Unsupervised Morphological Segmentation Based on Segment Predictability and Word Segments Alignment

author: Delphine Bernhard, TIMC - IMAG, Faculté de Médecine

Description

Word segments are relevant cues for the automatic acquisition of semantic relationships from morphologically related words. Indeed, morphemes are the smallest meaning-bearing units. We present an unsupervised method for the segmentation of words into sub-units devised for this objective. The system relies on segment predictability to discover a set of prefixes and suffixes and performs word segments alignment to detect morpheme boundaries.

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Unsupervised Morphological Segmentation Based on Word Segments Predictability and Alignment
0:37	Part I - Motivation
0:49	Why ? - part 1
2:01	Why ? - part 2
2:20	Why ? - part 3
2:50	Why ? - part 4
3:16	Why ? - part 5
3:34	Why ? - part 6
3:46	Objectives
4:30	Part II - Method
4:32	Constraints
5:41	Overview of the method
6:11	Acquisition of prefixes and suffixes [1] - part 1
6:29	Acquisition of prefixes and suffixes [1] - part 2
7:03	Acquisition of prefixes and suffixes [1] - part 3
7:08	Acquisition of prefixes and suffixes [2]
8:39	Extraction of stems
8:56	Alignment of word segments [1]
9:51	Alignment of word segments [2]
11:03	Selection of the best segmentation
11:57	Segmentation of new words
12:45	Part III - Results and conclusion
12:50	Evaluation
13:57	Examples [1]
14:32	Examples [2]
15:09	Main issues
15:42	Conclusion
17:24	Thank you
17:54	- Questions

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.