Financial News Summarization (Headers, Large)

Description

This model is a Financial news Summarizer, aimed to extract headers from financial news. This is a lg (large) version. Other versions may be found in Models Hub.

Predicted Entities

Copy S3 URI

How to use

document_assembler = nlp.DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("documents")

t5 = nlp.T5Transformer() \
    .pretrained("finsum_news_headers_lg" ,"en", "finance/models") \
    .setTask("summarization") \
    .setInputCols(["documents"]) \
    .setMaxOutputLength(512) \
    .setOutputCol("summaries")
    
data_df = spark.createDataFrame([["FTX is expected to make its debut appearance Tuesday in Delaware bankruptcy court, where its new management is expected to recount events leading up to the cryptocurrency platform’s sudden collapse and explain the steps it has since taken to secure customer funds and other assets."]]).toDF("text")

pipeline = nlp.Pipeline().setStages([document_assembler, t5])
results = pipeline.fit(data_df).transform(data_df)
results.select("summaries.result").show(truncate=False)

Results

FTX to Make Debut in Delaware Bankruptcy Court Tuesday.

Model Information

Model Name: finsum_news_headers_lg
Compatibility: Finance NLP 1.0.0+
License: Licensed
Edition: Official
Input Labels: [documents]
Output Labels: [summaries]
Language: en
Size: 925.6 MB

References

In-house JSL financial summarized news.