edsnlp.pipelines.qualifiers.hypothesis

patterns

pseudo: List[str] = ['aucun doute', 'même si', 'pas de condition', 'pas de doute', 'sans aucun doute', 'sans condition', 'sans risque'] module-attribute

confirmation: List[str] = ['certain', 'certaine', 'certainement', 'certaines', 'certains', 'confirmer', 'évidemment', 'évident', 'évidente', 'montrer que', 'visiblement'] module-attribute

preceding: List[str] = ['à condition', 'à la condition que', 'à moins que', 'au cas où', 'conditionnellement', 'doute', 'en admettant que', 'en cas', 'en considérant que', 'en supposant que', 'éventuellement', 'faudrait', 'hypothèse', 'hypothèses', 'idée depas confirmer', 'pas sûr', 'pas sûre', 'peut correspondre', 'peut-être', 'peuvent correspondre', 'possible', 'possiblement', 'potentiel', 'potentielle', 'potentiellement', 'potentielles', 'potentiels', 'prédisposant à', 'probable', 'probablement', 'probables', "recherche d'recherche de", 'recherche des', 'risque', 'sauf si', 'selon', 'si', "s'il", 'soit', 'sous condition', 'sous réserve', 'suspicion'] module-attribute

following: List[str] = ['?', 'envisagé', 'envisageable', 'envisageables', 'envisagées', 'envisagés', 'hypothétique', 'hypothétiquement', 'hypothétiques', 'pas certain', 'pas certaine', 'pas clair', 'pas claire', 'pas confirmé', 'pas confirmée', 'pas confirmées', 'pas confirmés', 'pas évident', 'pas évidente', 'pas sûr', 'pas sûre', 'possible', 'potentiel', 'potentielle', 'potentiels', 'probable', 'probables', ': \n', ':\n'] module-attribute

verbs_hyp: List[str] = ['douter', 'envisager', "s'apparenter", 'sembler', 'soupçonner', 'suggérer', 'suspecter'] module-attribute

verbs_eds: List[str] = ['abandonner', 'abolir', 'aborder', 'accepter', 'accidenter', 'accompagnemer', 'accompagner', 'acoller', 'acquérir', 'activer', 'actualiser', 'adapter', 'adhérer', 'adjuver', 'admettre', 'administrer', 'adopter', 'adresser', 'aggraver', 'agir', 'agréer', 'aider', 'aimer', 'alcooliser', 'alerter', 'alimenter', 'aller', 'allonger', 'alléger', 'alterner', 'altérer', 'amender', 'amener', 'améliorer', 'amyotrophier', 'améliorer', 'analyser', 'anesthésier', 'animer', 'annexer', 'annuler', 'anonymiser', 'anticiper', 'anticoaguler', 'apercevoir', 'aplatir', 'apparaître', 'appareiller', 'appeler', 'appliquer', 'apporter', 'apprendre', 'apprécier', 'appuyer', 'argumenter', 'arquer', 'arrêter', 'arriver', 'arrêter', 'articuler', 'aspirer', 'asseoir', 'assister', 'associer', 'assurer', 'assécher', 'attacher', 'atteindre', 'attendre', 'attribuer', 'augmenter', 'autonomiser', 'autoriser', 'avaler', 'avancer', 'avertir', 'avoir', 'avérer', 'aérer', 'baisser', 'ballonner', 'blesser', 'bloquer', 'boire', 'border', 'brancher', 'brûler', 'bénéficier', 'cadrer', 'calcifier', 'calculer', 'calmer', 'canaliser', 'capter', 'carencer', 'casser', 'centrer', 'cerner', 'certifier', 'changer', 'charger', 'chevaucher', 'choisir', 'chronomoduler', 'chuter', 'cicatriser', 'circoncire', 'circuler', 'classer', 'codéiner', 'coincer', 'colorer', 'combler', 'commander', 'commencer', 'communiquer', 'comparer', 'compliquer', 'compléter', 'comporter', 'comprendre', 'comprimer', 'concerner', 'conclure', 'condamner', 'conditionner', 'conduire', 'confiner', 'confirmer', 'confronter', 'congeler', 'conjoindre', 'conjuguer', 'connaître', 'connecter', 'conseiller', 'conserver', 'considérer', 'consommer', 'constater', 'constituer', 'consulter', 'contacter', 'contaminer', 'contenir', 'contentionner', 'continuer', 'contracter', 'contrarier', 'contribuer', 'contrôler', 'convaincre', 'convenir', 'convier', 'convoquer', 'copier', 'correspondre', 'corriger', 'corréler', 'coucher', 'coupler', 'couvrir', 'crapotter', 'creuser', 'croire', 'croiser', 'créer', 'crémer', 'crépiter', 'cumuler', 'curariser', 'céder', 'dater', 'demander', 'demeurer', 'destiner', 'devenir', 'devoir', 'diagnostiquer', 'dialyser', 'dicter', 'diffuser', 'différencier', 'différer', 'digérer', 'dilater', 'diluer', 'diminuer', 'diner', 'dire', 'diriger', 'discuter', 'disparaître', 'disposer', 'dissocier', 'disséminer', 'disséquer', 'distendre', 'distinguer', 'divorcer', 'documenter', 'donner', 'dorer', 'doser', 'doubler', 'durer', 'dyaliser', 'dyspner', 'débuter', 'décaler', 'déceler', 'décider', 'déclarer', 'déclencher', 'découvrir', 'décrire', 'décroître', 'décurariser', 'décéder', 'dédier', 'définir', 'dégrader', 'délivrer', 'dépasser', 'dépendre', 'déplacer', 'dépolir', 'déposer', 'dériver', 'dérouler', 'désappareiller', 'désigner', 'désinfecter', 'désorienter', 'détecter', 'déterminer', 'détruire', 'développer', 'dévouer', 'dîner', 'écraser', 'effacer', 'effectuer', 'effondrer', 'emboliser', 'emmener', 'empêcher', 'encadrer', 'encourager', 'endormir', 'endurer', 'enlever', 'enregistrer', 'entamer', 'entendre', 'entourer', 'entraîner', 'entreprendre', 'entrer', 'envahir', 'envisager', 'envoyer', 'espérer', 'essayer', 'estimer', 'être', 'examiner', 'excentrer', 'exciser', 'exclure', 'expirer', 'expliquer', 'explorer', 'exposer', 'exprimer', 'extérioriser', 'exécuter', 'faciliter', 'faire', 'fatiguer', 'favoriser', 'faxer', 'fermer', 'figurer', 'fixer', 'focaliser', 'foncer', 'former', 'fournir', 'fractionner', 'fragmenter', 'fuiter', 'fusionner', 'garder', 'graver', 'guider', 'gérer', 'gêner', 'honorer', 'hopsitaliser', 'hospitaliser', 'hydrater', 'hyperartérialiser', 'hyperfixer', 'hypertrophier', 'hésiter', 'identifier', 'illustrer', 'immuniser', 'impacter', 'implanter', 'impliquer', 'importer', 'imposer', 'impregner', 'imprimer', 'inclure', 'indifferencier', 'indiquer', 'infecter', 'infertiliser', 'infiltrer', 'informer', 'inhaler', 'initier', 'injecter', 'inscrire', 'insister', 'installer', 'interdire', 'interpréter', 'interrompre', 'intervenir', 'intituler', 'introduire', 'intéragir', 'inverser', 'inviter', 'ioder', 'ioniser', 'irradier', 'itérativer', 'joindre', 'juger', 'justifier', 'laisser', 'laminer', 'lancer', 'latéraliser', 'laver', 'lever', 'lier', 'ligaturer', 'limiter', 'lire', 'localiser', 'loger', 'louper', 'luire', 'lutter', 'lyricer', 'lyser', 'maculer', 'macérer', 'maintenir', 'majorer', 'malaiser', 'manger', 'manifester', 'manipuler', 'manquer', 'marcher', 'marier', 'marmoner', 'marquer', 'masquer', 'masser', 'mater', 'mener', 'mesurer', 'meteoriser', 'mettre', 'mitiger', 'modifier', 'moduler', 'modérer', 'monter', 'montrer', 'motiver', 'moucheter', 'mouler', 'mourir', 'multiopéréer', 'munir', 'muter', 'médicaliser', 'météoriser', 'naître', 'normaliser', 'noter', 'nuire', 'numériser', 'nécessiter', 'négativer', 'objectiver', 'observer', 'obstruer', 'obtenir', 'occasionner', 'occuper', 'opposer', 'opérer', 'organiser', 'orienter', 'ouvrir', 'palper', 'parasiter', 'paraître', 'parcourir', 'parer', 'paresthésier', 'parfaire', 'partager', 'partir', 'parvenir', 'passer', 'penser', 'percevoir', 'perdre', 'perforer', 'permettre', 'persister', 'personnaliser', 'peser', 'pigmenter', 'piloter', 'placer', 'plaindre', 'planifier', 'plier', 'plonger', 'porter', 'poser', 'positionner', 'posséder', 'poursuivre', 'pousser', 'pouvoir', 'pratiquer', 'preciser', 'prendre', 'prescrire', 'prier', 'produire', 'programmer', 'prolonger', 'prononcer', 'proposer', 'prouver', 'provoquer', 'préciser', 'précéder', 'prédominer', 'préexister', 'préférer', 'prélever', 'préparer', 'présenter', 'préserver', 'prévenir', 'prévoir', 'puruler', 'pénétrer', 'radiofréquencer', 'ralentir', 'ramener', 'rappeler', 'rapporter', 'rapprocher', 'rassurer', 'rattacher', 'rattraper', 'realiser', 'recenser', 'recevoir', 'rechercher', 'recommander', 'reconnaître', 'reconsulter', 'recontacter', 'recontrôler', 'reconvoquer', 'recouvrir', 'recueillir', 'recuperer', 'redescendre', 'rediscuter', 'refaire', 'refouler', 'refuser', 'regarder', 'rehausser', 'relancer', 'relayer', 'relever', 'relire', 'relâcher', 'remanier', 'remarquer', 'remercier', 'remettre', 'remonter', 'remplacer', 'remplir', 'rencontrer', 'rendormir', 'rendre', 'renfermer', 'renforcer', 'renouveler', 'renseigner', 'rentrer', 'reparler', 'repasser', 'reporter', 'reprendre', 'represcrire', 'reproduire', 'reprogrammer', 'représenter', 'repérer', 'requérir', 'respecter', 'ressembler', 'ressentir', 'rester', 'restreindre', 'retarder', 'retenir', 'retirer', 'retrouver', 'revasculariser', 'revenir', 'reverticaliser', 'revoir', 'rompre', 'rouler', 'réadapter', 'réadmettre', 'réadresser', 'réaliser', 'récidiver', 'récupérer', 'rédiger', 'réduire', 'réessayer', 'réexpliquer', 'référer', 'régler', 'régresser', 'réhausser', 'réopérer', 'répartir', 'répondre', 'répéter', 'réserver', 'résorber', 'résoudre', 'réséquer', 'réveiller', 'révéler', 'réévaluer', 'rêver', 'sacrer', 'saisir', 'satisfaire', 'savoir', 'scanner', 'scolariser', 'sembler', 'sensibiliser', 'sentir', 'serrer', 'servir', 'sevrer', 'signaler', 'signer', 'situer', 'siéger', 'soigner', 'sommeiller', 'sonder', 'sortir', 'souffler', 'souhaiter', 'soulager', 'soussigner', 'souvenir', 'spécialiser', 'stabiliser', 'statuer', 'stenter', 'stopper', 'stratifier', 'subir', 'substituer', 'sucrer', 'suggérer', 'suivre', 'supporter', 'supprimer', 'surajouter', 'surmonter', 'surveiller', 'survenir', 'suspecter', 'suspendre', 'suturer', 'synchroniser', 'systématiser', 'sécréter', 'sécuriser', 'sédater', 'séjourner', 'séparer', 'taire', 'taper', 'teinter', 'tendre', 'tenir', 'tenter', 'terminer', 'tester', 'thromboser', 'tirer', 'tiroir', 'tissulaire', 'titulariser', 'tolérer', 'tourner', 'tracer', 'trachéotomiser', 'traduire', 'traiter', 'transcrire', 'transférer', 'transmettre', 'transporter', 'trasnfixer', 'travailler', 'tronquer', 'trouver', 'téléphoner', 'ulcérer', 'uriner', 'utiliser', 'vacciner', 'valider', 'valoir', 'varier', 'vasculariser', 'venir', 'verifier', 'vieillir', 'viser', 'visualiser', 'vivre', 'voir', 'vouloir', 'vérifier', 'ébaucher', 'écarter', 'échographier', 'échoguider', 'échoir', 'échouer', 'éclairer', 'écraser', 'élargir', 'éliminer', 'émousser', 'épaissir', 'épargner', 'épuiser', 'épurer', 'équilibrer', 'établir', 'étager', 'étendre', 'étiqueter', 'étrangler', 'évaluer', 'éviter', 'évoluer', 'évoquer', 'être'] module-attribute

hypothesis

Hypothesis

Bases: Qualifier

Hypothesis detection with spaCy.

The component looks for five kinds of expressions in the text :

• preceding hypothesis, ie cues that precede a hypothetic expression
• following hypothesis, ie cues that follow a hypothetic expression
• pseudo hypothesis : contain a hypothesis cue, but are not hypothesis (eg "pas de doute"/"no doubt")
• hypothetic verbs : verbs indicating hypothesis (eg "douter")
• classic verbs conjugated to the conditional, thus indicating hypothesis

PARAMETER	DESCRIPTION
nlp	spaCy nlp pipeline to use for matching. TYPE: Language
pseudo	List of pseudo hypothesis cues. TYPE: Optional[List[str]]
preceding	List of preceding hypothesis cues TYPE: Optional[List[str]]
following	List of following hypothesis cues. TYPE: Optional[List[str]]
verbs_hyp	List of hypothetic verbs. TYPE: Optional[List[str]]
verbs_eds	List of mainstream verbs. TYPE: Optional[List[str]]
filter_matches	Whether to filter out overlapping matches. TYPE: bool
attr	spaCy's attribute to use: a string with the value "TEXT" or "NORM", or a dict with the key 'term_attr' we can also add a key for each regex. TYPE: str
on_ents_only	Whether to look for matches around detected entities only. Useful for faster inference in downstream tasks. TYPE: bool
within_ents	Whether to consider cues within entities. TYPE: bool
explain	Whether to keep track of cues for each entity. TYPE: bool
regex	A dictionnary of regex patterns. TYPE: Optional[Dict[str, Union[List[str], str]]]

Source code in edsnlp/pipelines/qualifiers/hypothesis/hypothesis.py

class Hypothesis(Qualifier):
    """
    Hypothesis detection with spaCy.

    The component looks for five kinds of expressions in the text :

    - preceding hypothesis, ie cues that precede a hypothetic expression
    - following hypothesis, ie cues that follow a hypothetic expression
    - pseudo hypothesis : contain a hypothesis cue, but are not hypothesis
      (eg "pas de doute"/"no doubt")
    - hypothetic verbs : verbs indicating hypothesis (eg "douter")
    - classic verbs conjugated to the conditional, thus indicating hypothesis

    Parameters
    ----------
    nlp : Language
        spaCy nlp pipeline to use for matching.
    pseudo : Optional[List[str]]
        List of pseudo hypothesis cues.
    preceding : Optional[List[str]]
        List of preceding hypothesis cues
    following : Optional[List[str]]
        List of following hypothesis cues.
    verbs_hyp : Optional[List[str]]
        List of hypothetic verbs.
    verbs_eds : Optional[List[str]]
        List of mainstream verbs.
    filter_matches : bool
        Whether to filter out overlapping matches.
    attr : str
        spaCy's attribute to use:
        a string with the value "TEXT" or "NORM", or a dict with the key 'term_attr'
        we can also add a key for each regex.
    on_ents_only : bool
        Whether to look for matches around detected entities only.
        Useful for faster inference in downstream tasks.
    within_ents : bool
        Whether to consider cues within entities.
    explain : bool
        Whether to keep track of cues for each entity.
    regex : Optional[Dict[str, Union[List[str], str]]]
        A dictionnary of regex patterns.
    """

    defaults = dict(
        following=following,
        preceding=preceding,
        pseudo=pseudo,
        termination=termination,
        verbs_eds=verbs_eds,
        verbs_hyp=verbs_hyp,
    )

    def __init__(
        self,
        nlp: Language,
        attr: str,
        pseudo: Optional[List[str]],
        preceding: Optional[List[str]],
        following: Optional[List[str]],
        termination: Optional[List[str]],
        verbs_eds: Optional[List[str]],
        verbs_hyp: Optional[List[str]],
        on_ents_only: bool,
        within_ents: bool,
        explain: bool,
    ):

        terms = self.get_defaults(
            pseudo=pseudo,
            preceding=preceding,
            following=following,
            termination=termination,
            verbs_eds=verbs_eds,
            verbs_hyp=verbs_hyp,
        )
        terms["verbs"] = self.load_verbs(
            verbs_hyp=terms.pop("verbs_hyp"),
            verbs_eds=terms.pop("verbs_eds"),
        )

        super().__init__(
            nlp=nlp,
            attr=attr,
            on_ents_only=on_ents_only,
            explain=explain,
            **terms,
        )

        self.within_ents = within_ents
        self.set_extensions()

    @staticmethod
    def set_extensions() -> None:
        if not Token.has_extension("hypothesis"):
            Token.set_extension("hypothesis", default=False)

        if not Token.has_extension("hypothesis_"):
            Token.set_extension(
                "hypothesis_",
                getter=lambda token: "HYP" if token._.hypothesis else "CERT",
            )

        if not Span.has_extension("hypothesis"):
            Span.set_extension("hypothesis", default=False)

        if not Span.has_extension("hypothesis_"):
            Span.set_extension(
                "hypothesis_",
                getter=lambda span: "HYP" if span._.hypothesis else "CERT",
            )

        if not Span.has_extension("hypothesis_cues"):
            Span.set_extension("hypothesis_cues", default=[])

        if not Doc.has_extension("hypothesis"):
            Doc.set_extension("hypothesis", default=[])

    def load_verbs(
        self,
        verbs_hyp: List[str],
        verbs_eds: List[str],
    ) -> List[str]:
        """
        Conjugate "classic" verbs to conditional, and add hypothesis
        verbs conjugated to all tenses.

        Parameters
        ----------
        verbs_hyp: List of verbs that specifically imply an hypothesis.
        verbs_eds: List of general verbs.

        Returns
        -------
        list of hypothesis verbs conjugated at all tenses and classic
        verbs conjugated to conditional.
        """

        classic_verbs = get_verbs(verbs_eds)
        classic_verbs = classic_verbs.loc[classic_verbs["mode"] == "Conditionnel"]
        list_classic_verbs = list(classic_verbs["term"].unique())

        hypo_verbs = get_verbs(verbs_hyp)
        list_hypo_verbs = list(hypo_verbs["term"].unique())

        return list_hypo_verbs + list_classic_verbs

    def process(self, doc: Doc) -> Doc:
        """
        Finds entities related to hypothesis.

        Parameters
        ----------
        doc: spaCy Doc object

        Returns
        -------
        doc: spaCy Doc object, annotated for hypothesis
        """

        matches = self.get_matches(doc)

        terminations = get_spans(matches, "termination")
        boundaries = self._boundaries(doc, terminations)

        # Removes duplicate matches and pseudo-expressions in one statement
        matches = filter_spans(matches, label_to_remove="pseudo")

        entities = list(doc.ents) + list(doc.spans.get("discarded", []))
        ents = None

        for start, end in boundaries:

            ents, entities = consume_spans(
                entities,
                filter=lambda s: check_inclusion(s, start, end),
                second_chance=ents,
            )

            sub_matches, matches = consume_spans(
                matches, lambda s: start <= s.start < end
            )

            if self.on_ents_only and not ents:
                continue

            sub_preceding = get_spans(sub_matches, "preceding")
            sub_following = get_spans(sub_matches, "following")
            sub_verbs = get_spans(sub_matches, "verbs")

            if not sub_preceding + sub_following + sub_verbs:
                continue

            if not self.on_ents_only:
                for token in doc[start:end]:
                    token._.hypothesis = any(
                        m.end <= token.i for m in sub_preceding + sub_verbs
                    ) or any(m.start > token.i for m in sub_following)

            for ent in ents:

                if self.within_ents:
                    cues = [m for m in sub_preceding + sub_verbs if m.end <= ent.end]
                    cues += [m for m in sub_following if m.start >= ent.start]
                else:
                    cues = [m for m in sub_preceding + sub_verbs if m.end <= ent.start]
                    cues += [m for m in sub_following if m.start >= ent.end]

                hypothesis = ent._.hypothesis or bool(cues)

                ent._.hypothesis = hypothesis

                if self.explain and hypothesis:
                    ent._.hypothesis_cues += cues

                if not self.on_ents_only and hypothesis:
                    for token in ent:
                        token._.hypothesis = True

        return doc

defaults = dict(following=following, preceding=preceding, pseudo=pseudo, termination=termination, verbs_eds=verbs_eds, verbs_hyp=verbs_hyp) class-attribute

within_ents = within_ents instance-attribute

__init__(nlp, attr, pseudo, preceding, following, termination, verbs_eds, verbs_hyp, on_ents_only, within_ents, explain)

Source code in edsnlp/pipelines/qualifiers/hypothesis/hypothesis.py

def __init__(
    self,
    nlp: Language,
    attr: str,
    pseudo: Optional[List[str]],
    preceding: Optional[List[str]],
    following: Optional[List[str]],
    termination: Optional[List[str]],
    verbs_eds: Optional[List[str]],
    verbs_hyp: Optional[List[str]],
    on_ents_only: bool,
    within_ents: bool,
    explain: bool,
):

    terms = self.get_defaults(
        pseudo=pseudo,
        preceding=preceding,
        following=following,
        termination=termination,
        verbs_eds=verbs_eds,
        verbs_hyp=verbs_hyp,
    )
    terms["verbs"] = self.load_verbs(
        verbs_hyp=terms.pop("verbs_hyp"),
        verbs_eds=terms.pop("verbs_eds"),
    )

    super().__init__(
        nlp=nlp,
        attr=attr,
        on_ents_only=on_ents_only,
        explain=explain,
        **terms,
    )

    self.within_ents = within_ents
    self.set_extensions()

set_extensions()

Source code in edsnlp/pipelines/qualifiers/hypothesis/hypothesis.py

@staticmethod
def set_extensions() -> None:
    if not Token.has_extension("hypothesis"):
        Token.set_extension("hypothesis", default=False)

    if not Token.has_extension("hypothesis_"):
        Token.set_extension(
            "hypothesis_",
            getter=lambda token: "HYP" if token._.hypothesis else "CERT",
        )

    if not Span.has_extension("hypothesis"):
        Span.set_extension("hypothesis", default=False)

    if not Span.has_extension("hypothesis_"):
        Span.set_extension(
            "hypothesis_",
            getter=lambda span: "HYP" if span._.hypothesis else "CERT",
        )

    if not Span.has_extension("hypothesis_cues"):
        Span.set_extension("hypothesis_cues", default=[])

    if not Doc.has_extension("hypothesis"):
        Doc.set_extension("hypothesis", default=[])

load_verbs(verbs_hyp, verbs_eds)

Conjugate "classic" verbs to conditional, and add hypothesis verbs conjugated to all tenses.

PARAMETER	DESCRIPTION
verbs_hyp	TYPE: List[str]
verbs_eds	TYPE: List[str]

RETURNS	DESCRIPTION
list of hypothesis verbs conjugated at all tenses and classic
verbs conjugated to conditional.

Source code in edsnlp/pipelines/qualifiers/hypothesis/hypothesis.py

def load_verbs(
    self,
    verbs_hyp: List[str],
    verbs_eds: List[str],
) -> List[str]:
    """
    Conjugate "classic" verbs to conditional, and add hypothesis
    verbs conjugated to all tenses.

    Parameters
    ----------
    verbs_hyp: List of verbs that specifically imply an hypothesis.
    verbs_eds: List of general verbs.

    Returns
    -------
    list of hypothesis verbs conjugated at all tenses and classic
    verbs conjugated to conditional.
    """

    classic_verbs = get_verbs(verbs_eds)
    classic_verbs = classic_verbs.loc[classic_verbs["mode"] == "Conditionnel"]
    list_classic_verbs = list(classic_verbs["term"].unique())

    hypo_verbs = get_verbs(verbs_hyp)
    list_hypo_verbs = list(hypo_verbs["term"].unique())

    return list_hypo_verbs + list_classic_verbs

process(doc)

Finds entities related to hypothesis.

PARAMETER	DESCRIPTION
doc	TYPE: Doc

RETURNS	DESCRIPTION
doc

Source code in edsnlp/pipelines/qualifiers/hypothesis/hypothesis.py

def process(self, doc: Doc) -> Doc:
    """
    Finds entities related to hypothesis.

    Parameters
    ----------
    doc: spaCy Doc object

    Returns
    -------
    doc: spaCy Doc object, annotated for hypothesis
    """

    matches = self.get_matches(doc)

    terminations = get_spans(matches, "termination")
    boundaries = self._boundaries(doc, terminations)

    # Removes duplicate matches and pseudo-expressions in one statement
    matches = filter_spans(matches, label_to_remove="pseudo")

    entities = list(doc.ents) + list(doc.spans.get("discarded", []))
    ents = None

    for start, end in boundaries:

        ents, entities = consume_spans(
            entities,
            filter=lambda s: check_inclusion(s, start, end),
            second_chance=ents,
        )

        sub_matches, matches = consume_spans(
            matches, lambda s: start <= s.start < end
        )

        if self.on_ents_only and not ents:
            continue

        sub_preceding = get_spans(sub_matches, "preceding")
        sub_following = get_spans(sub_matches, "following")
        sub_verbs = get_spans(sub_matches, "verbs")

        if not sub_preceding + sub_following + sub_verbs:
            continue

        if not self.on_ents_only:
            for token in doc[start:end]:
                token._.hypothesis = any(
                    m.end <= token.i for m in sub_preceding + sub_verbs
                ) or any(m.start > token.i for m in sub_following)

        for ent in ents:

            if self.within_ents:
                cues = [m for m in sub_preceding + sub_verbs if m.end <= ent.end]
                cues += [m for m in sub_following if m.start >= ent.start]
            else:
                cues = [m for m in sub_preceding + sub_verbs if m.end <= ent.start]
                cues += [m for m in sub_following if m.start >= ent.end]

            hypothesis = ent._.hypothesis or bool(cues)

            ent._.hypothesis = hypothesis

            if self.explain and hypothesis:
                ent._.hypothesis_cues += cues

            if not self.on_ents_only and hypothesis:
                for token in ent:
                    token._.hypothesis = True

    return doc

factory

DEFAULT_CONFIG = dict(pseudo=None, preceding=None, following=None, termination=None, verbs_hyp=None, verbs_eds=None, attr='NORM', on_ents_only=True, within_ents=False, explain=False) module-attribute

create_component(nlp, name, attr, pseudo, preceding, following, termination, verbs_eds, verbs_hyp, on_ents_only, within_ents, explain)

Source code in edsnlp/pipelines/qualifiers/hypothesis/factory.py

@deprecated_factory("hypothesis", "eds.hypothesis", default_config=DEFAULT_CONFIG)
@Language.factory("eds.hypothesis", default_config=DEFAULT_CONFIG)
def create_component(
    nlp: Language,
    name: str,
    attr: str,
    pseudo: Optional[List[str]],
    preceding: Optional[List[str]],
    following: Optional[List[str]],
    termination: Optional[List[str]],
    verbs_eds: Optional[List[str]],
    verbs_hyp: Optional[List[str]],
    on_ents_only: bool,
    within_ents: bool,
    explain: bool,
):
    return Hypothesis(
        nlp=nlp,
        attr=attr,
        pseudo=pseudo,
        preceding=preceding,
        following=following,
        termination=termination,
        verbs_eds=verbs_eds,
        verbs_hyp=verbs_hyp,
        on_ents_only=on_ents_only,
        within_ents=within_ents,
        explain=explain,
    )