Papers by Roman Yangarber

14 papers
Benchmarks and models for entity-oriented polarity detection (N18-3)

Copied to clipboard

Challenge: a dataset of 17,000 manually labeled documents is large for determining entity-oriented polarity in business news.
Approach: They propose a convolutional neural network-based approach to classify entity-oriented polarity in business news.
Outcome: The proposed model is based on convolutional neural networks and is small on the scale of existing models.
What Do Transformers Know about Government? (2024.lrec-main)

Copied to clipboard

Challenge: Currently, data is lacking for the research community working on grammatical constructions, and government in particular.
Approach: They use transformer language models to study how government relations are encoded . they use morphologically rich languages to train a classifier capable of discovering new types of government .
Outcome: The proposed classifiers can learn new types of government, the authors show . they find that the classifier can learn government relations in two languages .
Cross-lingual Named Entity Corpus for Slavic Languages (2024.lrec-main)

Copied to clipboard

Challenge: This work presents a corpus manually annotated with named entities for six Slavic languages .
Approach: They propose to manually annotate a corpus of names for six Slavic languages . they use a transformer-based neural network architecture to train multilingual models .
Outcome: The corpus consists of 5,017 documents on seven topics . each entity is described by a category, a lemma, and a unique cross-lingual identifier.
GPT-3.5 for Grammatical Error Correction (2024.lrec-main)

Copied to clipboard

Challenge: Recent work shows that GPT-3.5 struggles with several error types, including punctuation mistakes, tense errors, syntactic dependencies between words, and lexical compatibility at the sentence level.
Approach: They evaluate GPT-3.5 for grammatical error correction in multiple languages . they use it to re-rank correction hypotheses generated by other GEC models .
Outcome: The proposed model performs well in English and Russian, but struggles with errors in other languages.
Revita: a Language-learning Platform at the Intersection of ITS and CALL (L18-1)

Copied to clipboard

Challenge: Existing language-learning tools do not address the fundamental requirements of language learners and teachers.
Approach: They propose a free-to-use platform for language learning beyond the beginner level . they outline the established desiderata of CALL and ITS .
Outcome: The proposed platform supports language learning beyond the beginner level.
Entity Framing and Role Portrayal in the News (2025.findings-acl)

Copied to clipboard

Challenge: a dataset of news articles containing 22 fine-grained characters is annotated for entity framing and role portrayal . the dataset includes 1,378 recent news articles in five languages focusing on the Ukraine-Russia War and climate change .
Approach: They propose a multilingual and hierarchical corpus annotated for entity framing and role portrayal in news articles.
Outcome: The proposed dataset includes 1,378 recent news articles in five languages focusing on the Ukraine-Russia War and climate change . the authors report evaluation results on state-of-the-art multilingual transformers and hierarchical zero-shot learning using LLMs at the level of a document, paragraph, and sentence .
PolyNarrative: A Multilingual, Multilabel, Multi-domain Dataset for Narrative Extraction from News Articles (2025.acl-long)

Copied to clipboard

Challenge: a new dataset of news articles annotated for narratives provides a framework for narrative detection . recurring narratives can propagate with very high velocity across audiences, languages and countries .
Approach: They propose a multilingual dataset annotated for narratives using two-level taxonomies . they define narrative as a recurring, repetitive, overt or implicit claim that promotes a specific interpretation or viewpoint on an ongoing topic .
Outcome: The proposed dataset will foster research in narrative detection and enable new research directions . the authors identify multiple narratives in the same article, and the results are published online .
Linguistic Constructs Represent the Domain Model in Intelligent Language Tutoring (2023.eacl-demo)

Copied to clipboard

Challenge: a new language-learning platform, Revita, is being developed for language learners . the platform uses a system of linguistic constructs to represent domain knowledge .
Approach: They propose to use a domain model to represent the domain knowledge of Revita's online tutoring system.
Outcome: The proposed language-learning platform, Revita, is based on the domain model of linguistic constructs . the system is undergoing pilot use with hundreds of students at several universities .
NarratEX Dataset: Explaining the Dominant Narratives in News Texts (2025.findings-emnlp)

Copied to clipboard

Challenge: a dataset is created to explain the choice of the dominant narrative in a news article . the dataset is intended to address discourse polarization and propaganda detection .
Approach: They propose a dataset for explaining the choice of the dominant narrative in a news article . the dataset is annotated manually with a dominant narrative and sub-narrative labels .
Outcome: The proposed dataset is designed to explain the choice of the dominant narrative in a news article.
Neural Disambiguation of Lemma and Part of Speech in Morphologically Rich Languages (2020.lrec-1)

Copied to clipboard

Challenge: a method for disambiguating the lemma and part of speech of ambiguous words is proposed . a morphological analyser produces multiple analyses for ambiguously words .
Approach: They propose a method for disambiguating the lemma and part of speech of ambiguous words in context . they use a large un-annotated corpus of text and a morphological analyser to train neural networks on the output of the analyser .
Outcome: The proposed method outperforms the state-of-the-art on POS and lemma disambiguation in morphologically rich languages using no manual disambiguations or data annotations.
Effects of sub-word segmentation on performance of transformer language models (2023.emnlp-main)

Copied to clipboard

Challenge: Language models are a fundamental task in natural language processing, but few studies focus on the effect of sub-word segmentation on the performance of models.
Approach: They compare GPT and BERT models trained with statistical segmentation algorithm BPE to unsupervised morphological segmentation algorithms Morfessor and StateMorph.
Outcome: The proposed model trains for several languages and compares them with two unsupervised morphological segmentation algorithms.
Semi-automatically Annotated Learner Corpus for Russian (2022.lrec-1)

Copied to clipboard

Challenge: Revita Learner Corpus is a semi-automatically annotated learner corpus for Russian . it is used for research in second language acquisition and foreign language teaching .
Approach: They propose a semi-automatically annotated learner corpus for Russian that detects errors automatically and annotates errors by type.
Outcome: The proposed corpus detects errors automatically and is annotated by type . the data is made public and the process is much cheaper and faster .
Toward a Paradigm Shift in Collection of Learner Corpora (2020.lrec-1)

Copied to clipboard

Challenge: a pilot version of the Revita Learner Corpus (ReLCo) is available for Russian learners . it is collected and annotated automatically while learners practice with Revita .
Approach: They present the first version of the longitudinal Revita Learner Corpus (ReLCo) for Russian . the corpus contains 8 422 sentences exhibiting several types of errors committed by learners .
Outcome: The Russian version of the Revita Learner Corpus is publicly available . the pilot study shows that the corpus grows continuously while learners practice .
Probing the Category of Verbal Aspect in Transformer Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: a particular challenge is posed by ”alternative contexts” where either the perfective or the imperfective aspect is suitable grammatically and semantically.
Approach: They investigate how pretrained language models encode the grammatical category of verbal aspect in Russian.
Outcome: The proposed model has high predictive uncertainty about aspect in alternative contexts, the authors show .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations