Identifying Negation in the DGS Corpus Graz, 2019-05-03 Marc - - PowerPoint PPT Presentation

Identifying Negation
 in the 
 DGS Corpus

Graz, 2019-05-03 Marc Schulder, Thomas Hanke Universität Hamburg {marc.schulder,thomas.hanke}@uni-hamburg.de

Negation Devices
 in Sign Languages

• Negation particles
• Negation content words
• Manual negation morphemes
• Headshake
• Facial expression

3

✔ ✔ (✔) ((✔)) ☹

Negation Particles

• Words like “no”, “not”, “without”, etc.
• Lexemes are part of core annotation.
• Small set of words, easily listed.

4

To Do

Negation Content Words

• Words like “destroy”, “prevent”, etc.
• Large set of words (>1000).
• Lists of negation content words available

for English(Schulder et al. 2017, 2018-LREC, ...) and German(Schulder et al. 2018-COLING).

• Lists can be mapped to new languages

using bilingual dictionaries or bilingual
 word embeddings (Schulder et al. 2018-COLING).

5

To Do

CANalph

cannot

Negation Morphemes

6

Ongoing...

• Small set of morphemes,


e.g. alpha negation.

• Restricted set of


compatible lexemes.

• Approach: Inspect all tokens of these

lexemes and make sure negation morphemes are annotated as qualifiers.

Headshake

• Not part of core annotation.
• But annotators were asked to add

comments about further important

• bservations.
• Result: 


>7000 comments mentioning headshakes.

7

Headshake + Lexeme

8

NO

no

BRING

not brought

Indicate negation Emphasise negation

Headshake + Phrase

9

TOGETHER FIT TOGETHER NOT

It has nothing to do with each other at all

HS negates phrase

Non-negating Headshake

10

ALL OFF-CLOSE TO-CLOSE

All of them have been closed down

HS indicates negative sentiment

Uses of Headshake

• Emphasise existing negation
• Negate a word
• Negate a phrase
• Indicate negative sentiment
• Correction
• Backchanneling

11

Manual Annotation
 is slow, so…

• Approach 1:


Use German translations

• Approach 2:


Use the visual domain

12

To Do To Do

Negation in Translation

• Corpus contains German translations
• Source is signed communication
• Negation in German most likely caused

by negation in DGS

➡ If translation contains negation, but DGS

contains no negation lemma/morpheme, headshake is likely.

13

Into the Visual Domain: OpenPose (CMU)

14

OpenPose 2017

15

OpenPose 2018

16

But then OpenPose
 is slow as well…

• 3 camera perspectives per recording.
• 1 hour recording = 87 hours processing 


(double-GPU machine)

• For our corpus this results in


a processing time of 5½ years.

• 4 months on a High Performance Cluster.

17

Track movement of the nose,
 relative to face contour.

Detecting Headshakes in OpenPose Data

18

Detecting Headshakes in OpenPose Data

1.Run Open Pose. 2.Train a neural net classifier to

• detect headshakes in time series data;
• determine duration of headshakes.

19

Neural Net Training Challenges

• Need annotator comments to train classifier,

but time spans of comments are unreliable:

• span is for sign, not headshake;
• comment combines two observations, 


e.g. “constructed action + headshake”.

➡ Comments indicate existence of headshake,

but not time span.

➡ Translations may fulfil a similar function.

20

Outlook

• Lists: Negation particles


Negation content words.

• Annotation: Negation Morphemes.
• Visual Detection: Headshakes.


(OpenPose, neural nets,
 annotator comments, translations)

➡ Compare this “joint effort” with


detailed gold standard annotation.

21

Thank you very much
 for your attention!