Thesis presentation Event Extraction from Text and Translation to - PowerPoint PPT Presentation

Thesis presentation Event Extraction from Text and Translation to Event Calculus Geert Heyman June 2014 Geert Heyman (KULeuven) Thesis presentation June 2014 1 / 21

Outline Problem Definition & Goals 1 Approach 2 Extracting event information Translating event information Specifying background knowledge Making inferences about the story Results 3 Conclusions & Future Work 4 Geert Heyman (KULeuven) Thesis presentation June 2014 2 / 21

Outline Problem Definition & Goals 1 Approach 2 Extracting event information Translating event information Specifying background knowledge Making inferences about the story Results 3 Conclusions & Future Work 4 Geert Heyman (KULeuven) Thesis presentation June 2014 3 / 21

Problem Definition Understanding a story by: Geert Heyman (KULeuven) Thesis presentation June 2014 4 / 21

Problem Definition Understanding a story by: 1. Extracting event related information. Geert Heyman (KULeuven) Thesis presentation June 2014 4 / 21

Problem Definition Understanding a story by: 1. Extracting event related information. 2. Translating event related information to logic, using a fixed set a primitives (predicate,types). Geert Heyman (KULeuven) Thesis presentation June 2014 4 / 21

Problem Definition Understanding a story by: 1. Extracting event related information. 2. Translating event related information to logic, using a fixed set a primitives (predicate,types). 3. Specifying the meaning of the primitives in a logical theory (the background knowledge specification). Using event calculus Geert Heyman (KULeuven) Thesis presentation June 2014 4 / 21

Problem Definition Understanding a story by: 1. Extracting event related information. 2. Translating event related information to logic, using a fixed set a primitives (predicate,types). 3. Specifying the meaning of the primitives in a logical theory (the background knowledge specification). Using event calculus 4. Making inferences about the story by combining the obtained translation with the background knowledge specification Geert Heyman (KULeuven) Thesis presentation June 2014 4 / 21

Goals Make the extraction and translation steps more general. Geert Heyman (KULeuven) Thesis presentation June 2014 5 / 21

Goals Make the extraction and translation steps more general. Minimize the amount of story specific knowledge Geert Heyman (KULeuven) Thesis presentation June 2014 5 / 21

Goals Make the extraction and translation steps more general. Minimize the amount of story specific knowledge Specify the story setting (cities, train lines, ...) But don’t specify the characters, their intial locations, ... Geert Heyman (KULeuven) Thesis presentation June 2014 5 / 21

Goals Make the extraction and translation steps more general. Minimize the amount of story specific knowledge Specify the story setting (cities, train lines, ...) But don’t specify the characters, their intial locations, ... Make useful inferences: information implied by the text implicatures in the text (that what is suggested, but not implied) Geert Heyman (KULeuven) Thesis presentation June 2014 5 / 21

Outline Problem Definition & Goals 1 Approach 2 Extracting event information Translating event information Specifying background knowledge Making inferences about the story Results 3 Conclusions & Future Work 4 Geert Heyman (KULeuven) Thesis presentation June 2014 6 / 21

1. Extracting event information Geert Heyman (KULeuven) Thesis presentation June 2014 7 / 21

1. Extracting event information By assigning labels to words or phrases Geert Heyman (KULeuven) Thesis presentation June 2014 7 / 21

1. Extracting event information By assigning labels to words or phrases E.g., John enters enter . 01 the train. Geert Heyman (KULeuven) Thesis presentation June 2014 7 / 21

1. Extracting event information By assigning labels to words or phrases E.g., John enters enter . 01 the train. Combining two state-of-the-art extraction tools: TERENCE Semantic Role Labeller Geert Heyman (KULeuven) Thesis presentation June 2014 7 / 21

1. Extracting event information By assigning labels to words or phrases E.g., John enters enter . 01 the train. Combining two state-of-the-art extraction tools: TERENCE Semantic Role Labeller Does not rely on a stereotypical order of events → generally applicable Geert Heyman (KULeuven) Thesis presentation June 2014 7 / 21

1. Extracting event information: TERENCE Geert Heyman (KULeuven) Thesis presentation June 2014 8 / 21

1. Extracting event information: TERENCE Recognizes basic story elements and the relations between them: Geert Heyman (KULeuven) Thesis presentation June 2014 8 / 21

1. Extracting event information: TERENCE Recognizes basic story elements and the relations between them: Story entities and references to story entities Geert Heyman (KULeuven) Thesis presentation June 2014 8 / 21

1. Extracting event information: TERENCE Recognizes basic story elements and the relations between them: Story entities and references to story entities John entity mention → John forgot his entity mention → John wallet. Geert Heyman (KULeuven) Thesis presentation June 2014 8 / 21

1. Extracting event information: TERENCE Recognizes basic story elements and the relations between them: Story entities and references to story entities John entity mention → John forgot his entity mention → John wallet. Story events and their temporal relations Geert Heyman (KULeuven) Thesis presentation June 2014 8 / 21

1. Extracting event information: TERENCE Recognizes basic story elements and the relations between them: Story entities and references to story entities John entity mention → John forgot his entity mention → John wallet. Story events and their temporal relations AFTER John forgot event 1 his wallet, but an honest finder returned event 2 it. Geert Heyman (KULeuven) Thesis presentation June 2014 8 / 21

1. Extracting event information: Semantic Role Labeller Annotates words/constituents with syntactic and semantic information: Syntactic information: a syntactical dependence tree, word lemma’s Geert Heyman (KULeuven) Thesis presentation June 2014 9 / 21

1. Extracting event information: Semantic Role Labeller Annotates words/constituents with syntactic and semantic information: Syntactic information: a syntactical dependence tree, word lemma’s Semantic information: Geert Heyman (KULeuven) Thesis presentation June 2014 9 / 21

1. Extracting event information: Semantic Role Labeller Annotates words/constituents with syntactic and semantic information: Syntactic information: a syntactical dependence tree, word lemma’s Semantic information: Annotates predicates with their meaning Geert Heyman (KULeuven) Thesis presentation June 2014 9 / 21

1. Extracting event information: Semantic Role Labeller Annotates words/constituents with syntactic and semantic information: Syntactic information: a syntactical dependence tree, word lemma’s Semantic information: Annotates predicates with their meaning E.g., John enters enter . 01 the train. Geert Heyman (KULeuven) Thesis presentation June 2014 9 / 21

1. Extracting event information: Semantic Role Labeller Annotates words/constituents with syntactic and semantic information: Syntactic information: a syntactical dependence tree, word lemma’s Semantic information: Annotates predicates with their meaning E.g., John enters enter . 01 the train. Annotates the relationship that words/constituents have with a predicate. I.e. their semantic role. Geert Heyman (KULeuven) Thesis presentation June 2014 9 / 21

1. Extracting event information: Semantic Role Labeller Annotates words/constituents with syntactic and semantic information: Syntactic information: a syntactical dependence tree, word lemma’s Semantic information: Annotates predicates with their meaning E.g., John enters enter . 01 the train. Annotates the relationship that words/constituents have with a predicate. I.e. their semantic role. E.g., John A 0 of enter . 01 enters the train A 1 of enter . 01 . Geert Heyman (KULeuven) Thesis presentation June 2014 9 / 21

1. Extracting event information: Semantic Role Labeller Annotates words/constituents with syntactic and semantic information: Syntactic information: a syntactical dependence tree, word lemma’s Semantic information: Annotates predicates with their meaning E.g., John enters enter . 01 the train. Annotates the relationship that words/constituents have with a predicate. I.e. their semantic role. E.g., John A 0 of enter . 01 enters the train A 1 of enter . 01 . The tool output distributions of possible labels for a token, instead of a single one. Geert Heyman (KULeuven) Thesis presentation June 2014 9 / 21

1. Extracting event information: TERENCE + Semantic Role Labeller Geert Heyman (KULeuven) Thesis presentation June 2014 10 / 21

2. Translating event information Geert Heyman (KULeuven) Thesis presentation June 2014 11 / 21

2. Translating event information For every event annotated by TERENCE: 1. Translate the temporal relations associated with the event Geert Heyman (KULeuven) Thesis presentation June 2014 11 / 21