Agnieszka Kaliska

Dr. Agnieszka Kaliska

Institute of Romance Languages and Literatures, Adam Mickiewicz University in Poznań, Poznań, Wielkopolskie, Poland
+2
orcid
avatar
Co-authors
avatar
Following
avatar
Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 September 2021
Verified
Book Chapter
Closed access
PDF file
TSTomasz Stanisławek
Tomasz Stanisławek
FGFilip Graliński
Filip Graliński
AWAnna Wróblewska
Anna Wróblewska
DLDawid Lipiński
Dawid Lipiński
AKAgnieszka Kaliska
Agnieszka Kaliska
PBPrzemyslaw Biecek
Przemyslaw Biecek
16 April 2022 in arXiv
Verified
Preprint
Open access
PDF file
AWAnia Wróblewska
Ania Wróblewska
AKAgnieszka Kaliska
Agnieszka Kaliska
MPMaciej Pawłowski
Maciej Pawłowski
DWDawid Wiśniewski
Dawid Wiśniewski
WSWitold Sosnowski
Witold Sosnowski
AŁAgnieszka Ławrynowicz
Agnieszka Ławrynowicz
Food Computing is currently a fast-growing field of research. Natural language processing (NLP) is also increasingly essential in this field, especially for recognising food entities. However, there are still only a few well-defined tasks that serve as benchmarks for solutions in this area. We introduce a new dataset -- called \textit{TASTEset} -- to bridge this gap. In this dataset, Named Entity Recognition (NER) models are expected to find or infer various types of entities helpful in processing recipes, e.g.~food products, quantities and their units, names of cooking processes, physical quality of ingredients, their purpose, taste. The dataset consists of 700 recipes with more than 13,000 entities to extract. We provide a few state-of-the-art baselines of named entity recognition models, which show that our dataset poses a solid challenge to existing models. The best model achieved, on average, 0.95 $F_1$ score, depending on the entity type -- from 0.781 to 0.982. We share the dataset and the task to encourage progress on more in-depth and complex information extraction from recipes.
8 December 2011
Verified
Journal Article
Closed access
AKAgnieszka Kaliska
Agnieszka Kaliska
The common co-occurrence of words in a given context reflects both the extra-linguistic knowledge of a language user, and the specific intra-linguistic rules. We can say that lexicon and grammar are interpreters of the extra-linguistic reality. The purpose of our research is to consider, in French-Polish constrastive perspective, the relation between the pronoun and the meteorological verb (such as il and venter in Il vente) on the one hand and, on the other, the relation between the meteorological noun and the special kind of support verb named verbe d’occurrence on the Lexicon-Grammar ground (such as vent and mugir in Le vent mugit). We then raise the question of the particular status of meteorological nouns in the grammatical subject position and explain the non-predicative character of verbs in constructions such as Le vent mugit. In the end, we present a list of Polish and French examples containing meteorological support verbs or their stylistic and aspectual variants.
5 December 2023
Verified
Conference Paper
Open access
AŁAgnieszka Ławrynowicz
Agnieszka Ławrynowicz
AWAnna Wróblewska
Anna Wróblewska
AKAgnieszka Kaliska
Agnieszka Kaliska
MPMaciej Pawłowski
Maciej Pawłowski
DWDawid Wiśniewski
Dawid Wiśniewski
JDJakub Dutkiewicz
Jakub Dutkiewicz
Food computing is currently fast-growing into an innovative area of knowledge extraction. However, benchmarks for information extraction from semi-structured data, especially when dealing with more complex relations, are scarce in this domain. In this paper, we introduce a benchmark aimed at information extraction of complex entities to support ingredient substitution tasks. Firstly, we present a new dataset – called TASTEset – for fine-grained recognition of food entities in culinary recipes. Secondly, we provide complex entity annotations for substitution on top of the fine-grained entity mentions, which we carefully prepared. We share the dataset and the tasks to encourage progress on more in-depth and complex information extraction from recipes.
1 June 2022 in Journal of Linguistics/jazykovedný Casopis
Verified
Journal Article
Open access
PDF file
AKAgnieszka Kaliska
Agnieszka Kaliska
The technological revolution that has occurred in recent decades has made accessible for researches large textual data collections. At the same time, the development of increasingly sophisticated computer tools provides them with new methods of analyzing texts. In the present study however we examine the functionalities offered by traditional tools, namely GNU/Linux tools, easily accessible via the command line but still unknown among linguists with little or no computer knowledge. Our goal is to show how using the web corpus on the one hand and the processing GNU/Linux tools on the other, we can extract key-terms of fishing jargon.
1 January 2009 in Studia Romanica Posnaniensia
Verified
Journal Article
Open access
PDF file
AKAgnieszka Kaliska
Agnieszka Kaliska
This paper focuses on a group of French and Polish morphological causative constructions in which the cause and effect elements are contiguous. One of the main claims pursued here is that their semantic deep structure is parallel to the one of the respective analytical causative constructions. On the other hand, Polish prefixes are more problematic because of their capacity to express the causation and the perfectibility by the same form. Some linguists claim that there are no causative prefixes in Polish but only flexional circumfixes with the capacity to express the causation. The paper also tackles the problem of definability of causation. Sometimes vastly different ideas are subsumed under this label.