Using Thematic Information In Statistical Headline Generation

نویسندگان

  • Stephen Wan
  • Mark Dras
  • Cécile L. Paris
  • Robert Dale
چکیده

We explore the problem of single sentence summarisation. In the news domain, such a summary might resemble a headline. The headline generation system we present uses Singular Value Decomposition (SVD) to guide the generation of a headline towards the theme that best represents the document to be summarised. In doing so, the intuition is that the generated summary will more accurately reflect the content of the source document. This paper presents SVD as an alternative method to determine if a word is a suitable candidate for inclusion in the headline. The results of a recall based evaluation comparing three different strategies to word selection, indicate that thematic information does help improve recall.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Machine Learning Approach to Augmenting News Headline Generation

In this paper, we present the HybridTrim system which uses a machine learning technique to combine linguistic, statistical and positional information to identify topic labels for headlines in a text. We compare our system with the Topiary system which, in contrast, uses a statistical learning approach to finding topic descriptors for headlines. The Topiary system, developed at the University of...

متن کامل

Headline Generation for Written and Broadcast News

This technical report is an overview of work done on Headline Generation for written and broadcast news. The report covers HMM Hedge, a statistical approach based on the noisy channel model, Hedge Trimmer, a parse-andtrim approach using linguistically motivated trimming rules, and Topiary, a combination of Trimmer and Unsupervised Topic Discovery. Automatic evaluation of summaries using ROUGE a...

متن کامل

Conceptual Multi-layer Neural Network Model for Headline Generation

Neural attention-based models have been widely used recently in headline generation by mapping source document to target headline. However, the traditional neural headline generation models utilize the first sentence of the document as the training input while ignoring the impact of the document concept information on headline generation. In this work, A new neural attention-based model called ...

متن کامل

Improved Algorithms For Keyword Extraction and Headline Generation From Unstructured Text

The problem of generating headlines for documents using purely statistical approach has been long standing. We describe here an improved extractive approach based on keywords. The insight here is that if one tries to summarize a document, one will invariably use keywords from the document itself. There are two aspects to the problem namely, finding the relevant set of keywords and finding the p...

متن کامل

From Neural Sentence Summarization to Headline Generation: A Coarse-to-Fine Approach

Headline generation is a task of abstractive text summarization, and previously suffers from the immaturity of natural language generation techniques. Recent success of neural sentence summarization models shows the capacity of generating informative, fluent headlines conditioned on selected recapitulative sentences. In this paper, we investigate the extension of sentence summarization models t...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2003