I work on a range of projects at the intersection of Natural Language Processing and Crowdsourcing.
I am an Assistant Professor at the University of Sydney and advise startups on NLP technology.
A tool for classifying errors in coreference resolution
License: ISC License
I work on a range of projects at the intersection of Natural Language Processing and Crowdsourcing.
I am an Assistant Professor at the University of Sydney and advise startups on NLP technology.
I understand that the *.corrected.$ERROR_TYPE
files are the system output with $ERROR_TYPE
fixed, but what are the *_prog
files? And why isn't there one associated with confused entity? Thanks in advance!
Hi,
I am trying to use coreference_reading script for parsing coreference annotated file in CoNLL format. I would like to know what the function read_conll_coref() returns. Can you please help me with this ? If there is some documentation available of the whole system it would be great.
Thanks,
Joe
Original issue reported on code.google.com by [email protected]
on 13 Dec 2014 at 6:59
Can we give the input as a text file?
Dear Authors,
This is great work and it would be highly useful for future researchers if this repository is well maintained. Is there any active version of the same repository preferably in Python 3? Really would like to reimplement it but require some help.
Thank you
Hi,
For the following sentence, there's an extra mention in the cluster, and there's also a "remove" operation under Raw changes
. But what's the rationale behind not categorizing this as an extra mention error?
(5, 20, 23) Extra: the Giant Buddha
(17, 6, 14) this world 's largest outdoor seated bronze Buddha
(22, 1, 5) this giant bronze Buddha
Missing:
(19, 2, 9) Hong Kong 's Tian Tan Giant Buddha
Raw changes:
merge 2
introduce 1
split 2
remove 1
Categorised:
1 Conflated Entities
1 Missing Mention
Detailed error listing:
split (set([(17, 6, 14), (22, 1, 5)]), set([(17, 6, 14), (22, 1, 5), (5, 20, 23)]), '', ['split', 2, 1, None, '0_cataphoric', 2, 0, 0, 1, 0, 0, False, True, 'no_string_match', 'head_match', 'merge', 'split', False, 'part_', 'cluster_WORK_OF_ART', True, 'part_', 'cluster_', True, 'part_', 'cluster_', True, 'part_', 'cluster_'])
Properties included: split ['split', 2, 1, None, '0_cataphoric', 2, 0, 0, 1, 0, 0, False, True, 'no_string_match', 'head_match', 'merge', 'split', False, 'part_', 'cluster_WORK_OF_ART', True, 'part_', 'cluster_', True, 'part_', 'cluster_', True, 'part_', 'cluster_']
missing mention (19, 2, 9) Hong Kong 's Tian Tan Giant Buddha
missing mention (set([(19, 2, 9)]), set([(17, 6, 14), (22, 1, 5), (19, 2, 9)]), (set([(19, 2, 9)]), set([(17, 6, 14), (22, 1, 5), (19, 2, 9)]), ['merge', 1, 2, "hong_kong_'s_tian_tan_giant_buddha", '0_cataphoric', 1, 0, 0, 2, 0, 0, False, False, 'no_string_match', 'head_match', 'merge', 'introduce', True, 'part_', 'cluster_', True, 'part_', 'cluster_', True, 'part_', 'cluster_', True, 'part_', 'cluster_']), ['missing', 'name', "hong_kong_'s_tian_tan_giant_buddha", 'no_text_match', 'head_match', 'not_nested', False, False, False, 'ner_unknown', 'number_unknown', 'person_unknown', 'gender_unknown'])
Properties included: missing mention ['missing', 'name', "hong_kong_'s_tian_tan_giant_buddha", 'no_text_match', 'head_match', 'not_nested', False, False, False, 'ner_unknown', 'number_unknown', 'person_unknown', 'gender_unknown']
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.