Difference between revisions of "Word Segmentation Refinement by Wikipedia for Textual Entailment"
(Adding infobox) |
(Adding embed) |
||
Line 10: | Line 10: | ||
== Overview == | == Overview == | ||
Textual entailment in Chinese differs from the way handling English because of the lack of word delimiters and capitalization. Information from word segmentation and [[Wikipedia]] often plays an important role in textual entailment recognition. However, the inconsistency of boundaries of word segmentation and matched Wikipedia titles should be resolved first. This paper proposed 4 ways to incorporate Wikipedia title matching and word segmentation, experimented in several feature combinations. The best system redoes word segmentation after matching Wikipedia titles. The best feature combination for BC task uses content words and Wikipedia titles only, which achieves a macro-average F-measure of 67.33% and an accuracy of 68.9%. The best MC RITE system also achieves a macro-average F-measure of 46.11% and an accuracy of 58.34%. They beat all the runs in NTCIR-10 RITE-2 CT tasks. | Textual entailment in Chinese differs from the way handling English because of the lack of word delimiters and capitalization. Information from word segmentation and [[Wikipedia]] often plays an important role in textual entailment recognition. However, the inconsistency of boundaries of word segmentation and matched Wikipedia titles should be resolved first. This paper proposed 4 ways to incorporate Wikipedia title matching and word segmentation, experimented in several feature combinations. The best system redoes word segmentation after matching Wikipedia titles. The best feature combination for BC task uses content words and Wikipedia titles only, which achieves a macro-average F-measure of 67.33% and an accuracy of 68.9%. The best MC RITE system also achieves a macro-average F-measure of 46.11% and an accuracy of 58.34%. They beat all the runs in NTCIR-10 RITE-2 CT tasks. | ||
+ | |||
+ | == Embed == | ||
+ | === Wikipedia Quality === | ||
+ | <code> | ||
+ | <nowiki> | ||
+ | Lin, Chuan-Jie; Tu, Yu-Cheng. (2014). "[[Word Segmentation Refinement by Wikipedia for Textual Entailment]]".DOI: 10.1109/IRI.2014.7051944. | ||
+ | </nowiki> | ||
+ | </code> | ||
+ | |||
+ | === English Wikipedia === | ||
+ | <code> | ||
+ | <nowiki> | ||
+ | {{cite journal |last1=Lin |first1=Chuan-Jie |last2=Tu |first2=Yu-Cheng |title=Word Segmentation Refinement by Wikipedia for Textual Entailment |date=2014 |doi=10.1109/IRI.2014.7051944 |url=https://wikipediaquality.com/wiki/Word_Segmentation_Refinement_by_Wikipedia_for_Textual_Entailment}} | ||
+ | </nowiki> | ||
+ | </code> | ||
+ | |||
+ | === HTML === | ||
+ | <code> | ||
+ | <nowiki> | ||
+ | Lin, Chuan-Jie; Tu, Yu-Cheng. (2014). &quot;<a href="https://wikipediaquality.com/wiki/Word_Segmentation_Refinement_by_Wikipedia_for_Textual_Entailment">Word Segmentation Refinement by Wikipedia for Textual Entailment</a>&quot;.DOI: 10.1109/IRI.2014.7051944. | ||
+ | </nowiki> | ||
+ | </code> |
Revision as of 09:33, 18 May 2020
Authors | Chuan-Jie Lin Yu-Cheng Tu |
---|---|
Publication date | 2014 |
DOI | 10.1109/IRI.2014.7051944 |
Links |
Word Segmentation Refinement by Wikipedia for Textual Entailment - scientific work related to Wikipedia quality published in 2014, written by Chuan-Jie Lin and Yu-Cheng Tu.
Overview
Textual entailment in Chinese differs from the way handling English because of the lack of word delimiters and capitalization. Information from word segmentation and Wikipedia often plays an important role in textual entailment recognition. However, the inconsistency of boundaries of word segmentation and matched Wikipedia titles should be resolved first. This paper proposed 4 ways to incorporate Wikipedia title matching and word segmentation, experimented in several feature combinations. The best system redoes word segmentation after matching Wikipedia titles. The best feature combination for BC task uses content words and Wikipedia titles only, which achieves a macro-average F-measure of 67.33% and an accuracy of 68.9%. The best MC RITE system also achieves a macro-average F-measure of 46.11% and an accuracy of 58.34%. They beat all the runs in NTCIR-10 RITE-2 CT tasks.
Embed
Wikipedia Quality
Lin, Chuan-Jie; Tu, Yu-Cheng. (2014). "[[Word Segmentation Refinement by Wikipedia for Textual Entailment]]".DOI: 10.1109/IRI.2014.7051944.
English Wikipedia
{{cite journal |last1=Lin |first1=Chuan-Jie |last2=Tu |first2=Yu-Cheng |title=Word Segmentation Refinement by Wikipedia for Textual Entailment |date=2014 |doi=10.1109/IRI.2014.7051944 |url=https://wikipediaquality.com/wiki/Word_Segmentation_Refinement_by_Wikipedia_for_Textual_Entailment}}
HTML
Lin, Chuan-Jie; Tu, Yu-Cheng. (2014). "<a href="https://wikipediaquality.com/wiki/Word_Segmentation_Refinement_by_Wikipedia_for_Textual_Entailment">Word Segmentation Refinement by Wikipedia for Textual Entailment</a>".DOI: 10.1109/IRI.2014.7051944.