Text segmentation: Difference between revisions

Revision as of 18:01, 8 September 2020

Latest revision as of 14:19, 30 April 2025

(15 intermediate revisions by 10 users not shown)

Line 1:

{{Short description|Human writing practice}}

{{Use dmy dates|date=March 2016}}

{{Refimprove|date=October 2011}}

'''Text segmentation''' is the process of dividing written text into meaningful units, such as words, [[Sentencesentence (linguistics)|sentence]]s, or [[topic (linguistics)|topic]]s. The term applies both to [[mental process]]es used by humans when reading text, and to artificial processes implemented in computers, which are the subject of [[natural language processing]]. The problem is non-trivial, because while some written languages have explicit word boundary markers, such as the word spaces of written English and the distinctive initial, medial and final letter shapes of [[Arabic language|Arabic]], such signals are sometimes ambiguous and not present in all written languages.

Compare [[speech segmentation]], the process of dividing speech into linguistically meaningful portions.

Line 22 ⟶ 23:

Word splitting may also refer to the process of [[Syllabification|hyphenation]].

Some scholars have suggested that modern Chinese should be written in word segmentation, with

spaces between words like written English.<ref>{{cite journal |last=Zhang |first=Xiao-heng |journal=中文信息学报 |date=1998 |script-title=zh:也谈汉语书面语的分词问题——分词连写十大好处 |trans-title=Written Chinese Word-Segmentation Revisited: Ten advantages of word-segmented writing |url=http://jcip.cipsc.org.cn/CN/Y1998/V12/I3/58 |language=zh-Hans |script-journal=zh:中文信息学报 |trans-journal=[[Journal of Chinese Information Processing]] |volume=12 |issue=3 |pages=58–64 |access-date=2025-03-31}}</ref> Because there are ambiguous texts where only the author knows the intended meaning. For example, "美国会不同意。" may mean "美国 会 不同意。" (The US will not agree.) or "美 国会 不同意。" (The US Congress does not agree). For more details, see [[Chinese word-segmented writing]].

=== Intent segmentation ===

{{See also|Tri-box method}}{{Confusing section|date=September 2019}}

Intent segmentation is the problem of dividing written words into keyphrases (2 or more group of words).

Line 38 ⟶ 42:

=== Topic segmentation ===

{{main|TopicSee analysisalso|Document classification}}

Topic analysis consists of two main tasks: topic identification and text segmentation. While the first is a simple [[machine learning|classification]] of a specific text, the latter case implies that a document may contain multiple topics, and the task of computerized text segmentation may be to discover these topics automatically and segment the text accordingly. The topic boundaries may be apparent from section titles and paragraphs. In other cases, one needs to use techniques similar to those used in [[document classification]].

Segmenting the text into [[topic (linguistics)|topic]]s or [[discourse]] turns might be useful in some natural processing tasks: it can improve [[information retrieval]] or [[speech recognition]] significantly (by indexing/recognizing documents more precisely or by giving the specific part of a document corresponding to the query as a result). It is also needed in [[topic detection]] and tracking systems and [[text summarization|text summarizing]] problems.

Many different approaches have been tried:<ref>{{Citecite conference

| authorlast = Choi | first = Freddy Y. Y. Choi

| title = Advances in ___domain independent linear text segmentation

| booktitle = Proceedings of the 1st Meeting of the North American Chapter of the Association for Computational Linguistics (ANLP-NAACL-00)

| year = 2000

| url = httphttps://www.aclwebaclanthology.org/anthology/A00-2004/

| pages = 26&ndash;33

| title = Advances in ___domain independent linear text segmentation

| url = http://www.aclweb.org/anthology/A00-2004

| booktitlebook-title = Proceedings of the 1st Meeting of the North American Chapter of the Association for Computational Linguistics (ANLP-NAACL-00)

|format=PDF}}</ref><ref>{{Cite journal

| pages = 26&ndash;3326–33

| author = Jeffrey C. Reynar

| arxiv=cs/0003083

| author-link = Jeffrey C. Reynar

| access-date = 2025-03-31

| title = Topic Segmentation: Algorithms and Applications

|format=PDF}}</ref><ref>{{Citecite journalthesis

| version = IRCS-98-21

| last = Reynar | first = Jeffrey C.

| publisher = [[University of Pennsylvania]]

| year = 1998

| url = httphttps://repository.upenn.edu/cgihandle/viewcontent20.cgi?article=1068&context=ircs_reports500.14332/37673

| title = Topic Segmentation: Algorithms and Applications

| format = PDF

| accessdate = 2007-11-08

| degree = PhD

}}</ref> e.g. [[Hidden Markov model|HMM]], [[Lexical chain|lexical chains]], passage similarity using word [[co-occurrence]], [[cluster analysis|clustering]], [[topic modeling]], etc.

| publisher = [[University of Pennsylvania]]

| versionid = IRCS-98-21

| access-date = 2025-03-31

}}</ref> e.g. [[Hiddenhidden Markov model|HMM]], [[Lexicallexical chain|lexical chains]], passage similarity using word [[co-occurrence]], [[cluster analysis|clustering]], [[topic modeling]], etc.

It is quite an ambiguous task – people evaluating the text segmentation systems often differ in topic boundaries. Hence, text segment evaluation is also a challenging problem.

<!-- <math> WindowDiff(ref,hyp) {{=}} 1 \over{N-k} \sum |b(ref_i,ref_{i+k})-b(hyp_i,hyp_{i+k})|</math> -->

Line 87 ⟶ 93:

* [[Word count]]

* [[Line wrap and word wrap|Line breaking]]

* [[Image segmentation]]

{{Natural Language Processing}}

== References ==

{{Reflist}}

{{Natural Language Processing}}

[[Category:Tasks of natural language processing]]