tailieunhanh - Báo cáo khoa học: "Language Use: What can it Tell us?"

For 20 years, information extraction has focused on facts expressed in text. In contrast, this paper is a snapshot of research in progress on inferring properties and relationships among participants in dialogs, even though these properties/relationships need not be expressed as facts. For instance, can a machine detect that someone is attempting to persuade another to action or to change beliefs or is asserting their credibility? | Language Use What can it Tell us name name name address1 address1 address1 address2 address2 address2 address3 address3 address3 email email email Abstract For 20 years information extraction has focused on facts expressed in text. In contrast this paper is a snapshot of research in progress on inferring properties and relationships among participants in dialogs even though these properties relationships need not be expressed as facts. For instance can a machine detect that someone is attempting to persuade another to action or to change beliefs or is asserting their credibility We report results on both English and Arabic discussion forums. 1 Introduction Extracting explicitly stated information has been tested in MUC1 and ACE2 3 evaluations. For example for the text Mushaima a head of the opposition Haq movement an ACE system extracts the relation LeaderOf Mushaima a HaqMovement . In TREC QA3 systems answered questions . When was Mozart born for which the answer is contained in one or a few extracted text phrases. Sentiment analysis uses implicit meaning of text but has focused primarily on text known to be rich in opinions product reviews editorials and delves into only one aspect of implicit meaning. Our long-term goal is to predict social roles in informal group discussion from language uses LU even if those roles are not explicitly stated for example using the communication during a meeting identify the leader of a group. This paper provides a snapshot of preliminary ongoing research in predicting two classes of language use 1 http related_projects muc 2 http www. nist. gov speech tests ace 3 http data 341 Establish-Credibility and Attempt-To-Persuade. Technical challenges include dealing with the facts that those LUs are rare and subjective and that human judgments have low agreement. Our hybrid statistical rule-based approach detects those two LUs in English and Arabic. Our results are that 1 annotation at the .