Publications by OLST members

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

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}

}

@inproceedings{rigouts_terryn_supervised_2023,

title = {Supervised Feature-based Classification Approach to Bilingual Lexicon Induction from Specialised Comparable Corpora},

author = {Ayla Rigouts Terryn},

doi = {https://doi.org/10.26615/978-954-452-090-8_008},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the 2023 Workshop on Computational Terminology in NLP and Translation Studies (ConTeNTS), incorporating the BUCC workshop},

pages = {59–68},

publisher = {INCOMA Ltd. Shoumen},

address = {Varna, Bulgaria},

abstract = {This study, submitted to the BUCC2023 shared task on bilingual term alignment in comparable specialised corpora, introduces a supervised, feature-based classification approach. The approach employs both static cross-lingual embeddings and contextual multilingual embeddings, combined with surface-level indicators such as Levenshtein distance and term length, as well as linguistic information. Results exhibit improved performance over previous methodologies, illustrating the merit of integrating diverse features. However, the error analysis also reveals remaining challenges.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{marshman_weird_2022,

title = {Weird, Wonderful, Worthy, and Worrying: Use Cases for MT as Described in Canadian Newspapers},

author = {Elizabeth Marshman},

url = {http://acl-anthology.online/nettt-2022/},

year  = {2022},

date = {2022-07-01},

urldate = {2023-06-06},

booktitle = {Proceedings of the International Conference New Trends in Translation and Technology NeTTT 2022},

pages = {196–205},

address = {Rhodes Island, Greece},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{dube_handling_2022,

title = {Handling Idioms in Symbolic Multilingual Natural Language Generation},

author = {Michaelle Dubé and François Lareau},

editor = {Archna Bhatia and Paul Cook and Shiva Taslimipoor and Marcos Garcia and Carlos Ramisch},

url = {https://aclanthology.org/2022.mwe-1.17},

year  = {2022},

date = {2022-06-01},

urldate = {2024-05-31},

booktitle = {Proceedings of the 18th Workshop on Multiword Expressions @LREC2022},

pages = {118–126},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {While idioms are usually very rigid in their expression, they sometimes allow a certain level of freedom in their usage, with modifiers or complements splitting them or being syntactically attached to internal nodes rather than to the root (e.g., “take something with a big grain of salt”). This means that they cannot always be handled as ready-made strings in rule-based natural language generation systems. Having access to the internal syntactic structure of an idiom allows for more subtle processing. We propose a way to enumerate all possible language-independent n-node trees and to map particular idioms of a language onto these generic syntactic patterns. Using this method, we integrate the idioms from the LN-fr into GenDR, a multilingual realizer. Our implementation covers nearly 98% of LN-fr's idioms with high precision, and can easily be extended or ported to other languages.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kletz_methodology_2022,

title = {A Methodology for Building a Diachronic Dataset of Semantic Shifts and its Application to QC-FR-Diac-V1.0, a Free Reference for French},

author = {David Kletz and Philippe Langlais and François Lareau and Patrick Drouin},

editor = {Nicoletta Calzolari and Frédéric Béchet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Jan Odijk and Stelios Piperidis},

url = {https://aclanthology.org/2022.lrec-1.228},

year  = {2022},

date = {2022-06-01},

urldate = {2024-05-31},

booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference},

pages = {2117–2125},

publisher = {European Language Resources Association},

address = {Marseille, France},

abstract = {Different algorithms have been proposed to detect semantic shifts (changes in a word meaning over time) in a diachronic corpus. Yet, and somehow surprisingly, no reference corpus has been designed so far to evaluate them, leaving researchers to fallback to troublesome evaluation strategies. In this work, we introduce a methodology for the construction of a reference dataset for the evaluation of semantic shift detection, that is, a list of words where we know for sure whether they present a word meaning change over a period of interest. We leverage a state-of-the-art word-sense disambiguation model to associate a date of first appearance to all the senses of a word. Significant changes in sense distributions as well as clear stability are detected and the resulting words are inspected by experts using a dedicated interface before populating a reference dataset. As a proof of concept, we apply this methodology to a corpus of newspapers from Quebec covering the whole 20th century. We manually verified a subset of candidates, leading to QC-FR-Diac-V1.0, a corpus of 151 words allowing one to evaluate the identification of semantic shifts in French between 1910 and 1990.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{joan_casademont_allers-retours_2022-1,

title = {Allers-retours entre recherche et pratique : Analyse de besoins et capsules complémentaires au service des enseignants de Catalan langue additionnelle},

author = {Anna Joan Casademont and Nancy Gagné and Èric Viladrich Castellanas},

year  = {2022},

date = {2022-01-01},

publisher = {REFAD, ONE, CIRTA, Université TÉLUQ},

address = {Québec},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}