A maximum-likelihood approach to segmentation-based recognition of unconstrained handwriting text

Senda, Shuji; Yamada, Keiji

doi:10.1109/icdar.2001.953780

Cited by 19 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linguistic based text segmentation approaches are derived from the lexical cohesion theory of Halliday and Hasan (1976). They rely on terms repetition to detect topic changes (Reynar 1998;Hearst 1994;Youmans 1991), n-gram word or phrases (Levow 2004) or word frequency (Senda and Yamada 2001;Reynar 1999;Beeferman et al 1997) as well as lexical chaining to identify topic changes (Stokes 2004;Manning 1998) and prosodic clues to mark shifts to new topics (Levow 2004). To improve the accuracy of a text segmentation algorithm Choi et al (2001) applied Latent Semantic Analysis (LSA), a technique aimed at extracting and representing the contextual-usage meaning of words by statistical computations applied to a large corpus (Landauer and Dumais 1997).…”

Section: Previous Workmentioning

confidence: 99%

Text segmentation of spoken meeting transcripts

Sharp

Chibelushi

2008

Int J Speech Technol

View full text Add to dashboard Cite

Text segmentation has played an important role in information retrieval as well as natural language processing. Current segmentation methods are well suited for written and structured texts making use of their distinctive macrolevel structures; however text segmentation of transcribed multi-party conversation presents a different challenge given its ill-formed sentences and the lack of macro-level text units. This paper describes an algorithm suitable for segmenting spoken meeting transcripts combining semantically complex lexical relations with speech cue phrases to build lexical chains in determining topic boundaries.

show abstract

Section: Previous Workmentioning

confidence: 99%

Text segmentation of spoken meeting transcripts

Sharp

Chibelushi

2008

Int J Speech Technol

View full text Add to dashboard Cite

show abstract

“…A review of the literature on text segmentation techniques reveals two distinct approaches: statistically based and linguistically driven methods [5,14]. Some statistical approaches are based on probability distributions [2], machine learning techniques ranging from neural networks [4], to support vector machines [18] and Bayesian networks [21], while others treat text as an unlabelled sequence of topics using a hidden Markov model [24]. [8] developed a text segmentation tool called C99 which uses a divisive clustering algorithm developed by [20] to identify topic boundaries.…”

Section: Previous Workmentioning

confidence: 99%

Tracker Text Segmentation Approach: Integrating Complex Lexical and Conversation Cue Features

Chibelushi

Sharp²

2008

Proceedings of the 5th International Workshop on Natural Language Processing and Cognitive Science

View full text Add to dashboard Cite

While text segmentation is a topic which has received a great attention since 9/11, most of current research projects remain focused on expository texts, stories and broadcast news. Current segmentation methods are well suited for written and structured texts making use of their distinctive macro-level structures. Text segmentation of transcribed multi-party conversation presents a different challenge given the lack of linguistic features such as headings, paragraph, and well formed sentences. This paper describes an algorithm suited for transcribed meeting conversations combining semantically complex lexical relations with conversational cue phrases to build lexical chains in determining topic boundaries.

show abstract

“…By incorporating the factor of character size in determining the likelihood, they showed better performance than without including it. Senda et al published a similar approach to the above method and formulated the problem as a search for the most probable interpretation of character segmentation, recognition and context, but they did not deal with the likelihood of character size [6], [7]. In off-line handwriting recognition, the same problem of character segmentation and recognition occurs.…”

Section: Introductionmentioning

confidence: 99%

A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints

Nakagawa

Zhu

Onuma

2005

IEICE Transactions on Information and Systems

View full text Add to dashboard Cite

This paper presents a model and its effect for on-line handwritten Japanese text recognition free from line-direction constraint and writing format constraint such as character writing boxes or ruled lines. The model evaluates the likelihood composed of character segmentation, character recognition, character pattern structure and context. The likelihood of character pattern structure considers the plausible height, width and inner gaps within a character pattern that appear in Chinese characters composed of multiple radicals (subpatterns). The recognition system incorporating this model separates freely written text into text line elements, estimates the average character size of each element, hypothetically segments it into characters using geometric features, applies character recognition to segmented patterns and employs the model to search the text interpretation that maximizes likelihood as Japanese text. We show the effectiveness of the model through recognition experiments and clarify how the newly modeled factors in the likelihood affect the overall recognition rate.

show abstract

A maximum-likelihood approach to segmentation-based recognition of unconstrained handwriting text

Cited by 19 publications

References 1 publication

Text segmentation of spoken meeting transcripts

Text segmentation of spoken meeting transcripts

Tracker Text Segmentation Approach: Integrating Complex Lexical and Conversation Cue Features

A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints

Contact Info

Product

Resources

About