Publications by OLST members

@inproceedings{marshman_translation_2024,

title = {Translation programs in the age of genAI: Pivotal change, or plus ça change?},

author = {Elizabeth Marshman},

year  = {2024},

date = {2024-06-01},

address = {Montreal},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gazeau_flexible_2024,

title = {Flexible Lexicalization in Rule-based Text Realization},

author = {Avril Gazeau and François Lareau},

editor = {Nicoletta Calzolari and Min-Yen Kan and Veronique Hoste and Alessandro Lenci and Sakriani Sakti and Nianwen Xue},

url = {https://aclanthology.org/2024.lrec-main.649},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-31},

booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},

pages = {7366–7376},

publisher = {ELRA and ICCL},

address = {Torino, Italia},

abstract = {GenDR is a text realizer that takes as input a graph-based semantic representation and outputs the corresponding syntactic dependency trees. One of the tasks in this transduction is lexicalization, i.e., choosing the right lexical units to express a given semanteme. To do so, GenDR uses a semantic dictionary that maps semantemes to corresponding lexical units in a given language. This study aims to develop a flexible lexicalization module to automatically build a rich semantic dictionary for French. To achieve this, we tried two methods. The first one consisted in extracting information from the French Lexical Network, a large-scale French lexical resource, and adapting it to GenDR. The second one was to test a contextual neural language model's ability to generate potential additional lexicalizations. The first method significantly broadened the coverage of GenDR, while the additional lexicalizations produced by the language model turned out to be of limited use, which brings us to the conclusion that it is not suited to perform the task we've asked from it.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{liu_assessing_2024,

title = {Assessing BERT's sensitivity to idiomaticity},

author = {Li Liu and François Lareau},

editor = {Archna Bhatia and Gosse Bouma and A. Seza Dogruoz and Kilian Evang and Marcos Garcia and Voula Giouli and Lifeng Han and Joakim Nivre and Alexandre Rademaker},

url = {https://aclanthology.org/2024.mwe-1.4},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-31},

booktitle = {Proceedings of the Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD) @ LREC-COLING 2024},

pages = {14–23},

publisher = {ELRA and ICCL},

address = {Torino, Italia},

abstract = {BERT-like language models have been demonstrated to capture the idiomatic meaning of multiword expressions. Linguists have also shown that idioms have varying degrees of idiomaticity. In this paper, we assess CamemBERT's sensitivity to the degree of idiomaticity within idioms, as well as the dependency of this sensitivity on part of speech and idiom length. We used a demasking task on tokens from 3127 idioms and 22551 tokens corresponding to simple lexemes taken from the French Lexical Network (LN-fr), and observed that CamemBERT performs distinctly on tokens embedded within idioms compared to simple ones. When demasking tokens within idioms, the model is not proficient in discerning their level of idiomaticity. Moreover, regardless of idiomaticity, CamemBERT excels at handling function words. The length of idioms also impacts CamemBERT's performance to a certain extent. The last two observations partly explain the difference between the model's performance on idioms versus simple lexemes. We conclude that the model treats idioms differently from simple lexemes, but that it does not capture the difference in compositionality between subclasses of idioms.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{alfetlawi_can_2024,

title = {Can generative AI help users overcome classic challenges for MT? A pilot study},

author = {Anwar Ghanim Alfetlawi and Elizabeth Marshman},

year  = {2024},

date = {2024-02-01},

address = {Doha, Qatar},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{san_martin_what_2024,

title = {What Generative Artificial Intelligence Means for Terminological Definitions},

author = {Antonio San Martín},

url = {https://ceur-ws.org/Vol-3703/paper1.pdf},

year  = {2024},

date = {2024-01-01},

urldate = {2024-03-26},

booktitle = {Proceedings of the 3rd International Conference on Multilingual Digital Terminology Today (MDTT 2024)},

publisher = {CEUR-WS},

address = {Granada},

abstract = {This paper examines the impact of Generative Artificial Intelligence (GenAI) on the creation and consumption of terminological definitions. GenAI tools like ChatGPT present a mix of benefits and drawbacks compared to traditional terminological resources. ChatGPT excels in providing context-specific meanings in an interactive and customized fashion but faces challenges with accuracy. Terminological definitions in recognized resources will likely survive because of their reliability. From the point of view of the terminologist, tools like ChatGPT enable AI-assisted terminography, including post-editing terminography, as an approach blending AI efficiency with human expertise for faster definition creation.},

note = {arXiv:2402.16139 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{michot_carre_2024,

title = {Un carré, est-ce toujours un carré? : pistes pour travailler le lexique mathématique au primaire.},

author = {Sandrine Michot and Ophélie Tremblay},

year  = {2024},

date = {2024-01-01},

booktitle = {Actes du colloque du GDM 2023},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{escouflaire_subjectivite_2024,

title = {La subjectivité dans le journalisme québécois et belge : Transfert de connaissances inter-médias et inter-cultures},

author = {Louis Escouflaire and Antoine Venant and Antoine Descampes and Cédric Fayron},

year  = {2024},

date = {2024-01-01},

booktitle = {JADT 2024: 17th International Conference on Statistical Analysis of Textual Data},

address = {Brussels},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{rigouts_terryn_exploratory_2024,

title = {Exploratory Study on the Impact of English Bias of Generative Large Language Models in Dutch and French},

author = {Ayla Rigouts Terryn and Miryam Lhoneux},

year  = {2024},

date = {2024-01-01},

booktitle = {Proceedings of The 4th Workshop on Human Evaluation of NLP Systems (HumEval’24) at LREC-COLING},

pages = {12–27},

publisher = {European Language Resources Association},

address = {Turin, Italy},

abstract = {The most widely used LLMs like GPT4 and Llama 2 are trained on large amounts of data, mostly in English but are still able to deal with non-English languages. This English bias leads to lower performance in other languages, especially low-resource ones. This paper studies the linguistic quality of LLMs in two non-English high-resource languages: Dutch and French, with a focus on the influence of English. We first construct a comparable corpus of text generated by humans versus LLMs (GPT-4, Zephyr, and GEITje) in the news domain. We proceed to annotate linguistic issues in the LLM-generated texts, obtaining high inter-annotator agreement, and analyse these annotated issues. 

 We find a substantial influence of English for all models under all conditions: on average, 16textbackslash% of all annotations of linguistic errors or peculiarities had a clear link to English. Fine-tuning a LLM to a target language (GEITje is fine-tuned on Dutch) reduces the number of linguistic issues and probably also the influence of English. We further find that using a more elaborate prompt leads to linguistically better results than a concise prompt. Finally, increasing the temperature for one of the models leads to lower linguistic quality but does not alter the influence of English.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{marshman_updating_2023,

title = {Updating translator education programs: Adapting to technologies and their impacts in the Canadian language industry},

author = {Elizabeth Marshman and Anwar Ghanim Alfetlawi and Haifa Ben Naji and Dipen Dave and Ahmed Elhuseiny Bedeir and Ting Liu},

year  = {2023},

date = {2023-11-01},

publisher = {ASLING},

address = {Luxembourg},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{marshman_updating_2023-1,

title = {Updating TTI programs for today’s Canadian market: A case study at uOttawa},

author = {Elizabeth Marshman and Anwar Ghanim Alfetlawi and Haifa Ben Naji and Dipen Dave and Ahmed Elhuseiny Bedeir and Ting Liu},

year  = {2023},

date = {2023-10-01},

address = {Monterey, California/Virtual},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mille_mod-d2t_2023,

title = {Mod-D2T: A Multi-layer Dataset for Modular Data-to-Text Generation},

author = {Simon Mille and François Lareau and Stamatia Dasiopoulou and Anya Belz},

editor = {C. Maria Keet and Hung-Yi Lee and Sina Zarrieß},

url = {https://aclanthology.org/2023.inlg-main.36},

doi = {10.18653/v1/2023.inlg-main.36},

year  = {2023},

date = {2023-09-01},

urldate = {2024-05-31},

booktitle = {Proceedings of the 16th International Natural Language Generation Conference},

pages = {455–466},

publisher = {Association for Computational Linguistics},

address = {Prague, Czechia},

abstract = {Rule-based text generators lack the coverage and fluency of their neural counterparts, but have two big advantages over them: (i) they are entirely controllable and do not hallucinate; and (ii) they can fully explain how an output was generated from an input. In this paper we leverage these two advantages to create large and reliable synthetic datasets with multiple human-intelligible intermediate representations. We present the Modular Data-to-Text (Mod-D2T) Dataset which incorporates ten intermediate-level representations between input triple sets and output text; the mappings from one level to the next can broadly be interpreted as the traditional modular tasks of an NLG pipeline. We describe the Mod-D2T dataset, evaluate its quality via manual validation and discuss its applications and limitations. Data, code and documentation are available at https://github.com/mille-s/Mod-D2T.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{venant_predicates_2023,

title = {Predicates and entities in Abstract Meaning Representation},

author = {Antoine Venant and François Lareau},

editor = {Owen Rambow and François Lareau},

url = {https://aclanthology.org/2023.depling-1.4},

year  = {2023},

date = {2023-03-01},

urldate = {2024-05-31},

booktitle = {Proceedings of the Seventh International Conference on Dependency Linguistics (Depling, GURT/SyntaxFest 2023)},

pages = {32–41},

publisher = {Association for Computational Linguistics},

address = {Washington, D.C.},

abstract = {Nodes in Abstract Meaning Representation (AMR) are generally thought of as neo-Davidsonian entities. We review existing translation into neo-Davidsonian representations and show that these translations inconsistently handle copula sentences. We link the problem to an asymmetry arising from a problematic handling of words with no associated PropBank frames for the underlying predicate. We introduce a method to automatically and uniformly decompose AMR nodes into an entity-part and a predicative part, which offers a consistent treatment of copula sentences and quasi- predicates such as brother or client.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{san_martin_extracting_2023,

title = {Extracting the Agent-Patient Relation from Corpus With Word Sketches},

author = {San Martín, Antonio and Trekker, Catherine and Díaz-Bautista, Juan Carlos},

url = {https://aclanthology.org/2023.ldk-1.73.pdf},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 4th Conference on Language, Data and Knowledge},

pages = {666--675},

publisher = {NOVA CLUNL},

address = {Vienna, Austria},

abstract = {Word sketches are a powerful function of Sketch Engine that automatically summarizes the most common usage patterns of a search word in a corpus. While they have proven to be a valuable tool for collocational analysis in both general and specialized language, their potential for the extraction of terminological knowledge is yet to be fully realized. To address this, we introduce a novel semantic sketch grammar designed to extract the agent-patient relation, an important yet understudied relation. This paper presents the various stages of developing the rules that compose this sketch grammar as well as the evaluation of their precision. The errors identified during the evaluation process are also analyzed to guide future improvements. The sketch grammar is available online so that any user can apply it to their own corpora in Sketch Engine.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}