import gensim
from gensim.utils import simple_preprocess

def sent_to_words(sentences):
    for sentence in sentences:
        yield(gensim.utils.simple_preprocess(str(sentence), deacc=True))  # deacc=True removes punctuations

data = papers.paper_text_processed.values.tolist()
data_words = list(sent_to_words(data))

print(data_words[:1][0][:30])