Merge pull request #237 from igor0/blimp

Add BLiMP

lm_eval/tasks/__init__.py

@@ -44,6 +44,7 @@ from . import wikitext
 from . import lambada_multilingual
 from . import mutual
 from . import truthfulqa
+from . import blimp
 
 ########################################
 # Translation tasks
@@ -217,6 +218,74 @@ TASK_REGISTRY = {
     "pile_wikipedia": pile.PileWikipedia,
     "pile_youtubesubtitles": pile.PileYoutubeSubtitles,
     
+    # BLiMP
+    "blimp_adjunct_island": blimp.BlimpAdjunctIsland,
+    "blimp_anaphor_gender_agreement": blimp.BlimpAnaphorGenderAgreement,
+    "blimp_anaphor_number_agreement": blimp.BlimpAnaphorNumberAgreement,
+    "blimp_animate_subject_passive": blimp.BlimpAnimateSubjectPassive,
+    "blimp_animate_subject_trans": blimp.BlimpAnimateSubjectTrans,
+    "blimp_causative": blimp.BlimpCausative,
+    "blimp_complex_NP_island": blimp.BlimpComplex_NPIsland,
+    "blimp_coordinate_structure_constraint_complex_left_branch": blimp.BlimpCoordinateStructureConstraintComplexLeftBranch,
+    "blimp_coordinate_structure_constraint_object_extraction": blimp.BlimpCoordinateStructureConstraintObjectExtraction,
+    "blimp_determiner_noun_agreement_1": blimp.BlimpDeterminerNounAgreement_1,
+    "blimp_determiner_noun_agreement_2": blimp.BlimpDeterminerNounAgreement_2,
+    "blimp_determiner_noun_agreement_irregular_1": blimp.BlimpDeterminerNounAgreementIrregular_1,
+    "blimp_determiner_noun_agreement_irregular_2": blimp.BlimpDeterminerNounAgreementIrregular_2,
+    "blimp_determiner_noun_agreement_with_adj_2": blimp.BlimpDeterminerNounAgreementWithAdj_2,
+    "blimp_determiner_noun_agreement_with_adj_irregular_1": blimp.BlimpDeterminerNounAgreementWithAdjIrregular_1,
+    "blimp_determiner_noun_agreement_with_adj_irregular_2": blimp.BlimpDeterminerNounAgreementWithAdjIrregular_2,
+    "blimp_determiner_noun_agreement_with_adjective_1": blimp.BlimpDeterminerNounAgreementWithAdjective_1,
+    "blimp_distractor_agreement_relational_noun": blimp.BlimpDistractorAgreementRelationalNoun,
+    "blimp_distractor_agreement_relative_clause": blimp.BlimpDistractorAgreementRelativeClause,
+    "blimp_drop_argument": blimp.BlimpDropArgument,
+    "blimp_ellipsis_n_bar_1": blimp.BlimpEllipsisNBar_1,
+    "blimp_ellipsis_n_bar_2": blimp.BlimpEllipsisNBar_2,
+    "blimp_existential_there_object_raising": blimp.BlimpExistentialThereObjectRaising,
+    "blimp_existential_there_quantifiers_1": blimp.BlimpExistentialThereQuantifiers_1,
+    "blimp_existential_there_quantifiers_2": blimp.BlimpExistentialThereQuantifiers_2,
+    "blimp_existential_there_subject_raising": blimp.BlimpExistentialThereSubjectRaising,
+    "blimp_expletive_it_object_raising": blimp.BlimpExpletiveItObjectRaising,
+    "blimp_inchoative": blimp.BlimpInchoative,
+    "blimp_intransitive": blimp.BlimpIntransitive,
+    "blimp_irregular_past_participle_adjectives": blimp.BlimpIrregularPastParticipleAdjectives,
+    "blimp_irregular_past_participle_verbs": blimp.BlimpIrregularPastParticipleVerbs,
+    "blimp_irregular_plural_subject_verb_agreement_1": blimp.BlimpIrregularPluralSubjectVerbAgreement_1,
+    "blimp_irregular_plural_subject_verb_agreement_2": blimp.BlimpIrregularPluralSubjectVerbAgreement_2,
+    "blimp_left_branch_island_echo_question": blimp.BlimpLeftBranchIslandEchoQuestion,
+    "blimp_left_branch_island_simple_question": blimp.BlimpLeftBranchIslandSimpleQuestion,
+    "blimp_matrix_question_npi_licensor_present": blimp.BlimpMatrixQuestionNpiLicensorPresent,
+    "blimp_npi_present_1": blimp.BlimpNpiPresent_1,
+    "blimp_npi_present_2": blimp.BlimpNpiPresent_2,
+    "blimp_only_npi_licensor_present": blimp.BlimpOnlyNpiLicensorPresent,
+    "blimp_only_npi_scope": blimp.BlimpOnlyNpiScope,
+    "blimp_passive_1": blimp.BlimpPassive_1,
+    "blimp_passive_2": blimp.BlimpPassive_2,
+    "blimp_principle_A_c_command": blimp.BlimpPrinciple_ACCommand,
+    "blimp_principle_A_case_1": blimp.BlimpPrinciple_ACase_1,
+    "blimp_principle_A_case_2": blimp.BlimpPrinciple_ACase_2,
+    "blimp_principle_A_domain_1": blimp.BlimpPrinciple_ADomain_1,
+    "blimp_principle_A_domain_2": blimp.BlimpPrinciple_ADomain_2,
+    "blimp_principle_A_domain_3": blimp.BlimpPrinciple_ADomain_3,
+    "blimp_principle_A_reconstruction": blimp.BlimpPrinciple_AReconstruction,
+    "blimp_regular_plural_subject_verb_agreement_1": blimp.BlimpRegularPluralSubjectVerbAgreement_1,
+    "blimp_regular_plural_subject_verb_agreement_2": blimp.BlimpRegularPluralSubjectVerbAgreement_2,
+    "blimp_sentential_negation_npi_licensor_present": blimp.BlimpSententialNegationNpiLicensorPresent,
+    "blimp_sentential_negation_npi_scope": blimp.BlimpSententialNegationNpiScope,
+    "blimp_sentential_subject_island": blimp.BlimpSententialSubjectIsland,
+    "blimp_superlative_quantifiers_1": blimp.BlimpSuperlativeQuantifiers_1,
+    "blimp_superlative_quantifiers_2": blimp.BlimpSuperlativeQuantifiers_2,
+    "blimp_tough_vs_raising_1": blimp.BlimpToughVsRaising_1,
+    "blimp_tough_vs_raising_2": blimp.BlimpToughVsRaising_2,
+    "blimp_transitive": blimp.BlimpTransitive,
+    "blimp_wh_island": blimp.BlimpWhIsland,
+    "blimp_wh_questions_object_gap": blimp.BlimpWhQuestionsObjectGap,
+    "blimp_wh_questions_subject_gap": blimp.BlimpWhQuestionsSubjectGap,
+    "blimp_wh_questions_subject_gap_long_distance": blimp.BlimpWhQuestionsSubjectGapLongDistance,
+    "blimp_wh_vs_that_no_gap": blimp.BlimpWhVsThatNoGap,
+    "blimp_wh_vs_that_no_gap_long_distance": blimp.BlimpWhVsThatNoGapLongDistance,
+    "blimp_wh_vs_that_with_gap": blimp.BlimpWhVsThatWithGap,
+    "blimp_wh_vs_that_with_gap_long_distance": blimp.BlimpWhVsThatWithGapLongDistance,
 }
 
 

lm_eval/tasks/blimp.py

+"""
+BLiMP: A Benchmark of Linguistic Minimal Pairs for English
+https://arxiv.org/abs/1912.00582
+
+@article{warstadt2019blimp,
+  title={BLiMP: A Benchmark of Linguistic Minimal Pairs for English},
+  author={Warstadt, Alex and Parrish, Alicia and Liu, Haokun and Mohananey, Anhad and Peng, Wei, and Wang, Sheng-Fu and Bowman, Samuel R},
+  journal={arXiv preprint arXiv:1912.00582},
+  year={2019}
+}
+"""
+
+from lm_eval.base import rf
+from lm_eval.metrics import mean
+from .common import HFTask
+
+
+class BlimpTask(HFTask):
+    VERSION = 0
+    DATASET_PATH = "blimp"
+
+    def download(self):
+        super().download()
+
+        # The HF dataset only contains a "train" dataset, but the harness expects a "validation"
+        # dataset. Let's use the training dataset, on the assumption that the model wasn't actually
+        # trained on this data.
+
+        self.data["validation"] = self.data["train"]
+        del self.data["train"]
+
+    def fewshot_context(self, doc, num_fewshot, provide_description, rnd):
+        assert num_fewshot == 0
+        assert not provide_description
+        return ""
+
+    def doc_to_text(self, doc):
+        # this method is invoked by tests only
+        return ""
+
+    def doc_to_target(self, doc):
+        # this method is invoked by tests only
+        return ""
+
+    def construct_requests(self, doc, ctx):
+        assert not ctx
+
+        # Calculate the loglikelihood for the good and the bad sentence.
+        # Note that loglikelihood translates the "" prefix to the "<|endoftext|>" token
+        return [
+            rf.loglikelihood("", doc["sentence_good"]),
+            rf.loglikelihood("", doc["sentence_bad"]),
+        ]
+
+    def process_results(self, doc, results):
+        likelihood1, likelihood2 = results
+
+        # the model got this case right iff the good sentence scored higher than the bad sentence
+        acc = 1.0 if likelihood1 > likelihood2 else 0.0
+
+        return {
+            "acc": acc,
+        }
+
+    def higher_is_better(self):
+        return {
+            "acc": True,
+        }
+
+    def aggregation(self):
+        return {
+            "acc": mean,
+        }
+
+
+class BlimpAdjunctIsland(BlimpTask):
+    DATASET_NAME = "adjunct_island"
+
+
+class BlimpAnaphorGenderAgreement(BlimpTask):
+    DATASET_NAME = "anaphor_gender_agreement"
+
+
+class BlimpAnaphorNumberAgreement(BlimpTask):
+    DATASET_NAME = "anaphor_number_agreement"
+
+
+class BlimpAnimateSubjectPassive(BlimpTask):
+    DATASET_NAME = "animate_subject_passive"
+
+
+class BlimpAnimateSubjectTrans(BlimpTask):
+    DATASET_NAME = "animate_subject_trans"
+
+
+class BlimpCausative(BlimpTask):
+    DATASET_NAME = "causative"
+
+
+class BlimpComplex_NPIsland(BlimpTask):
+    DATASET_NAME = "complex_NP_island"
+
+
+class BlimpCoordinateStructureConstraintComplexLeftBranch(BlimpTask):
+    DATASET_NAME = "coordinate_structure_constraint_complex_left_branch"
+
+
+class BlimpCoordinateStructureConstraintObjectExtraction(BlimpTask):
+    DATASET_NAME = "coordinate_structure_constraint_object_extraction"
+
+
+class BlimpDeterminerNounAgreement_1(BlimpTask):
+    DATASET_NAME = "determiner_noun_agreement_1"
+
+
+class BlimpDeterminerNounAgreement_2(BlimpTask):
+    DATASET_NAME = "determiner_noun_agreement_2"
+
+
+class BlimpDeterminerNounAgreementIrregular_1(BlimpTask):
+    DATASET_NAME = "determiner_noun_agreement_irregular_1"
+
+
+class BlimpDeterminerNounAgreementIrregular_2(BlimpTask):
+    DATASET_NAME = "determiner_noun_agreement_irregular_2"
+
+
+class BlimpDeterminerNounAgreementWithAdj_2(BlimpTask):
+    DATASET_NAME = "determiner_noun_agreement_with_adj_2"
+
+
+class BlimpDeterminerNounAgreementWithAdjIrregular_1(BlimpTask):
+    DATASET_NAME = "determiner_noun_agreement_with_adj_irregular_1"
+
+
+class BlimpDeterminerNounAgreementWithAdjIrregular_2(BlimpTask):
+    DATASET_NAME = "determiner_noun_agreement_with_adj_irregular_2"
+
+
+class BlimpDeterminerNounAgreementWithAdjective_1(BlimpTask):
+    DATASET_NAME = "determiner_noun_agreement_with_adjective_1"
+
+
+class BlimpDistractorAgreementRelationalNoun(BlimpTask):
+    DATASET_NAME = "distractor_agreement_relational_noun"
+
+
+class BlimpDistractorAgreementRelativeClause(BlimpTask):
+    DATASET_NAME = "distractor_agreement_relative_clause"
+
+
+class BlimpDropArgument(BlimpTask):
+    DATASET_NAME = "drop_argument"
+
+
+class BlimpEllipsisNBar_1(BlimpTask):
+    DATASET_NAME = "ellipsis_n_bar_1"
+
+
+class BlimpEllipsisNBar_2(BlimpTask):
+    DATASET_NAME = "ellipsis_n_bar_2"
+
+
+class BlimpExistentialThereObjectRaising(BlimpTask):
+    DATASET_NAME = "existential_there_object_raising"
+
+
+class BlimpExistentialThereQuantifiers_1(BlimpTask):
+    DATASET_NAME = "existential_there_quantifiers_1"
+
+
+class BlimpExistentialThereQuantifiers_2(BlimpTask):
+    DATASET_NAME = "existential_there_quantifiers_2"
+
+
+class BlimpExistentialThereSubjectRaising(BlimpTask):
+    DATASET_NAME = "existential_there_subject_raising"
+
+
+class BlimpExpletiveItObjectRaising(BlimpTask):
+    DATASET_NAME = "expletive_it_object_raising"
+
+
+class BlimpInchoative(BlimpTask):
+    DATASET_NAME = "inchoative"
+
+
+class BlimpIntransitive(BlimpTask):
+    DATASET_NAME = "intransitive"
+
+
+class BlimpIrregularPastParticipleAdjectives(BlimpTask):
+    DATASET_NAME = "irregular_past_participle_adjectives"
+
+
+class BlimpIrregularPastParticipleVerbs(BlimpTask):
+    DATASET_NAME = "irregular_past_participle_verbs"
+
+
+class BlimpIrregularPluralSubjectVerbAgreement_1(BlimpTask):
+    DATASET_NAME = "irregular_plural_subject_verb_agreement_1"
+
+
+class BlimpIrregularPluralSubjectVerbAgreement_2(BlimpTask):
+    DATASET_NAME = "irregular_plural_subject_verb_agreement_2"
+
+
+class BlimpLeftBranchIslandEchoQuestion(BlimpTask):
+    DATASET_NAME = "left_branch_island_echo_question"
+
+
+class BlimpLeftBranchIslandSimpleQuestion(BlimpTask):
+    DATASET_NAME = "left_branch_island_simple_question"
+
+
+class BlimpMatrixQuestionNpiLicensorPresent(BlimpTask):
+    DATASET_NAME = "matrix_question_npi_licensor_present"
+
+
+class BlimpNpiPresent_1(BlimpTask):
+    DATASET_NAME = "npi_present_1"
+
+
+class BlimpNpiPresent_2(BlimpTask):
+    DATASET_NAME = "npi_present_2"
+
+
+class BlimpOnlyNpiLicensorPresent(BlimpTask):
+    DATASET_NAME = "only_npi_licensor_present"
+
+
+class BlimpOnlyNpiScope(BlimpTask):
+    DATASET_NAME = "only_npi_scope"
+
+
+class BlimpPassive_1(BlimpTask):
+    DATASET_NAME = "passive_1"
+
+
+class BlimpPassive_2(BlimpTask):
+    DATASET_NAME = "passive_2"
+
+
+class BlimpPrinciple_ACCommand(BlimpTask):
+    DATASET_NAME = "principle_A_c_command"
+
+
+class BlimpPrinciple_ACase_1(BlimpTask):
+    DATASET_NAME = "principle_A_case_1"
+
+
+class BlimpPrinciple_ACase_2(BlimpTask):
+    DATASET_NAME = "principle_A_case_2"
+
+
+class BlimpPrinciple_ADomain_1(BlimpTask):
+    DATASET_NAME = "principle_A_domain_1"
+
+
+class BlimpPrinciple_ADomain_2(BlimpTask):
+    DATASET_NAME = "principle_A_domain_2"
+
+
+class BlimpPrinciple_ADomain_3(BlimpTask):
+    DATASET_NAME = "principle_A_domain_3"
+
+
+class BlimpPrinciple_AReconstruction(BlimpTask):
+    DATASET_NAME = "principle_A_reconstruction"
+
+
+class BlimpRegularPluralSubjectVerbAgreement_1(BlimpTask):
+    DATASET_NAME = "regular_plural_subject_verb_agreement_1"
+
+
+class BlimpRegularPluralSubjectVerbAgreement_2(BlimpTask):
+    DATASET_NAME = "regular_plural_subject_verb_agreement_2"
+
+
+class BlimpSententialNegationNpiLicensorPresent(BlimpTask):
+    DATASET_NAME = "sentential_negation_npi_licensor_present"
+
+
+class BlimpSententialNegationNpiScope(BlimpTask):
+    DATASET_NAME = "sentential_negation_npi_scope"
+
+
+class BlimpSententialSubjectIsland(BlimpTask):
+    DATASET_NAME = "sentential_subject_island"
+
+
+class BlimpSuperlativeQuantifiers_1(BlimpTask):
+    DATASET_NAME = "superlative_quantifiers_1"
+
+
+class BlimpSuperlativeQuantifiers_2(BlimpTask):
+    DATASET_NAME = "superlative_quantifiers_2"
+
+
+class BlimpToughVsRaising_1(BlimpTask):
+    DATASET_NAME = "tough_vs_raising_1"
+
+
+class BlimpToughVsRaising_2(BlimpTask):
+    DATASET_NAME = "tough_vs_raising_2"
+
+
+class BlimpTransitive(BlimpTask):
+    DATASET_NAME = "transitive"
+
+
+class BlimpWhIsland(BlimpTask):
+    DATASET_NAME = "wh_island"
+
+
+class BlimpWhQuestionsObjectGap(BlimpTask):
+    DATASET_NAME = "wh_questions_object_gap"
+
+
+class BlimpWhQuestionsSubjectGap(BlimpTask):
+    DATASET_NAME = "wh_questions_subject_gap"
+
+
+class BlimpWhQuestionsSubjectGapLongDistance(BlimpTask):
+    DATASET_NAME = "wh_questions_subject_gap_long_distance"
+
+
+class BlimpWhVsThatNoGap(BlimpTask):
+    DATASET_NAME = "wh_vs_that_no_gap"
+
+
+class BlimpWhVsThatNoGapLongDistance(BlimpTask):
+    DATASET_NAME = "wh_vs_that_no_gap_long_distance"
+
+
+class BlimpWhVsThatWithGap(BlimpTask):
+    DATASET_NAME = "wh_vs_that_with_gap"
+
+
+class BlimpWhVsThatWithGapLongDistance(BlimpTask):
+    DATASET_NAME = "wh_vs_that_with_gap_long_distance"

tests/tests/testdata/blimp_adjunct_island-v0-loglikelihood

+976a5cac4bdb724632eebd4cb9e522203ce3da8d5525288a597c86e80469f3f2
\ No newline at end of file

tests/tests/testdata/blimp_adjunct_island-v0-res.json

+{"results": {"blimp_adjunct_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_adjunct_island": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_anaphor_gender_agreement-v0-loglikelihood

+2d8964e56a17661502ecf3f09c0befba63915360ddf2145b0bd845816950515d
\ No newline at end of file

tests/tests/testdata/blimp_anaphor_gender_agreement-v0-res.json

+{"results": {"blimp_anaphor_gender_agreement": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_anaphor_gender_agreement": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_anaphor_number_agreement-v0-loglikelihood

+0bdad31c974ba064e1f1ba931841ec2ba7461e8b0ca54ea5f79f08b6bae0bab5
\ No newline at end of file

tests/tests/testdata/blimp_anaphor_number_agreement-v0-res.json

+{"results": {"blimp_anaphor_number_agreement": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_anaphor_number_agreement": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_animate_subject_passive-v0-loglikelihood

+064c38fcd072b8bd12f54ea4f8e41599ed4e11dc386e93b77e1fc07967d1f960
\ No newline at end of file

tests/tests/testdata/blimp_animate_subject_passive-v0-res.json

+{"results": {"blimp_animate_subject_passive": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_animate_subject_passive": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_animate_subject_trans-v0-loglikelihood

+2a84231e7b79f517427e57e2099c88fed3d60a7efab4ef9506e263b4091d5cfa
\ No newline at end of file

tests/tests/testdata/blimp_animate_subject_trans-v0-res.json

+{"results": {"blimp_animate_subject_trans": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_animate_subject_trans": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_causative-v0-loglikelihood

+3d67ad025185dbb0808ebd7f508edcb5750c18fc3c01ad91f20fda80780c916c
\ No newline at end of file

tests/tests/testdata/blimp_causative-v0-res.json

+{"results": {"blimp_causative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_causative": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_complex_NP_island-v0-loglikelihood

+f46cfcc7e43050a235fd2a6b989cabbfbcce76786df74db9f0d4a9cd1caa1628
\ No newline at end of file

tests/tests/testdata/blimp_complex_NP_island-v0-res.json

+{"results": {"blimp_complex_NP_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_complex_NP_island": 0}}
\ No newline at end of file

tests/tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-loglikelihood

+7e1cc5b9f71abfbe56c4bdf343a1e5632785b66a986b8e904a41ed8f45a2c33e
\ No newline at end of file

tests/tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-res.json

+{"results": {"blimp_coordinate_structure_constraint_complex_left_branch": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_coordinate_structure_constraint_complex_left_branch": 0}}
\ No newline at end of file