عنوان

Query Focused Abstractive Summarization Using BERTSUM Model

Number

TL53912

.Language of Text, Soundtrack etc

انگلیسی

Title Proper

Query Focused Abstractive Summarization Using BERTSUM Model

General Material Designation

[Thesis]

First Statement of Responsibility

Abdullah, Deen Mohammad

Subsequent Statement of Responsibility

Chali, Yllias

Name of Publisher, Distributor, etc.

University of Lethbridge (Canada)

Date of Publication, Distribution, etc.

2020

Text of Note

78 p.

Dissertation or thesis details and type of degree

M.Sc.

Body granting the degree

University of Lethbridge (Canada)

Text preceding or following the note

2020

Text of Note

In Natural Language Processing, researchers find many challenges on Query Focused Abstractive Summarization (QFAS), where Bidirectional Encoder Representations from Transformers for Summarization (BERTSUM) can be used for both extractive and abstractive summarization. As there is few available datasets for QFAS, we have generated queries for two publicly available datasets, CNN/Daily Mail and Newsroom, according to the context of the documents and summaries. To generate abstractive summaries, we have applied two different approaches, which are Query focused Abstractive and Query focused Extractive then Abstractive summarizations. In the first approach, we have sorted the sentences of the documents from the most query-related sentences to the less query-related sentences, and in the second approach, we have extracted only the query related sentences to fine-tune the BERTSUM model. Our experimental results show that both of our approaches show good results on ROUGE metric for CNN/Daily Mail and Newsroom datasets.

Subject Term

Artificial intelligence

Subject Term

Computer science

Subject Term

Engineering

Abdullah, Deen Mohammad

Chali, Yllias

University of Lethbridge (Canada)

Electronic name

p

[Thesis]

276903

a

Y