11,583 Hits in 3.5 sec

Knowledge-based Conversational Search [article]

Svitlana Vakulenko
2019 arXiv   pre-print
Our results show that question answering is one of the key components required for efficient information access but it is not the only type of dialogue interactions that a conversational search system  ...  between utterances as well as domain-specific implicit semantic relations from shared background knowledge.  ...  Further research is needed to integrate semantic coherence criteria based on the graph structure as presented in Chapter 4.  ... 
arXiv:1912.06859v1 fatcat:rab6kemqujflrobib7lvvy6hue

Visual Semantics for Reducing False Positives in Video Search [chapter]

Rohini K. Srihari, Adrian Novischi
2012 Multimedia Information Extraction  
Significant progress has been made in text-based information extraction, which can be brought to bear for video search.  ...  This is useful in similarity search (i.e. searching by example), but has drawbacks when more semantic search is desired, e.g. find video clips of Obama meeting with ordinary citizens.  ...  Summary We have focused on the problem of granular and semantic searching of video, e.g. searching for specific events involving specific entities.  ... 
doi:10.1002/9781118219546.ch7 fatcat:zu3isvtusrc3rdpvtpdgu5zuui

An ontology-based semantic tagger for IE system

Narjès Boufaden
2003 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03  
In this paper, we present a method for the semantic tagging of word chunks extracted from a written transcription of conversations.  ...  This work is part of an ongoing project for an information extraction system in the field of maritime Search And Rescue (SAR).  ...  Thanks to the Defense Research Establishment Valcartier for providing us with the dialog transcriptions and to National Search and rescue Secretariat for the valuable SAR manuals.  ... 
doi:10.3115/1075178.1075179 dblp:conf/acl/Boufaden03 fatcat:atmykoado5gpje4pcr3dsaanty

End-To-End Named Entity And Semantic Concept Extraction From Speech

S. Ghannay, A. Caubriere, Y. Esteve, N. Camelin, E. Simonnet, A. Laurent, E. Morin
2018 2018 IEEE Spoken Language Technology Workshop (SLT)  
Named entity recognition (NER) is among SLU tasks that usually extract semantic information from textual documents.  ...  The results are promising since this end-to-end approach provides similar results (F-measure=0.66 on test data) than a classical pipeline approach to detect named entity categories (F-measure=0.64).  ...  Machine learning based systems do not have good performance when they are trained on perfect transcriptions and deployed to process ASR ones, even if that can be partially compensated by simulating ASR  ... 
doi:10.1109/slt.2018.8639513 dblp:conf/slt/GhannayCECSLM18 fatcat:57vt27wcpbdvvfvfrrtoz325na

Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems

Yun-Nung Chen
2015 Proceedings of the ACL-IJCNLP 2015 Student Research Workshop  
Searches can be based on metadata or on full-text (or other content-based) indexing.  ...  " face forms and entity contexts based on dependency-based entity embeddings.  ... 
doi:10.3115/v1/p15-3001 dblp:conf/acl/Chen15 fatcat:kfxqwlfgpfgl7maz25j42nebme

Semantic Structure in a Federated Collaboration Environment

John Buford, Venkatesh Krishnaswamy
2012 Proceedings of the 8th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing  
Recently we have extended ConnectedSpaces to enable spaces and their contents to have semantic properties.  ...  Different collaboration models are supported with different semantic structure. The design and implementation is described, and example illustrations are provided.  ...  The server is a set of extensions to the semantic wiki bundle produced by Ontoprise which is in turn based on the semantic wiki extension to mediawiki.  ... 
doi:10.4108/icst.collaboratecom.2012.250456 dblp:conf/colcom/BufordK12 fatcat:llnzcpckkbevfdypjhbchhefsu

Integration of automatic spatial annotations from different sources by means of semantic technologies

Javier Nogueras-Iso, Verónica Lázaro, Ludovic Moncla
2016 Scire. Representación y organización del conocimiento  
the conversion of the output of these tools into a common spatial annotation language based on semantic technologies to facilitate their integration and interoperability.  ...  As a common annotation language we propose the use of a text annotation based on RDFa and using the vocabulary proposed by the international initiative  ...  Acknowledgements This work has been partially funded by Universidad de Zaragoza through Catedra Logisman on Technological Document Management and UZ2016-TEC-05 research project.  ... 
doi:10.54886/scire.v22i2.4361 fatcat:kanc4eilgbgmhbim7bfwo53k2m

Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddings

Yun-Nung Chen, Alexander I. Rudnicky
2014 2014 IEEE Spoken Language Technology Workshop (SLT)  
However, current technology typically limits conversational interactions to a few narrow predefined domains/topics.  ...  Freebase, Wikipedia, FrameNet) to induce types of slots for generating semantic seeds, and enriches the semantics of spoken queries with neural word embeddings, where semantically related concepts can  ...  [18] , developed based on Frame Semantics [19] .  ... 
doi:10.1109/slt.2014.7078640 dblp:conf/slt/ChenR14 fatcat:i4b66ftgzfahbmcnlnh3ofz53q

Curriculum-Based Transfer Learning for an Effective End-to-End Spoken Language Understanding and Domain Portability

Antoine Caubrière, Natalia Tomashenko, Antoine Laurent, Emmanuel Morin, Nathalie Camelin, Yannick Estève
2019 Interspeech 2019  
To overcome the lack of data available for this spoken language understanding approach, we investigate the use of a transfer learning strategy based on the principles of curriculum learning.  ...  We present an end-to-end approach to extract semantic concepts directly from the speech audio signal.  ...  We assume that named entities recognition and slot filling task based on semantic concept extraction are very close SLU tasks and we assume that named entities are more generic semantic concepts than the  ... 
doi:10.21437/interspeech.2019-1832 dblp:conf/interspeech/CaubriereTLMCE19 fatcat:kid42a4pd5fatn2wzwrkdcfxni

Measuring Semantic Coherence of a Conversation [article]

Svitlana Vakulenko, Maarten de Rijke, Michael Cochez, Vadim Savenkov, Axel Polleres
2018 arXiv   pre-print
We introduce the task of measuring semantic (in)coherence in a conversation with respect to background knowledge, which relies on the identification of semantic relations between concepts introduced during  ...  We propose and evaluate graph-based and machine learning-based approaches for measuring semantic coherence using knowledge graphs, their vector space embeddings and word embedding models, as sources of  ...  For the top-k shortest path computation, we apply an approach based on bidirectional breadth-first search [25] using the space-efficient binary Header, Dictionary, Triples (HDT) encoding [11] of the  ... 
arXiv:1806.06411v1 fatcat:5htffhqbtndvxgpwq7jdx6bzu4

Semi-automatic conversion of BioProp semantic annotation to PASBio annotation

Richard Tsai, Hong-Jie Dai, Chi-Hsin Huang, Wen-Lian Hsu
2008 BMC Bioinformatics  
In previous work, we constructed a biomedical corpus based on the PropBank standard called BioProp, on which we developed an ML-based SRL system, BIOSMILE.  ...  Semantic role labeling (SRL) is an important text analysis technique. In SRL, sentences are represented by one or more predicate-argument structures (PAS).  ...  This work was expanded upon with the release of our web-based search application, BIOSMILE web search [15] , in February 2008.  ... 
doi:10.1186/1471-2105-9-s12-s18 pmid:19091017 pmcid:PMC2638158 fatcat:o5x5ni676raa3lfcqo7nh2cddm

A method for integrating and ranking the evidence for biochemical pathways by mining reactions from text

Makoto Miwa, Tomoko Ohta, Rafal Rak, Andrew Rowley, Douglas B. Kell, Sampo Pyysalo, Sophia Ananiadou
2013 Bioinformatics  
Our approach extracts the reactions directly from the models and then turns them into queries for three text mining-based MEDLINE literature search systems.  ...  We find that a Support Vector Machine-based system outperforms several baselines and matches the performance of the rule-based system.  ...  MEDIE is a search engine that can be used to query MEDLINE abstracts based on named entity recognition and normalized syntactic structures produced by deep parsing.  ... 
doi:10.1093/bioinformatics/btt227 pmid:23813008 pmcid:PMC3694679 fatcat:uisraousjjdv5a7c4fmh3odjhq

linkedISA: semantic representation of ISA-Tab experimental metadata

Alejandra González-Beltrán, Eamonn Maguire, Susanna-Assunta Sansone, Philippe Rocca-Serra
2014 BMC Bioinformatics  
We applied the conversion tool as part of Bio-GraphIIn, a web-based application supporting integration of the semantically-rich experimental descriptions.  ...  on user-provided ontology annotations in the experimental metadata.  ...  13th International Workshop on Network Tools and Applications in Biology (NETTAB 2013).  ... 
doi:10.1186/1471-2105-15-s14-s4 pmid:25472428 pmcid:PMC4255742 fatcat:3tpqrjmvp5hgpafasevv33rx2q

Towards a Platform for Curation Technologies: Enriching Text Collections with a Semantic-Web Layer [chapter]

Peter Bourgonje, Julian Moreno-Schneider, Jan Nehring, Georg Rehm, Felix Sasaki, Ankit Srivastava
2016 Lecture Notes in Computer Science  
In an attempt to put a Semantic Web-layer that provides linguistic analysis and discourse information on top of digital content, we develop a platform for digital curation technologies.  ...  Indexing entities also allows us to disambiguate based on entity clustering (planned for the next phase in this two-year project).  ...  Eventually we will also be able to handle the conversion of non-textual data into text (e. g., transcripts for audio, subtitles for video, etc.).  ... 
doi:10.1007/978-3-319-47602-5_14 fatcat:ez53ffo7zzgw7b37flh6rtdutm

Leveraging semantic web search and browse sessions for multi-turn spoken dialog systems

Lu Wang, Larry Heck, Dilek Hakkani-Tur
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We also achieve better performance for both entity and relation extraction on web search queries when compared with nontrivial baselines.  ...  Our session-based models outperform the state-of-the-art method for entity extraction task in SDS.  ...  As our models are trained on web search log in the film domain, we test them on the sessions of film-related tasks with manual transcripts.  ... 
doi:10.1109/icassp.2014.6854369 dblp:conf/icassp/WangHH14 fatcat:bragpfent5ayjnkmm5t34bs4dm
« Previous Showing results 1 — 15 out of 11,583 results