Results 1 - 10 of 61

Deep Learning of Knowledge Graph Embeddings for Semantic Parsing of Twitter Dialogs

by Larry Heck , Hongzhao Huang
"... Abstract-This paper presents a novel method to learn neural knowledge graph embeddings. The embeddings are used to compute semantic relatedness in a coherence-based semantic parser. The approach learns embeddings directly from structured knowledge representations. A deep neural network approach kno ..."
Abstract - Add to MetaCart
known as Deep Structured Semantic Modeling (DSSM) is used to scale the approach to learn neural embeddings for all of the concepts (pages) of Wikipedia. Experiments on Twitter dialogs show a 23.6% reduction in semantic parsing errors compared to the state-of-the-art unsupervised approach.

The SJTU System for Dialog State Tracking Challenge 2

by Kai Sun, Lu Chen, Su Zhu, Kai Yu
"... Dialog state tracking challenge provides a common testbed for state tracking al-gorithms. This paper describes the SJTU system submitted to the second Dialogue State Tracking Challenge in detail. In the system, a statistical semantic parser is used to generate refined semantic hypothe-ses. A large n ..."
Abstract - Add to MetaCart
Dialog state tracking challenge provides a common testbed for state tracking al-gorithms. This paper describes the SJTU system submitted to the second Dialogue State Tracking Challenge in detail. In the system, a statistical semantic parser is used to generate refined semantic hypothe-ses. A large

Multi-domain learning and generalization in dialog state tracking

by Jason D Williams - In Proceedings of SIGDIAL , 2013
"... Abstract Statistical approaches to dialog state tracking synthesize information across multiple turns in the dialog, overcoming some speech recognition errors. When training a dialog state tracker, there is typically only a small corpus of well-matched dialog data available. However, often there is ..."
Abstract - Cited by 6 (1 self) - Add to MetaCart
Abstract Statistical approaches to dialog state tracking synthesize information across multiple turns in the dialog, overcoming some speech recognition errors. When training a dialog state tracker, there is typically only a small corpus of well-matched dialog data available. However, often

Latent semantic modeling for slot filling in conversational understanding.

by Gokhan Tur , Asli Celikyilmaz , Dilek Hakkani-Tür - In Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), , 2013
"... ABSTRACT In this paper, we propose a new framework for semantic template filling in a conversational understanding (CU) system. Our method decomposes the task into two steps: latent n-gram clustering using a semi-supervised latent Dirichlet allocation (LDA) and sequence tagging for learning semanti ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
semantic structures in a CU system. Latent semantic modeling has been investigated to improve many natural language processing tasks such as syntactic parsing or topic tracking. However, due to several complexity problems caused by issues involving utterance length or dialog corpus size, it has not been

Recipe For Building Robust Spoken Dialog State Trackers: Dialog State Tracking Challenge System Description

by Sungjin Lee, Maxine Eskenazi , 2013
"... For robust spoken conversational interaction, many dialog state tracking algorithms have been developed. Few studies, however, have reported the strengths and weaknesses of each method. The Dialog State Tracking Challenge (DSTC) is designed to address this issue by comparing various methods on the s ..."
Abstract - Cited by 8 (2 self) - Add to MetaCart
For robust spoken conversational interaction, many dialog state tracking algorithms have been developed. Few studies, however, have reported the strengths and weaknesses of each method. The Dialog State Tracking Challenge (DSTC) is designed to address this issue by comparing various methods

Word-based Dialog State Tracking with Recurrent Neural Networks

by Matthew Henderson, Blaise Thomson, Steve Young - in Proceedings of SIGdial , 2014
"... Recently discriminative methods for track-ing the state of a spoken dialog have been shown to outperform traditional generative models. This paper presents a new word-based tracking method which maps di-rectly from the speech recognition results to the dialog state without using an explicit semantic ..."
Abstract - Cited by 5 (4 self) - Add to MetaCart
semantic decoder. The method is based on a recurrent neural network structure which is capable of generalising to unseen dialog state hypotheses, and which requires very little feature engineering. The method is evaluated on the second Dialog State Tracking Challenge (DSTC2) corpus and the results

Copenhagen-Malmö: Tree Approximations of Semantic Parsing Problems

by Natalie Schluter, Jakob Elming, Sigrid Klerke, Dirk Hovy, Barbara Plank, Anders Johannsen, Anders Søgaard
"... In this shared task paper for SemEval-2014 Task 8, we show that most se-mantic structures can be approximated by trees through a series of almost bijective graph transformations. We transform in-put graphs, apply off-the-shelf methods from syntactic parsing on the resulting trees, and retrieve outpu ..."
Abstract - Add to MetaCart
output graphs. Us-ing tree approximations, we obtain good results across three semantic formalisms, with a 15.9 % error reduction over a state-of-the-art semantic role labeling system on development data. Our system came in 3/6 in the shared task closed track. 1

Automatic Classification of Dialog Acts with Semantic Classification Trees and Polygrams

by Marion Mast, Heinrich Niemann, Elmar Nöth, Ernst Günter Schukat-Talamazzini - CONNECTIONIST, STATISTICAL AND SYMBOLIC APPROACHES TO LEARNING FOR NATURAL LANGUAGE PROCESSING , 1995
"... This paper presents automatic methods for the classification of dialog acts. In the verbmobil application (speech-to-speech translation of face-to-face dialogs) maximally 50 % of the utterances are analyzed in depth and for the rest, shallow processing takes place. The dialog component keeps track o ..."
Abstract - Cited by 11 (0 self) - Add to MetaCart
This paper presents automatic methods for the classification of dialog acts. In the verbmobil application (speech-to-speech translation of face-to-face dialogs) maximally 50 % of the utterances are analyzed in depth and for the rest, shallow processing takes place. The dialog component keeps track

Conversations in the Crowd: Collecting Data for Task-Oriented Dialog Learning

by Walter S Lasecki , Ece Kamar , Dan Bohus , Asi Group
"... Abstract A major challenge in developing dialog systems is obtaining realistic data to train the systems for specific domains. We study the opportunity for using crowdsourcing methods to collect dialog datasets. Specifically, we introduce ChatCollect, a system that allows researchers to collect con ..."
Abstract - Add to MetaCart
conversations focused around definable tasks from pairs of workers in the crowd. We demonstrate that varied and in-depth dialogs can be collected using this system, then discuss ongoing work on creating a crowd-powered system for parsing semantic frames. We then discuss research opportunities in using

From conversational tooltips to grounded discourse: head pose tracking in interactive dialog systems

by Trevor Darrell - Proceedings of the International Conference on Multi-modal Interfaces , 2004
"... Head pose and gesture offer several key conversational grounding cues and are used extensively in face-to-face interaction among people. While the machine interpretation of these cues has previously been limited to output modalities, recent advances in facepose tracking allow for systems which are r ..."
Abstract - Cited by 7 (1 self) - Add to MetaCart
Head pose and gesture offer several key conversational grounding cues and are used extensively in face-to-face interaction among people. While the machine interpretation of these cues has previously been limited to output modalities, recent advances in facepose tracking allow for systems which
Results 1 - 10 of 61