors suggest an international consortium. The 2017 simplification study likewise involves several co-authors. The site does not give the countries or institutions of these partners, so the shape of the network can only be inferred from the co-authorship itself. The Amahuaca work brings together linguists focused on Amazonian languages. The Quechua study pairs Pool Pocco with Arturo Oncevay. Taken together, these collaborations show Peruvian researchers working both in large multilingual projects and in small teams centred on particular languages of the country. Since Lima is the only city region and the university the only institution here, the site shows no links between Peruvian industry and academia. ### Timeline In 2017 the first Peruvian work appears on this site: the study of text simplification through explicitly labelled pairs of complex and simplified text. It remains the most cited of the country's works here. In 2022 the university is connected to UniMorph 4.0, a multilingual morphology resource. This shifts the emphasis toward shared infrastructure for many languages, including those with little digital support. In 2025 the Universal Dependencies treebank for Amahuaca brings an Amazonian language of Peru into a cross-linguistic annotation framework. In 2026 the study by Pocco and Oncevay on Quechua Collao tests large language models on morphosyntactic transformation and finds that task and prompt design count for more than model scale. It extends the recent line of work on the low-resource languages of Peru. ## Where ## Agglomerations (1) 1. [**Lima**1 institution*187 citations*](https://md.research.elamur.ai/free/en/agglomerations/lima/) ## Institutions (1) ### 🎓 Universities (1) **[Pontificia Universidad Católica del Perú](https://md.research.elamur.ai/free/en/universities/pontificia-universidad-catolica-del-peru/)**University · [Lima](https://md.research.elamur.ai/free/en/agglomerations/lima/), Peru*4 works · 187 citations* ## Works in our library (4) Works of its institutions, the most cited first. 1. [**Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs**Fernando Alva-Manchego, Joachim Bingel, Gustavo Paetzold, et al.*2017 · 104 citations*](https://md.research.elamur.ai/free/en/papers/manchego-2017-learning-how-simplify-explicit-labeling/) 2. [**UniMorph 4.0: Universal Morphology**Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa*2022 · 82 citations*](https://md.research.elamur.ai/free/en/papers/batsuren-2022-unimorph-4/) 3. [**Universal Dependencies for Amahuaca**Candy Angulo, Pilar Valenzuela, Roberto Zariquiey*2025 · 1 citation*](https://md.research.elamur.ai/free/en/papers/angulo-2025-universal-dependencies-amahuaca/) 4. [**On the Robustness of Morphosyntactic Transformation with Large Language Models: The Case of Quechua Collao**Pool Pocco, Arturo Oncevay*2026*](https://md.research.elamur.ai/free/en/papers/pocco-2026-robustness-morphosyntactic-transformation-large-language/) ## Concepts, shelves and topics Of its works in our library: the number of works on each and its rating among them. 📚 Shelves 5[Linguistics & languages · 3 works · 5.5](https://md.research.elamur.ai/free/en/shelves/linguistics/) · [English · 1 work · 4.5](https://md.research.elamur.ai/free/en/shelves/en/) · [Machine translation · 1 work · 3.4](https://md.research.elamur.ai/free/en/shelves/machine-translation/) · [Machine translation · 1 work · 3.4](https://md.research.elamur.ai/free/en/shelves/mtrans/) · [Natural language processing · 1 work · 3.4](https://md.research.elamur.ai/free/en/shelves/nlp/) 🧭 Topics 3[Morphology · 1 work · 9.1](https://md.research.elamur.ai/free/en/topics/morphology/) · [Universal Dependencies · 1 work · 1.0](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) · [Low-resource languages · 1 work · 0.0](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) ## Works by year ### 2020s [**2026** 1 work](https://md.research.elamur.ai/free/en/papers/pocco-2026-robustness-morphosyntactic-transformation-large-language/) · [**2025** 1 work](https://md.research.elamur.ai/free/en/papers/angulo-2025-universal-dependencies-amahuaca/) · [**2022** 1 work](https://md.research.elamur.ai/free/en/papers/batsuren-2022-unimorph-4/) ### 2010s [**2017** 1 work](https://md.research.elamur.ai/free/en/papers/manchego-2017-learning-how-simplify-explicit-labeling/) - [← back to](https://md.research.elamur.ai/free/en/countries/) — countries