Improving Sentence Completion in Dialogues with Multi-Modal Features

نویسندگان

  • Anruo Wang
  • Barbara Di Eugenio
  • Lin Chen
چکیده

With the aim of investigating how humans understand each other through language and gestures, this paper focuses on how people understand incomplete sentences. We trained a system based on interrupted but resumed sentences, in order to find plausible completions for incomplete sentences. Our promising results are based on multi-modal features.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Hybridization of Facial Features and Use of Multi Modal Information for 3D Face Recognition

Despite of achieving good performance in controlled environment, the conventional 3D face recognition systems still encounter problems in handling the large variations in lighting conditions, facial expression and head pose The humans use the hybrid approach to recognize faces and therefore in this proposed method the human face recognition ability is incorporated by combining global and local ...

متن کامل

Stability-Weighted Matrix Completion of Incomplete Multi-modal Data for Disease Diagnosis

Effective utilization of heterogeneous multi-modal data for Alzheimer's Disease (AD) diagnosis and prognosis has always been hampered by incomplete data. One method to deal with this is low-rank matrix completion (LRMC), which simultaneous imputes missing data features and target values of interest. Although LRMC yields reasonable results, it implicitly weights features from all the modalities ...

متن کامل

Public Transport Ontology for Passenger Information Retrieval

Passenger information aims at improving the user-friendliness of public transport systems while influencing passenger route choices to satisfy transit user’s travel requirements. The integration of transit information from multiple agencies is a major challenge in implementation of multi-modal passenger information systems. The problem of information sharing is further compounded by the multi-l...

متن کامل

Co-reference via Pointing and Haptics in Multi-Modal Dialogues

This paper describes our ongoing work on resolving third person pronouns and deictic words in a multi-modal corpus. We show that about two thirds of these referring expressions have antecedents that are introduced by pointing gestures or by haptic-ostensive actions (actions that involve manipulating an object). After describing our annotation scheme, we discuss the co-reference models we learn ...

متن کامل

Anaphora Resolution Using Extended Centering Algorithm In A Multi-Modal Dialogue System

Anaphora in multi-modal dialogues have different aspects compared to the anaphora in language-only dialogues. They often refer to the items signified by a gesture or by visual means. In this paper, we define two kinds of anaphora: screen anaphora and referring anaphora, and propose two general methods to resolve these anaphora. One is a simple mapping algorithm that can find items refetxed with...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012