Paclic2013Memo
をテンプレートにして作成
[
トップ
] [
新規
|
一覧
|
単語検索
|
最終更新
|
ヘルプ
]
開始行:
[[FrontPage]]
-Barriere's (2009) TerminoWeb
-[[TechCollo (Wible, and others)>http://techcollo.stringn...
-Normallized MI --> frequency divided by the number of se...
-[[LTTCELC-Learner-Corpus>http://lttcelc.org/]]
-Greenstone/FLAX Web Phrases
-[[Linggle>http://linggle.com/##CMD]]
-[[Netspeak.org>http://www.netspeak.org/]]
**Keynote [#m6aff977]
-Magnetoencephalography (MEG)
--word recognition
---visual cortices, Occipital Lobe --> abstract sign rec...
---lemma/lexical access
---recomposition of stem and suffix
**Keynote2: Prof. Wen-Lian Hsu (Academia Sinica) [#f848ea...
-The archaelogist is in trouble ([people: [be]: [in a sit...
-The old archaelogist named John Doe is in a very serious...
--phrases --> classes (NP, PP, AdjP)
--Simple phrase: word, word combination
--Complex phrase: named entity frame
--Scenerio frame:
--Frame elements
---exaple??
--How to score an Insertion?
--Principle Pattern Analysis
---60 patterns out of all the sentence structures will co...
---Using that framework, you can do the insertion/deletio...
**Keynote by Tsujii Junichi (Microsoft Research, Beijing)...
-Language acquisition --> skimming huge amount of data --...
-Semantic trigger (Pinker) --> certain contexts
--text <--> knowledge (bootstrapping)
-Innate ability (Chomsky)
--grammar (linear sequence --> structure --> meaning)
-rationalism vs. empiricism
--Ken Church (2011): A pendulum swung too far toward empi...
--Integrating [grammar, rule] into [data]
-Knowledge mining
--Triggering: Big knowledge to enhance NLP abilities
---entity linking
---relation extraction
-Entity linking
--MS --> Microsoft or Multiple sclerosis
--entity relation in knowledge domain (human knows all th...
--categories in knowledge
-How to use those structural knowledge to disambiguate th...
-Build classifiers, looking at the context and tell which...
-Inference relationship among different cues with differe...
-Semantic parsing
--Identify grammatical relationships
--Extract entity relationships
-Parsing: Current state of the arts
--F-value too high
--Most relations are very simple (DET-N, ADJ-N) and trivial
--Non-trivial one: PP attachment
---accuracy is around 80-85%
-semantically crucial problems are not properly solved by...
-They use HPSG
-Fragments of parsing are compared to each other and comp...
-inferences involved --> difficult
-statistical models of inferences have become scalable an...
-integration of NLP with knowledge-based inferences is be...
終了行:
[[FrontPage]]
-Barriere's (2009) TerminoWeb
-[[TechCollo (Wible, and others)>http://techcollo.stringn...
-Normallized MI --> frequency divided by the number of se...
-[[LTTCELC-Learner-Corpus>http://lttcelc.org/]]
-Greenstone/FLAX Web Phrases
-[[Linggle>http://linggle.com/##CMD]]
-[[Netspeak.org>http://www.netspeak.org/]]
**Keynote [#m6aff977]
-Magnetoencephalography (MEG)
--word recognition
---visual cortices, Occipital Lobe --> abstract sign rec...
---lemma/lexical access
---recomposition of stem and suffix
**Keynote2: Prof. Wen-Lian Hsu (Academia Sinica) [#f848ea...
-The archaelogist is in trouble ([people: [be]: [in a sit...
-The old archaelogist named John Doe is in a very serious...
--phrases --> classes (NP, PP, AdjP)
--Simple phrase: word, word combination
--Complex phrase: named entity frame
--Scenerio frame:
--Frame elements
---exaple??
--How to score an Insertion?
--Principle Pattern Analysis
---60 patterns out of all the sentence structures will co...
---Using that framework, you can do the insertion/deletio...
**Keynote by Tsujii Junichi (Microsoft Research, Beijing)...
-Language acquisition --> skimming huge amount of data --...
-Semantic trigger (Pinker) --> certain contexts
--text <--> knowledge (bootstrapping)
-Innate ability (Chomsky)
--grammar (linear sequence --> structure --> meaning)
-rationalism vs. empiricism
--Ken Church (2011): A pendulum swung too far toward empi...
--Integrating [grammar, rule] into [data]
-Knowledge mining
--Triggering: Big knowledge to enhance NLP abilities
---entity linking
---relation extraction
-Entity linking
--MS --> Microsoft or Multiple sclerosis
--entity relation in knowledge domain (human knows all th...
--categories in knowledge
-How to use those structural knowledge to disambiguate th...
-Build classifiers, looking at the context and tell which...
-Inference relationship among different cues with differe...
-Semantic parsing
--Identify grammatical relationships
--Extract entity relationships
-Parsing: Current state of the arts
--F-value too high
--Most relations are very simple (DET-N, ADJ-N) and trivial
--Non-trivial one: PP attachment
---accuracy is around 80-85%
-semantically crucial problems are not properly solved by...
-They use HPSG
-Fragments of parsing are compared to each other and comp...
-inferences involved --> difficult
-statistical models of inferences have become scalable an...
-integration of NLP with knowledge-based inferences is be...
ページ名: