The Same Semantic Relations Link Structurally Different Realizations of Concepts
Notice bibliographique
Résumé
To make sense of an utterance, people identify in its linear linguistic expression the concepts and the connections between them. A concept normally has a lexical realization; connections between concepts often do not, but they are perceived even without the benefit of lexical cues. Making these connections – called semantic relations in the field of natural language processing – relies on the form and structure of linguistic expressions, and the concepts these expressions evoke. This implies two levels: the level of the text, the linguistic expression with its form and (grammatical) structure, and the level of the concepts which the speaker wants to convey. An overview of the literature shows that semantic relations are, for pragmatic reasons, a means to an end – extract information, explain the links between the head of a phrase and its arguments, and so on – and that is why they are analyzed from the perspective of what they link. At the text level, the process of semantic relation analysis is informed by syntactic elements – noun phrases, verbs and their arguments, clauses and so on – thus differentiating semantic relations based on the complexity of the syntactic constructions in which their arguments appear. At the conceptual level, the same semantic relation is assigned to pairs of concepts, regardless of their surface expression. The process can be said to disregard the implications of having syntactic constructions of various complexity correspond to the concepts linked. In this article, we propose to put semantic relations first: analyze them, determine what constraints they place on the concepts they connect, and how those concepts can be lexicalized. Lexicalization takes place via expressions of increasing syntactic complexity: phrases, clauses and multi-clause sentences. Next, we show how the linguistic phenomena involved in producing different lexicalizations explain – in a systematic manner – how semantic relations can have instances in syntactic constructions of various complexity. We focus on binary semantic relations between concepts/textual elements within sentences. This kind of analysis leads to a better understanding of the relations themselves and to a systematic account of phenomena related to their occurrence in texts. It reveals some of the assumptions and linguistic gaps people fill when they recognize relations in text. From the computational point of view of text processing, such a solid basis of the analysis of semantic relations adds consistency. Evidence for a particular relation can come from all its instances in a text, regardless of the syntactic form of the concepts it connects. Knowledge of the expected concepts and their syntactic realization may signal the presence of covert or implied information, which we can then work to retrieve. Assigning a semantic relation should be a conscious choice, with the understanding of what implications such a tag has both for the implicitly and explicitly expressed elements of a concept.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,003 | 0,011 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,001 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,004 | 0,003 |
| Études des sciences et des technologies | 0,003 | 0,018 |
| Communication savante | 0,007 | 0,023 |
| Science ouverte | 0,002 | 0,006 |
| Intégrité de la recherche | 0,003 | 0,003 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,009 | 0,002 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».