Upload
others
View
26
Download
0
Embed Size (px)
Citation preview
Visualization of patent claims structure to improve their
readability
Shichao Dong
Supervisor
2
Dr. Gabriela FERRARO
NICTA and The Australian National
University, Canberra, ACT, Australia
NICTA is funded by the Australian Government through the Department of Communications and the Australian Research Council
through the ICT Centre of Excellence Program. NICTA is also funded and supported by the Australian Capital Territory, the New
South Wales, Queensland and Victorian Governments, the Australian National University, the University of New South Wales, the
University of Melbourne, the University of Queensland, the University of Sydney, Griffith University, Queensland University of
Technology, Monash University and other university partners.
Introduction
Objectives:
Revise the state-of-the-art literatures about text readability;
Built a software application that visualize the patent claims
hierarchical structure;
Design a user study evaluation to assess whether the
proposed software improves the reading experience.
Motivation
Education
Health
Law
1. Language learning
2. Selection for different group education
1. People with cognitive reading disability.
2. Medical records
1. Contracts
2. Licences
3. Patent Documents
Patent claims are difficult to read and understand
• Patent claims contains knowledge in certain field
• Patent claims contains complex linguistic structure
• Patent claims are written in long sentence
There is a need for method and technique to improve the patent claim readability
The patent claims are organized in the hierarchical structure
Motivation
Karmakar and Zhu (2010) define that:
A document readability could be regarded as an indicator of this
document's understandability to particular groups of readers.
High readability include : improved readership, good comprehension,
clear memorization, fast reading speed, and long reading persistence
Readability
KARMAKAR, S. AND ZHU, Y. 2010. Visualizing text readability. In Advanced Information Management and Service (IMS), 2010 6th
International Conference on (2010), pp. 291–296. IEEE.
Patent are legal documents have a predefined document
structure that consists of several sections, such as title, abstract,
background of the invention, description of the drawings and
claims.
The claims are the most important section as they define the
scope of legal protection of the invention. In most modern
patent laws, patent applications must have at least one claim.
Patent claims
Patent claims hierarchical
structure Independent claims (IC) : independent claims stands on their
own. These kind of claims do not refer back to the previous claims (Pressman, 2012). Basically, they define the scope in a board and general way. The first claim of a patent is always an independent claim.
Dependent claims (DC) : dependent claims makes references to the claim they dependent on (Pressman, 2012). They refer back to one or more than one claims from the previous claims. Compared with the IC, dependent claims define the right protection in a narrow scope. The references to other claims are made explicit by textual refer read in isolation, they should be read after understanding the claims they dependent on.
Patent claims hierarchical
structure
Independent claims (IC) Dependent claims (DC)
stands on their own makes references
do not refer back refer back to one or more
than one claims
define the scope in a board
and general way
define the right protection
in a narrow scope
read alone read after understanding the
claims they dependent on
first claim -
Example-Independent claims (IC)
A boring tool comprising a body, a plurality of cutting blades
supported by the body so as to be movable along paths equally
incline at an acute angle to an axis of rotation of the body,
outer ends of the blades having cutting edges and projecting
beyond the body, characterized by a rotatable blade advancing
member having a screwed shank within a threaded bore on the
axis of rotation and a head abutting inner ends of the blades
for advancing and retracting the blades on their paths
consequent upon rotation of the shank within the bore, and
means operable from the exterior of the body for causing
rotation of the blade advancing member.
Example-Dependent claims (DC)
A boring tool according to claim 1 characterized in that the means for causing rotation of the blade advancing member comprises a worm rotatable by a detachable handle or key and a meshing worm wheel secured to a shaft extending from the shank of the blade advancing member and co-axial there- with.
A boring tool according to claim 1 or 2 characterized in that the tool advancing member has a head with a conical surface abutting the inner ends of the cutting blades.
A boring tool according to any of claims 1-4 characterized in that the cutter blades are guided by holes in the body which lie in planes radial to the axis of rotation.
Reference
Data Example
Keys Example
Id CLM-00002
Body, transPhrase, claim_preamble Content of the claim
Claim type dependent
claimBackReference Of claim 1
claimSize 20
Claim Text 2. The building structure of wherein
an upper surface of the elongate
protrusion is flat.
Literature Review
The Text readability and improvement
The patent claim readability and
improvement
The patent claim readability improvement
through visualization
Offering support for difficult words (Brooke et al. (2012))
Text simplification (CENTAL (2014), De Belder and Moens (2010),
Woodsend and Lapata (2011))
Building detections for abbreviation, terminology, correcting spelling and
splitting compound (Grigonytea et al. (2014), Kvist et al. (2011))
Improving text readability through linguistic techniques
Character presentation (e.g. font size) (Legge and Bigelow (2011), O’Brien et al. (2005))
Sentence presentation (e.g. sentence length, space) (Schneps et al. (2013), Zorzi et al. (2012))
Document presentation (e.g. web browser plug-in)(de Santana et al. (2013), Gregoret al. (2003))
Apply specific rules (e.g. web for age over 40) (Nielsen (2011), Santana et al. (2012))
Visualizing metrics (e.g. paragraph understandability) (Karmakar and Zhu (2010))
Improving text readability through visualization
Visualizing the structure (independent & dependent)(Sheremetyeva (2003))
Claim summarization and paraphrase (Shinmori et al. (2003), Bouayad-Agha et al. (2009))
Identify linguistic parts in the claims (e.g. find the boundary in texts using ML method)
(Sang and Déjean (2001))
Using gazetteers or other index (Smith and Osborne (2006))
Improve presentation of claims without changing the text (Ferraro et al. (2014))
Improving the patent claim readability
Implementation – The input
example
Patent Claims
Source : http://worldwide.espacenet.com/publicationDetails/claims?DB=worldwide.espacenet.com&ND=3&locale=en_EP&FT=D&date=19801126&CC=EP&NR=0019018A1&KC=A1&tree=false
Test 1: Raw texts
1. A boring tool comprising a body, a plurality of cutting blades supported by the body so as to be movable along paths equally incline at
an acute angle to an axis of rotation of the body, outer ends of the blades having cutting edges and projecting beyond the body,
characterised by
a rotatable blade advancing member having a screwed shank within a threaded bore on the axis of rotation and a head abutting inner
ends of the blades for advancing and retracting the blades on their paths consequent upon rotation of the shank within the bore, and
means operable from the exterior of the body for causing rotation of the blade advancing member.
2. A boring tool according to claim 1 characterised in that the means for causing rotation of the blade advancing member comprises a
worm rotatable by a detachable handle or key and a meshing worm wheel secured to a shaft extending from the shank of the blade
advancing member and co-axial therewith.
3. A boring tool according to claim 1 or 2 characterised in that the tool advancing member has a head with a conical surface abutting the
inner ends of the cutting blades.
4. A boring tool according to claim 1 characterised in that the head lies within a cylindrical cavity extending inwardly from one end of
the body member, the open end of the cavity being closed by a plug which backs a frusto-coiucal pressure pad supporting the cutter
blades.
5. A boring tool according to any of claims 1-4 characterised in that the cutter blades are guided by holes in the body which lie in planes
radial to the axis of rotation.
6. A boring tool according to any of claims 1-5 characterised in that a serrated drive spigot co-axial with the axis of rotation of the tool is
mounted on one end of the body remote from the cutting blades and for insertion within a corresponding socket in a drive adaptor, the
tool being detachably securable to the adaptor by a ring nut engagesble with a screw threaded portion of the adaptor.
7. A boring tool according to claim 6 characterised in that the adaptor has a threaded hole to engage the screwed end of a power drill
drive shaft.
Test 2: EPO approach
According to official introduction (official webpage), the
European Patent Office (EPO) is the executive arm of
the European Patent Organization which offers inventors
seeking patent protection in up to 40 European countries.
The EPO provides a service that we can search and
explore the claims with plot views
1. A boring tool comprising a body, a plurality of cutting blades supported by the body so as to be movable along paths equally incline at an acute angle to an axis of rotation
of the body, outer ends of the blades having cutting edges and projecting beyond the body, characterised by
a rotatable blade advancing member having a screwed shank within a threaded bore on the axis of rotation and a head abutting inner ends of the blades for advancing and
retracting the blades on their paths consequent upon rotation of the shank within the bore, and means operable from the exterior of the body for causing rotation of the
blade advancing member.
2. A boring tool according to claim 1 characterised in that the means for causing rotation of the blade advancing member comprises a worm rotatable by a detachable handle
or key and a meshing worm wheel secured to a shaft extending from the shank of the blade advancing member and co-axial therewith.
3. A boring tool according to claim 1 or 2 characterised in that the tool advancing member has a head with a conical surface abutting the inner ends of the cutting blades.
4. A boring tool according to claim 1 characterised in that the head lies within a cylindrical cavity extending inwardly from one end of the body member, the open end of the
cavity being closed by a plug which backs a frusto-coiucal pressure pad supporting the cutter blades.
5. A boring tool according to any of claims 1-4 characterised in that the cutter blades are guided by holes in the body which lie in planes radial to the axis of rotation.
6. A boring tool according to any of claims 1-5 characterised in that a serrated drive spigot co-axial with the axis of rotation of the tool is mounted on one end of the body
remote from the cutting blades and for insertion within a corresponding socket in a drive adaptor, the tool being detachably securable to the adaptor by a ring nut
engagesble with a screw threaded portion of the adaptor.
7. A boring tool according to claim 6 characterised in that the adaptor has a threaded hole to engage the screwed end of a power drill drive shaft.
1
2 3 4 5 6
7
4. A boring tool according to claim 1 characterised in that the head lies within a cylindrical cavity extending inwardly from one end of the body member, the open end of the
cavity being closed by a plug which backs a frusto-coiucal pressure pad supporting the cutter blades.
5. A boring tool according to any of claims 1-4 characterised in that the cutter blades are guided by holes in the body which lie in planes radial to the axis of rotation.
3. A boring tool according to claim 1 or 2 characterised in that the tool advancing member has a head with a conical surface abutting the inner ends of the cutting blades.
6. A boring tool according to any of claims 1-5 characterised in that a serrated drive spigot co-axial with the axis of rotation of the tool is mounted on one end of the body
remote from the cutting blades and for insertion within a corresponding socket in a drive adaptor, the tool being detachably securable to the adaptor by a ring nut engagesble
with a screw threaded portion of the adaptor.
2. A boring tool according to claim 1 characterised in that the means for causing rotation of the blade advancing member comprises a worm rotatable by a detachable handle
or key and a meshingworm wheel secured to a shaft extending from the shank of the blade advancing member and co-axial therewith.
1. A boring tool comprising a body, a plurality of cutting blades supported by the body so as to be movable along paths equally incline at an acute angle to an axis of rotation
of the body, outer ends of the blades having cutting edges and projecting beyond the body, characterised by a rotatable blade advancing member having a screwed shank
within a threaded bore on the axis of rotation and a head abutting inner ends of the blades for advancing and retracting the blades on their paths consequent upon rotation
of the shank within the bore, and means operable from the exterior of the body for causing rotation of the blade advancing member.
7. A boring tool according to claim 6 characterised in that the adaptor has a threaded hole to engage the screwed end of a power drill drive shaft.
1 2 3 4 5 6 7
“and” & “or” relationship
1 2 3 4 5 6 7
3. A boring tool according to claim 1 or 2 characterised in that the tool advancing member has a head with a conical surface abutting the inner ends of the cutting blades.
“and” & “or” relationship
1 2 3 4 5 6 7
5. A boring tool according to any of claims 1-4 characterised in that the cutter blades are guided by holes in the body which lie in planes radial to the axis of rotation.
Link to the previous claims
• 1. A boring tool comprising a body, a plurality of cutting blades supported by the body so as to be movable along paths equally incline at an acute angle to an axis of rotation of the body, outer ends of the blades having cutting edges and projecting beyond the body, characterised by a rotatable blade advancing member having a screwed shank within a threaded bore on the axis of rotation and a head abutting inner ends of the blades for advancing and retracting the blades on their paths consequent upon rotation of the shank within the bore, and means operable from the exterior of the body for causing rotation of the blade advancing member.
• 2. A boring tool according to claim 1 characterised in that the means for causing rotation of the blade advancing member comprises a worm rotatable by a detachable handle or key and a meshing worm wheel secured to a shaft extending from the shank of the blade advancing member and co-axial therewith.
• 3. A boring tool according to claim 1 or 2 characterised in that the tool advancing member has a head with a conical surface abutting the inner ends of the cutting blades.
• 4. A boring tool according to claim 1 characterised in that the head lies within a cylindrical cavity extending inwardly from one end of the body member, the open end of the cavity being closed by a plug which backs a frusto-coiucal pressure pad supporting the cutter blades.
• 5. A boring tool according to any of claims 1-4 characterised in that the cutter blades are guided by holes in the body which lie in planes radial to the axis of rotation.
• 6. A boring tool according to any of claims 1-5 characterised in that a serrated drive spigot co-axial with the axis of rotation of the tool is mounted on one end of the body remote from the cutting blades and for insertion within a corresponding socket in a drive adaptor, the tool being detachably securable to the adaptor by a ring nut engagesble with a screw threaded portion of the adaptor.
• 7. A boring tool according to claim 6 characterised in that the adaptor has a threaded hole to engage the screwed end of a power drill drive shaft.
1
2 3 4 5 6
7
Link to the previous claims
1 2 3 4 5 6 7
6. A boring tool according to any of claims 1-5 characterised in that a serrated drive spigot co-axial with the axis of rotation of the tool is mounted on one end of the body remote from the cutting blades and for insertion within a corresponding socket in a drive adaptor, the tool being detachably securable to the adaptor by a ring nut engagesble with a screw threaded portion of the adaptor.
7. A boring tool according to claim 6 characterised in that the adaptor has a threaded hole to engage the screwed end of a power drill drive shaft.
User study
Type : survey or questionnaire
Participant : occupation, age, education
Question options: strongly agree ,somewhat
agree, neutral, somewhat disagree and
strongly disagree
User study
Technology acceptance model (TAM) (Davis, 1989) attempts to understand why people accept or reject information technologies. In this model, external variables (e.g., user characteristics, political influences, organisational factors, and development process) are expected to influence technology acceptance indirectly by affecting peoples beliefs, attitudes, or intentions (Szajna, 1996).
Task technology fit (TTF) (Goodhue, 1995) views technologies as means for a goal- directed person to perform tasks. It posits that technologies will be used if, and only if, their available functionalities support the users activities.
Web site user satisfaction (WSUS)(Muylle et al., 2004) is based on a two-step study. First, a pilot study was conducted in order to define which items contribute to user satisfaction if using a web interface to interact with technology users. Second, a confirmatory factor analysis was performed for these items and its results demonstrated the adequate validity and reliability of the initial model.
User Study
1. In my opinion, it is important to improve the readability of patent documents 2. In my opinion, it is difficult to read patent documents 3. I do not find information I need easily from patent documents in this format 4. In my opinion, I prefer to read raw text 5. In my opinion, I prefer to read raw text with plot demonstration such as tree view about the
document structure 6. In my opinion, I prefer to read raw text with notations such as font color, sentence spaces and
underline 7. In my opinion, I have never tried texts with settings from Question 4 to 6, but I would like to try
if these strategy is available 8. In my opinion, information provided in patent documents as they are is sufficient and further
visualization is not needed 9. I feel easy to understand the UI and visualization result 10. I can easily see the structure of the patent claims in this form 11. I do not find information I need easily from patent documents as they are now 12. I can concentrate more in this form compared with raw text 13. I can concentrate more in this form compared with EOP method 14. I cannot understand the demonstration and plots at all 15. In my opinion, this settings and visualization form would contribute to information sufficiency 16. In my opinion, it is difficult to use this kind of improvement option 17. In my opinion, the information and technology structures of this kind of improvement option
are clear 18. In my opinion, this kind of improvement option was versatile enough 19. In my opinion, this kind of improvement option dose not perform as I expected, but I still
open to the visualization technique and I would like to try more products using this strategy
Conclusion
Study the state-of-the-art research approaches to improve
the readability
Study the state-of-the-art research approaches to improve
the readability by using visualization techniques
Develop a demo to implement our ideas for improve patent
claims readability
Design user study to evaluate the demo
Future Work
Implement the user-driven evaluation
Try other visualization techniques
Extend this approach to different languages
Reference list
ALUISIO, S., SPECIA, L., GASPERIN, C., AND SCARTON, C. 2010. Readability assessment for text simplification. In Proceedings of the NAACL HLT 2010 Fifth Work- shop on Innovative Use of NLP for Building Educational Applications (2010), pp. 1–9. Association for Computational Linguistics.
BEN FRY, C. R. Processing introduction. https://www.processing.org. Ac- cessed July 4, 2014. BOUAYAD-AGHA, N., CASAMAYOR, G., FERRARO, G., MILLE, S., VIDAL, V., AND WANNER, L. 2009. Improving the comprehension of legal documentation: the case of patent claims. In Proceedings of
the 12th International Conference on Artificial Intelligence and Law (2009), pp. 78–87. ACM. BROOKE, J., TSANG, V., JACOB, D., SHEIN, F., AND HIRST, G. 2012. Building readability lexicons with unannotated corpora. In Proceedings of the First Workshop on Predicting and Improving Text Readability for
target reader populations (2012), pp. 33–39. Association for Computational Linguistics. BURGUNDER, L. 2010. Legal aspects of managing technology. Cengage Learning. CALLAN, J. AND ESKENAZI, M. 2007. Combining lexical and grammatical fea- tures to improve readability measures for first and second language texts. In NAACL HLT (2007). CROSSLEY, S. A., ALLEN, D. B., AND MCNAMARA, D. S. 2011. Text readability and intuitive simplification: A comparison of readability formulas. Reading in a foreign language 23, 1, 84–101. DAVIS, F. D. 1989. Perceived usefulness, perceived ease of use, and user accep- tance of information technology. MIS quarterly, 319–340. DE SANTANA, V. F., DE OLIVEIRA, R., ALMEIDA, L. D. A., AND BARANAUSKAS, M. C. C. 2012. Web accessibility and people with dyslexia: a survey on techniques and guidelines. In Proceedings of the
International Cross-Disciplinary Conference on Web Accessibility (2012), pp. 35. ACM. DE SANTANA, V. F., DE OLIVEIRA, R., ALMEIDA, L. D. A., AND ITO, M. 2013. Firefixia: An accessibility web browser customization toolbar for people with dyslexia. In Proceedings of the 10th International
Cross-Disciplinary Conference on Web Accessibility (2013), pp. 16. ACM. DUBAY, W. H. 2007. Smart Language: Readers, Readability, and the Grading of Text. ERIC. FERRARO, G., SUOMINEN, H., AND NUALART, J. 2014. Segmentation of patent claims for improving their readability. In Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader
Populations (PITR)@ EACL (2014), pp. 66–73. FISHBEIN, M. AND AJZEN, I. 1975. Belief, attitude, intention and behavior: An intro- duction to theory and research. FRANC ̧ OIS, T. AND MILTSAKAKI, E. 2012. Do nlp and machine learning improve traditional readability formulas? In Proceedings of the First Workshop on Predicting and Improving Text Readability for target reader
populations (2012), pp. 49–57. Association for Computational Linguistics. GOODHUE, D. L. 1995. Understanding user evaluations of information systems. Management science 41, 12, 1827–1844. GREGOR, P., DICKINSON, A., MACAFFER, A., AND ANDREASEN, P. 2003. See- worda personal word processing environment for dyslexic computer users. British Journal of Educational Technology 34, 3,
341–355. GREGOR, P. AND NEWELL, A. F. 2000. An empirical investigation of ways in which some of the problems encountered by some dyslexics may be alleviated using computer techniques. In Proceedings of the fourth
international ACM conference on Assistive technologies (2000), pp. 85–91. ACM. KARMAKAR, S. AND ZHU, Y. 2010. Visualizing text readability. In Advanced Infor- mation Management and Service (IMS), 2010 6th International Conference on (2010), pp. 291–296. IEEE. LEGGE, G. E. AND BIGELOW, C. A. 2011. Does print size matter for reading? a review of findings from vision science and typography. Journal of Vision 11, 5, 8. LEYKIN, A. AND TUCERYAN, M. 2004. Automatic determination of text readabil- ity over textured backgrounds for augmented reality systems. In Proceedings of the 3rd IEEE/ACM International Symposium on
Mixed and Augmented Reality (2004), pp. 224–230. IEEE Computer Society. MCLAUGHLIN, G. H. 1969. Smog grading: A new readability formula. Journal of reading 12, 8, 639–646. MUYLLE, S., MOENAERT, R., AND DESPONTIN, M. 2004. The conceptualiza- tion and empirical validation of web site user satisfaction. Information & Manage- ment 41, 5, 543–560. NIELSEN, J. 2011. Top 10 mistakes in web design. Retrieved August 22, 2013. O’BRIEN, B. A., MANSFIELD, J. S., AND LEGGE, G. E. 2005. The effect of print size on reading speed in dyslexia. Journal of Research in Reading 28, 3, 332–349. OFFICIAL WEBPAGE, E. Epo: about us. http://www.epo.org/about-us/ office.html. Accessed July 4, 2014. PRESSMAN, D. 2012. Patent it Yourself: Your Step-by-step Guide to Filing at the US Patent Office. Nolo. RELLO, L., SAGGION, H., BAEZA-YATES, R., AND GRAELLS, E. 2012. Graph- ical schemes may improve readability but not understandability for people with dyslexia. In Proceedings of the First Workshop on
Predicting and Improving Text Read- ability for target reader populations (2012), pp. 25–32. Association for Computational Linguistics. SANG, E. F. AND DE ́JEAN, H. 2001. Introduction to the conll-2001 shared task: Clause identification. arXiv preprint cs/0107016. SATO, S., MATSUYOSHI, S., AND KONDOH, Y. 2008. Automatic assessment of japanese text readability based on a textbook corpus. In LREC (2008). SCHNEPS, M. H., THOMSON, J. M., SONNERT, G., POMPLUN, M., CHEN, C., AND HEFFNER-WONG, A. 2013. Shorter lines facilitate reading in those who strug- gle. PloS one 8, 8, e71161. SCHWARM, S. E. AND OSTENDORF, M. 2005. Reading level assessment using sup- port vector machines and statistical language models. In Proceedings of the 43rd Annual Meeting on Association for Computational
Linguistics (2005), pp. 523–530. As- sociation for Computational Linguistics. SHAYWITZ, S. E. AND SHAYWITZ, B. A. 2005. Dyslexia (specific reading disabil- ity). Biological psychiatry 57, 11, 1301–1309. SHEREMETYEVA, S. 2003. Natural language analysis of patent claims. In Proceed- ings of the ACL-2003 workshop on Patent corpus processing-Volume 20 (2003), pp. 66–73. Association for Computational Linguistics. SHINMORI, A. AND OKUMURA, M. 2004. Aligning patent claims with detailed descriptions for readability. SHINMORI, A., OKUMURA, M., MARUKAWA, Y., AND IWAYAMA, M. 2003. Patent claim processing for readability: structure analysis and term explanation. In Pro- ceedings of the ACL-2003 workshop on Patent
corpus processing-Volume 20 (2003), pp. 56–65. Association for Computational Linguistics. SMITH, A. AND OSBORNE, M. 2006. Using gazetteers in discriminative informa- tion extraction. In Proceedings of the Tenth Conference on Computational Natural Lan- guage Learning (2006), pp. 133–140. Association
for Computational Linguistics. SZAJNA, B. 1996. Empirical evaluation of the revised technology acceptance model. Management science 42, 1, 85–92. ZORZI, M., BARBIERO, C., FACOETTI, A., LONCIARI, I., CARROZZI, M., MONTICO, M., BRAVAR, L., GEORGE, F., PECH-GEORGEL, C., AND ZIEGLER, J. C. 2012. Extra-large letter spacing
improves reading in dyslexia. Proceedings of the National Academy of Sciences 109, 28, 11455–11459.