State-of-the-art in several areas of NLP: Difference between revisions

From HLT@INESC-ID

No edit summary
 
No edit summary
 
Line 83: Line 83:
</tr>
</tr>
</table>
</table>
[[category:Seminars]]
[[category:Seminars 2009]]

Latest revision as of 13:25, 21 May 2009

Date

  • 15:00, May 15, 2009
  • Room 336

Program

State-of-the-Art Techniques for Question Analysis

Ana Cristina Mendes
Ana Cristina Mendes

Question-Answering (QA) is the task of retrieving the correct and concise answer to questions posed in Natural Language, from large amounts of free-text documents. Being the first step on the typical architecture of QA systems, the analysis of questions plays a crucial role in the success of such systems: on one hand, the question analysis can greatly narrow down the search space by posing constraints to the answer; on the other hand, it is unlikely that a question will be properly answered if this step has performed poorly.

This presentation addresses the techniques employed in question analysis, under two different perspectives: question analysis will be decomposed in sub-tasks, for which the state-of-the-art techniques will be introduced; also, references will be made to question analysis in domains with different characteristics.

Speaker: Ana Cristina Mendes

Processing of interrogatives in European Portuguese

Helena Moniz
Helena Moniz

The aim of our proposal is twofold: i) to automatically identify and model the interrogative structures in spontaneous speech and ii) to discuss the weight of the linguistic features that best describe these structures.

Different proposals have been made related to the relative weight of several approaches: statistical methods, morphosyntactic features, prosodic parameters or combinations of the previous. The interrogative structures in languages such as English have already been described in great detail, while for European Portuguese this issue is still in much discussion. Even for well-studied languages, one of today’s challenges is to model interrogatives in order to account for more natural human-machine interactions, in speech recognition, speech synthesis, dialogue and conversational agents, question answering, machine translation, etc.

We will focus our study on the identification of interrogatives in broadcast news. Surface rich transcriptions of this kind of data are crucial to make the automatic recognition output intelligible for hearing-impaired people. The idiosyncratic nature of broadcast news provides us with complex information where interrogatives may have different pragmatic functions: e.g., to conduct interviews, to seek for confirmation, to request for more detail information, to readdress the previous question, to change topics of conversation, and thus structuring discourse into units of semantic sense. As literature exploring the interface prosody/pragmatic shows, intonation plays a major role in the distinction of these pragmatic functions.

Morphosyntactic information is also a key factor, mainly due to the fact that languages have subtypes of interrogatives accordingly to the scope/focus of the constituent that is been asked. They may be /total/, when all the content of the utterance is been questioned; or /Wh-questions/, when a specific constituent, /e.g./, the subject, is the focus of interrogation. In European Portuguese these distinctions at the morphosyntactic level are accompanied by different prosodic contours as well.

Speaker: Helena Moniz

Sistemas de Diálogo: estado da arte

José David Lopes
José David Lopes

Com esta apresentação pretende-se fazer um ponto da situação do desenvolvimento do sistemas de diálogo. A apresentação procurará descrever a evolução dos sistemas de diálogo, bem como as várias tipologias existentes. Apresentar-se-ão algumas situações da vida quotidiana em que os sistemas de diálogo foram aplicados. Por último, serão ainda apresentados alguns sistemas de diálogo citados na literatura, fazendo-se um ponto da situação das suas mais recentes evoluções.

Speaker: José David Lopes