A Machine Learning Approach to Extract Temporal Information from Texts in Swedish and Generate Animated 3D Scenes

Carsim is a program that automatically converts narratives into 3D scenes. Carsim considers authentic texts describing road accidents, generally collected from web sites of Swedish newspapers or transcribed from hand-written accounts by victims of accidents. One of the program’s key features is that it animates the generated scene to visualize events. To create a consistent animation, Carsim extracts the participants mentioned in a text and identifies what they do. In this paper, we focus on the extraction of temporal relations between actions. We first describe how we detect time expressions and events. We then present a machine learning technique to order the sequence of events identified in the narratives. We finally report the results we obtained. 1 Extraction of Temporal Information and Scene Visualization Carsim is a program that generates 3D scenes from narratives describing road accidents (Johansson et al., 2005; Dupuy et al., 2001). It considers authentic texts, generally collected from web sites of Swedish newspapers or transcribed from handwritten accounts by victims of accidents. One of Carsim’s key features is that it animates the generated scene to visualize events described in the narrative. The text below, a newspaper article with its translation into English, illustrates the goals and challenges of it. We bracketed the entities, time expressions, and events and we annotated them with identifiers, denoted respectively oi, tj , and ek: En {bussolycka}e1 i södra Afghanistan krävdee2 {på torsdagen}t1 {20 dödsoffer}o1 . Ytterligare {39 personer}o2 skadadese3 i olyckane4. Busseno3 {var på väg}e5 från Kandahar mot huvudstaden Kabul när deno4 under en omkörninge6 kördee7 av vägbanano5 och voltadee8, meddeladee9 general Salim Khan, biträdande polischef i Kandahar. TT-AFP & Dagens Nyheter, July 8, 2004 {20 persons}o1 diede2 in a {bus accident}e1 in southern Afghanistan {on Thursday}t1. In addition, {39 persons}o2 {were injured}e3 in the accidente4. The buso3 {was on its way}e5 from Kandahar to the capital Kabul when ito4 {drove off}e7 the roado5 while overtakinge6 and {flipped over}e8, saide9 General Salim Khan, assistant head of police in Kandahar. The text above, our translation. To create a consistent animation, the program needs to extract and understand who the participants are and what they do. In the case of the accident above, it has to: 1. Detect the involved physical entities o3, o4, and o5. 2. Understand that the pronoun o4 refers to o3. 3. Detect the events e6, e7, and e8.