A Machine Learning Approach to Extract Temporal Information from Texts in Swedish and Generate Animated 3D Scenes
نویسندگان
چکیده
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.
منابع مشابه
Extraction of Temporal Information from Texts in Swedish
This paper describes the implementation and evaluation of a generic component to extract temporal information from texts in Swedish. It proceeds in two steps. The first step extracts time expressions and events, and generates a feature vector for each element it identifies. Using the vectors, the second step determines the temporal relations, possibly none, between the extracted events and orde...
متن کاملConverting Texts of Road Accidents into 3D Scenes
This paper describes a system to create animated 3D scenes of car accidents from reports written in Swedish. The system has been developed using news reports of varying size and complexity. The text-to-scene conversion process consists of two stages. An information extraction module creates a tabular description of the accident and a visual simulator generates and animates the scene.
متن کاملCarsim: A System to Convert Written Accident Reports into Animated 3D Scenes
This paper describes a system to create animated 3D scenes of car accidents from reports written in Swedish. The system has been developed using news reports of varying size and complexity. The text-to-scene conversion process consists of two stages. An information extraction module creates a tabular description of the accident and a visual simulator generates and animates the scene. We first d...
متن کاملCarsim: A System To Visualize Written Road Accident Reports As Animated 3D Scenes
This paper describes a system to create animated 3D scenes of car accidents from reports written in Swedish. The system has been developed using news reports of varying size and complexity. The text-to-scene conversion process consists of two stages. An information extraction module creates a structured representation of the accident and a visual simulator generates and animates the scene. We f...
متن کاملGeoreferencing Semi-Structured Place-Based Web Resources Using Machine Learning
In recent years, the shared content on the web has had significant growth. A great part of these information are publicly available in the form of semi-strunctured data. Moreover, a significant amount of these information are related to place. Such types of information refer to a location on the earth, however, they do not contain any explicit coordinates. In this research, we tried to georefer...
متن کامل