NLP and the We at TU Darmstadt

Flashcards and summaries for NLP and the We at the TU Darmstadt

Arrow Arrow

It’s completely free

studysmarter schule studium
d

4.5 /5

studysmarter schule studium
d

4.8 /5

studysmarter schule studium
d

4.5 /5

studysmarter schule studium
d

4.8 /5

Study with flashcards and summaries for the course NLP and the We at the TU Darmstadt

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

What is the intuition behind passage retrieval and its steps?

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

What are phrases and constituents?

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

What are the advantages of a SVM?
This was only a preview of our StudySmarter flashcards.
Flascard Icon Flascard Icon

Millions of flashcards created by students

Flascard Icon Flascard Icon

Create your own flashcards as quick as possible

Flascard Icon Flascard Icon

Learning-Assistant with spaced repetition algorithm

Sign up for free!

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

What are the problems of sequence labeling as classification?

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

What are the advantages of probabilistic sequence models?

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

How do we measure user happiness in a search engine?

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

Of which things do the test collection need to consist of?
This was only a preview of our StudySmarter flashcards.
Flascard Icon Flascard Icon

Millions of flashcards created by students

Flascard Icon Flascard Icon

Create your own flashcards as quick as possible

Flascard Icon Flascard Icon

Learning-Assistant with spaced repetition algorithm

Sign up for free!

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

Explain the concept of PageRank.

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

What happens in the ranking process within heading creation?

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

How do you select an anchor?

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

How does target selection in the link discovery task work?
This was only a preview of our StudySmarter flashcards.
Flascard Icon Flascard Icon

Millions of flashcards created by students

Flascard Icon Flascard Icon

Create your own flashcards as quick as possible

Flascard Icon Flascard Icon

Learning-Assistant with spaced repetition algorithm

Sign up for free!

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

What are concept maps?

Your peers in the course NLP and the We at the TU Darmstadt create and share summaries, flashcards, study plans and other learning materials with the intelligent StudySmarter learning app.

Get started now!

Flashcard Flashcard

Exemplary flashcards for NLP and the We at the TU Darmstadt on StudySmarter:

NLP and the We

What is the intuition behind passage retrieval and its steps?

Intuition: the answer to a question is usually not the full document. Either
a passage, or a part of it.


  1. IR engine retrieves documents using query terms

  2. Segment the documents into shorter units --> something like paragraphs

  3. Passage ranking --> Use answer type to help re-rank passages

NLP and the We

What are phrases and constituents?

Phrases are contiguous sequences of related words


Constituent = a word or a group of words that function(s) as a single unit within a
hierarchical structure

NLP and the We

What are the advantages of a SVM?
  • deals well with high-dimensional, sparse vectors: can convert nominal features into e.g. Boolean representation

  • very flexible: different kernel functions, variation in number of support vectors

  • robust classifiers, noise tolerant

  • efficient implementations available

NLP and the We

What are the problems of sequence labeling as classification?
  • Not easy to integrate information from category of tokens on both sides

  • Difficult to propagate uncertainty between decisions and “collectively” determine the most likely joint assignment of categories to all of the tokens in a sequence.

NLP and the We

What are the advantages of probabilistic sequence models?
  • integrating uncertainty over multiple, interdependent classifications

  • and collectively determine the most likely global assignment.

  • generative sequence models (like Hidden markov model) and discriminative sequence models (like Conditional Random Field)

NLP and the We

How do we measure user happiness in a search engine?
  • equated with the relevance of search results to the query

  • Standard methodology in information retrieval consists of three elements.

    • A benchmark document collection

    • A benchmark suite of queries

    • An assessment of the relevance of each query-document pair

NLP and the We

Of which things do the test collection need to consist of?
  1. document collection
  2. test suite of information needs, expressible as queries
  3. set of relevance judgments, standardly a binary assessment of either relevant or nonrelevant for each query-document pair

NLP and the We

Explain the concept of PageRank.

Idea: 

  • Assign a query-independent measure of prestige to each Web resource


The PageRank solution:

  • The number of in-links is correlated to a resource’s prestige

  • Links from good resources should count more than links from bad ones

NLP and the We

What happens in the ranking process within heading creation?

Many different approaches, e.g.,

  • Phraseness: Degree of lexical cohesion or collocateness of a heading

  • Informativeness: Degree of representativeness for this document

    • TF.IDF, language models informativeness, likelihood-ratio test,…

NLP and the We

How do you select an anchor?
  • Named entities

  • Noun phrases

  • Collocations

  • Document titles

  • any single word or n-gram

  • existing anchors --> e.g. in Wikipedia

NLP and the We

How does target selection in the link discovery task work?

Text- based

  • Compare two documents

  • Select those that are similar to the current document

  • But: not too similar, since these would be almost identical!

Link-based

NLP and the We

What are concept maps?
structured representation of information; consists of concepts

Concepts = Objects, persons, groups, events, abstract concepts --> everything that could have an article in Wikipedia


Linking Words = describing relationships between two concepts

Proposition =
meaningful statement; propositional coherence

Sign up for free to see all flashcards and summaries for NLP and the We at the TU Darmstadt

Singup Image Singup Image
Wave

Other courses from your degree program

For your degree program NLP and the We at the TU Darmstadt there are already many courses on StudySmarter, waiting for you to join them. Get access to flashcards, summaries, and much more.

Back to TU Darmstadt overview page

Computersystemsicherheit

Betriebssysteme

Architekturen und Entwurf von Rechnersystemen

Betriebssysteme 2020

Visual Computing

UbiCom in Geschäftsprozessen

Technology Mgmt

Venture Valuation

Ethics in NLP

Trade Theory and Policy at

Hochschule Rhein-Waal

Endocrine and the Life Cycle at

University of Southampton

Literary and Cultural Theory at

Universität Stuttgart

We at

Universität Duisburg-Essen

Data and web mining at

Instituto Politécnico de Coimbra

Similar courses from other universities

Check out courses similar to NLP and the We at other universities

Back to TU Darmstadt overview page

What is StudySmarter?

What is StudySmarter?

StudySmarter is an intelligent learning tool for students. With StudySmarter you can easily and efficiently create flashcards, summaries, mind maps, study plans and more. Create your own flashcards e.g. for NLP and the We at the TU Darmstadt or access thousands of learning materials created by your fellow students. Whether at your own university or at other universities. Hundreds of thousands of students use StudySmarter to efficiently prepare for their exams. Available on the Web, Android & iOS. It’s completely free.

Awards

Best EdTech Startup in Europe

Awards
Awards

EUROPEAN YOUTH AWARD IN SMART LEARNING

Awards
Awards

BEST EDTECH STARTUP IN GERMANY

Awards
Awards

Best EdTech Startup in Europe

Awards
Awards

EUROPEAN YOUTH AWARD IN SMART LEARNING

Awards
Awards

BEST EDTECH STARTUP IN GERMANY

Awards
X

StudySmarter - The study app for students

StudySmarter

4.5 Stars 1100 Rating
Start now!
X

Good grades at university? No problem with StudySmarter!

89% of StudySmarter users achieve better grades at university.

50 Mio Flashcards & Summaries
Create your own content with Smart Tools
Individual Learning-Plan

Learn with over 1 million users on StudySmarter.

Already registered? Just go to Login