'loves', 'hates', 'likes', 'smells', 'touches', 'pushes', 'moves', 'sees',
'lifts', 'hits'
]
if __name__ == "__main__":
np.random.seed(seed=9)
random.seed(9)
# Preprocess Corpus
glove_list, bert_list = RSA.preprocess_data('./head_adj_trans_corpus.txt')
print("data processed")
# Generate glove hypothesis models
embed_dict = RSA.get_glove_embeds(
glove_list, "../../glove_utils/glove/glove.6B.300d.txt", 300,
lexical_idxs, verb_list)
adj1 = np.array(embed_dict[lexical_idxs[0]])
subj = np.array(embed_dict[lexical_idxs[1]])
verb = np.array(embed_dict[lexical_idxs[2]])
adj2 = np.array(embed_dict[lexical_idxs[3]])
obj = np.array(embed_dict[lexical_idxs[4]])
rand_verb = np.array(embed_dict[-1])
print("glove embeds generated")
# Generate BERT reference model
bert_embeds = RSA.get_bert_embeds(bert_list, 0)
print("BERT embeds generated")
rsa_subj_dist = []
rsa_obj_dist = []
'tables', 'doors', 'windows', 'planes', 'cars', 'trucks'
]
if __name__ == "__main__":
np.random.seed(seed=9)
random.seed(9)
# Preprocess corpus
glove_list, bert_list = RSA.preprocess_data('./copula_PP_corpus.txt',
noun_list)
print("data processed")
# Get dictionary of Glove embedding hypothesis models
embed_dict = RSA.get_glove_embeds(
glove_list, "../../glove_utils/glove/glove.6B.300d.txt", 300,
noun_idxs, noun_list, verb_idx)
glove_subj = np.array(embed_dict[noun_idxs[0]])
glove_nonarg = np.array(embed_dict[noun_idxs[1]])
glove_rand = np.array(embed_dict[-1])
print("glove embeds generated")
# Get BERT embedding reference models
bert_embeds = RSA.get_bert_embeds(bert_list, verb_idx + 1)
print("BERT embeds generated")
rsa_subj_dist = []
rsa_nonarg_dist = []
rsa_rand_dist = []
samples = []