Nils Reiter, Benjamin Krautter, Janis Pagel, Marcus Willand Detecting Protagonists in German Plays around 1800 as a Classification Task
Disclaimer We have progressed in our work We will present the current state of our research Not only what is in the submitted paper Updated results Talk includes analysis on dramas from 1700 to 1900 See also Krautter et. al. 2018: Titelhelden und Protagonisten – Interpretierbare Figurenklassifikation in deutschsprachigen Dramen. LitLab Pamphlets , vol. 7 , November 2018. 2
Analyse (German) dramatic texts computationally Historical perspective Investigate character types Coreference resolution for dramatic texts Quantitative Drama Analytics (QuaDramA) Cooperation between German literary studies and computational linguistics 3
Historical perspective Investigate character types Coreference resolution for dramatic texts Quantitative Drama Analytics (QuaDramA) Cooperation between German literary studies and computational linguistics Analyse (German) dramatic texts computationally 3
Investigate character types Coreference resolution for dramatic texts Quantitative Drama Analytics (QuaDramA) Cooperation between German literary studies and computational linguistics Analyse (German) dramatic texts computationally Historical perspective 3
Coreference resolution for dramatic texts Quantitative Drama Analytics (QuaDramA) Cooperation between German literary studies and computational linguistics Analyse (German) dramatic texts computationally Historical perspective Investigate character types 3
Quantitative Drama Analytics (QuaDramA) Cooperation between German literary studies and computational linguistics Analyse (German) dramatic texts computationally Historical perspective Investigate character types Coreference resolution for dramatic texts 3
Introduction 1
Typically divided into acts and scenes Typically designed to be performed (on stage) Stage directions Cast Dramatic conflict What is a Drama? Use of action and dialogue 5
Typically designed to be performed (on stage) Stage directions Cast Dramatic conflict What is a Drama? Use of action and dialogue Typically divided into acts and scenes 5
Stage directions Cast Dramatic conflict What is a Drama? Use of action and dialogue Typically divided into acts and scenes Typically designed to be performed (on stage) 5
Cast Dramatic conflict What is a Drama? Use of action and dialogue Typically divided into acts and scenes Typically designed to be performed (on stage) Stage directions 5
Dramatic conflict What is a Drama? Use of action and dialogue Typically divided into acts and scenes Typically designed to be performed (on stage) Stage directions Cast 5
What is a Drama? Use of action and dialogue Typically divided into acts and scenes Typically designed to be performed (on stage) Stage directions Cast Dramatic conflict 5
<div type="h4"> <div type="scene"> </stage> <hi>Der Prinz. Emilia. Marinelli.</hi> <stage> <head>Fünfter Auftritt</head> <p> Wo ist sie? wo? – <div type="text"> </div> </desc> <title>5. Auftritt</title> <desc> <div> Wir suchen Sie überall, <speaker>DER PRINZ.</speaker> schönstes Fräulein.– Sie sind doch wohl?– Nun so ist alles wohl! Der Graf, Ihre Mutter, –</p> </sp> <sp who="#emilia"> <speaker>EMILIA.</speaker> <l> Ah, gnädigster Herr! wo sind sie? Wo ist meine Mutter?</l> </sp> <sp who="#der_prinz"> Excerpt from Lessing’s Emilia Galotti Fünfter Auftritt Der Prinz. Emilia. Marinelli. DER PRINZ. Wo ist sie? wo? - Wir suchen Sie überall, schönstes Fräulein. - Sie sind doch wohl? - Nun so ist alles wohl! Der Graf, Ihre Mutter, - EMILIA. Ah, gnädigster Herr! wo sind sie? Wo ist meine Mutter? 6
<div type="h4"> <div type="scene"> <hi>Der Prinz. Emilia. Marinelli.</hi> <stage> <head>Fünfter Auftritt</head> <speaker>DER PRINZ.</speaker> <div type="text"> </div> </desc> <title>5. Auftritt</title> <desc> <div> <p> Wo ist sie? wo? – <sp who="#der_prinz"> Wir suchen Sie überall, schönstes Fräulein.– Sie sind doch wohl?– Nun so ist alles wohl! </sp> <sp who="#emilia"> <speaker>EMILIA.</speaker> <l> Ah, gnädigster Herr! wo sind sie? Wo ist meine Mutter?</l> </sp> </stage> Excerpt from Lessing’s Emilia Galotti Fünfter Auftritt Der Prinz. Emilia. Marinelli. DER PRINZ. Wo ist sie? wo? - Wir suchen Sie überall, schönstes Fräulein. - Sie sind doch wohl? - Nun so ist alles wohl! Der Graf, Ihre Mutter, - EMILIA. Der Graf, Ihre Mutter, –</p> Ah, gnädigster Herr! wo sind sie? Wo ist meine Mutter? 6
Analyse results w.r.t. literary interpretation Goals Classify all figures in play regarding the classes: Protagonist - Not Protagonist 7
Goals Classify all figures in play regarding the classes: Protagonist - Not Protagonist Analyse results w.r.t. literary interpretation 7
We settled on: Protagonist Causes or solves the central dramatic conflict This can happen actively or passively From this follows: There can be more than one protagonist per drama Not only “heroes” in a positive sense, but also “anti-heroes” allowed Definition of Being a Protagonist Difficult from theoretical point of view 8
From this follows: There can be more than one protagonist per drama Not only “heroes” in a positive sense, but also “anti-heroes” allowed Definition of Being a Protagonist Difficult from theoretical point of view We settled on: Protagonist Causes or solves the central dramatic conflict This can happen actively or passively 8
Definition of Being a Protagonist Difficult from theoretical point of view We settled on: Protagonist Causes or solves the central dramatic conflict This can happen actively or passively From this follows: There can be more than one protagonist per drama Not only “heroes” in a positive sense, but also “anti-heroes” allowed 8
Experiments 2
Features Feature Name Description Character speech, normalised on Tokens whole text 10
Features Feature Name Description Character speech, normalised on Tokens whole text Different measures: (weighted) degree , Centrality closeness , betweenness , eigenvector 10
Features Feature Name Description Character speech, normalised on Tokens whole text Different measures: (weighted) degree , Centrality closeness , betweenness , eigenvector Topic Modelling 10 Topics trained on the dramas 10
Features Feature Name Description Character speech, normalised on Tokens whole text Different measures: (weighted) degree , Centrality closeness , betweenness , eigenvector Topic Modelling 10 Topics trained on the dramas Number of scenes where figure is Actives present 10
Features Feature Name Description Character speech, normalised on Tokens whole text Different measures: (weighted) degree , Centrality closeness , betweenness , eigenvector Topic Modelling 10 Topics trained on the dramas Number of scenes where figure is Actives present Number of Scenes where figure is Passives mentioned 10
Features Feature Name Description Character speech, normalised on Tokens whole text Different measures: (weighted) degree , Centrality closeness , betweenness , eigenvector Topic Modelling 10 Topics trained on the dramas Number of scenes where figure is Actives present Number of Scenes where figure is Passives mentioned LastAct Is figure present in the last act? 10
Features Feature Name Description Character speech, normalised on Tokens whole text Different measures: (weighted) degree , Centrality closeness , betweenness , eigenvector Topic Modelling 10 Topics trained on the dramas Number of scenes where figure is Actives present Number of Scenes where figure is Passives mentioned LastAct Is figure present in the last act? NumberFig In respective drama 10
Features Feature Name Description Character speech, normalised on Tokens whole text Different measures: (weighted) degree , Centrality closeness , betweenness , eigenvector Topic Modelling 10 Topics trained on the dramas Number of scenes where figure is Actives present Number of Scenes where figure is Passives mentioned LastAct Is figure present in the last act? NumberFig In respective drama e.g. Weimar Classicism , Bourgeois Genre Tragedy , Naturalism , etc. 10
https://en.wikipedia.org/wiki/Centrality Centrality Figure 1: A) Betweenness centrality, B) Closeness centrality, C) Eigenvector centrality, D) Degree centrality. Source: 11
Three annotators Each data point represents a character in a play Arrays of feature values Class: P (Title character) / C (Not title character) Example Emilia: {tokens=0.09, actives=0.16, ..., Random forest class=P} Experimental Setup 114 dramas in our corpus 12
Recommend
More recommend
