Headline generation based on statistical translation

Banko, Michele; Mittal, Vibhu O.; Witbrock, Michael

doi:10.3115/1075218.1075259

Cited by 184 publications

(151 citation statements)

References 19 publications

Supporting

Mentioning

144

Contrasting

Unclassified

Order By: Relevance

“…The first statistical framework for Automatic title generation was proposed by Banko, Mittal and Witbrock [11]. In this paper, we refer it as the 'BMW model'.…”

Section: Bmw Model For Title Generationmentioning

confidence: 99%

Analysis of BMW Model for Title Word Selection on Indic Script

Reddy¹,

Vardhan²,

Govardhan³

2011

IJCA

View full text Add to dashboard Cite

A title is a short summary that represents document's main theme. Title can help the reader to have the main idea without reading the entire document. To generate a title for a document, we have to select appropriate words as title words and put them in sequence. The process of generating title for a given document by using machine, can be done by using summarization approaches or by using Statistical approaches or by combing both. For a given document, selecting appropriate words for generating a title by using any available approach mainly depends on the characteristics of the language. In this paper ,we have examined the influence of the language characteristics in the process of title word selection by using the Naïve Bayes probabilistic approach ( called BMW Model ) on the documents which are available in the language ' Telugu '. And also we have investigated the influence of word weight for the selection of title words in BMW Model. By using F1 metric, we have evaluated the title word selection process.

show abstract

“…The first statistical framework for Automatic title generation was proposed by Banko, Mittal and Witbrock [11]. In this paper, we refer it as the 'BMW model'.…”

Section: Bmw Model For Title Generationmentioning

confidence: 99%

Analysis of BMW Model for Title Word Selection on Indic Script

Reddy¹,

Vardhan²,

Govardhan³

2011

IJCA

View full text Add to dashboard Cite

show abstract

“…It involves indentifying interest words in the text, and combining them into the title [20]. Therefore, the feature set for this model should capture selection constraints at the word level, and the contextual constraints at the word sequence level.…”

Section: Local Featuresmentioning

confidence: 99%

Learning to Generate a Table-of-Contents with Supportive Knowledge

Nguyen

Shimazu

2011

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn the text summarization field, a table-of-contents is a type of indicative summary that is especially suited for locating information in a long document, or a set of documents. It is also a useful summary for a reader to quickly get an overview of the entire contents. The current models for generating a table-of-contents produced relatively low quality output with many meaningless titles, or titles that have no overlapping meaning with the corresponding contents. This problem may be due to the lack of semantic information and topic information in those models. In this research, we propose to integrate supportive knowledge into the learning models to improve the quality of titles in a generated tableof-contents. The supportive knowledge is derived from a hierarchical clustering of words, which is built from a large collection of raw text, and a topic model, which is directly estimated from the training data. The relatively good results of the experiments showed that the semantic and topic information supplied by supportive knowledge have good effects on title generation, and therefore, they help to improve the quality of the generated table-of-contents.

show abstract

“…Given the verbose text, the system's task is to reconstruct the original message. The problem can be modeled in terms of simple word-level features, as in (Banko et al 2000), or in terms of parse tree structures, as in (Knight and Marcu 2000;Turner and Charniak 2005). One downside of these statistical approaches is the need for annotated training data to learn model parameters.…”

Section: Related Workmentioning

confidence: 99%

Syntactic sentence compression in the biomedical domain: facilitating access to related articles

Lin

Wilbur

2007

Inf Retrieval

View full text Add to dashboard Cite

We explore a syntactic approach to sentence compression in the biomedical domain, grounded in the context of result presentation for related article search in the PubMed search engine. By automatically trimming inessential fragments of article titles, a system can effectively display more results in the same amount of space. Our implemented prototype operates by applying a sequence of syntactic trimming rules over the parse trees of article titles. Two separate studies were conducted using a corpus of manually compressed examples from MEDLINE: an automatic evaluation using BLEU and a summative evaluation involving human assessors. Experiments show that a syntactic approach to sentence compression is effective in the biomedical domain and that the presentation of compressed article titles supports accurate ''interest judgments'', decisions by users as to whether an article is worth examining in more detail.

show abstract

Headline generation based on statistical translation

Cited by 184 publications

References 19 publications

Analysis of BMW Model for Title Word Selection on Indic Script

Analysis of BMW Model for Title Word Selection on Indic Script

Learning to Generate a Table-of-Contents with Supportive Knowledge

Syntactic sentence compression in the biomedical domain: facilitating access to related articles

Contact Info

Product

Resources

About