6533b7d3fe1ef96bd126165b

RESEARCH PRODUCT

Measuring Semantic Coherence of a Conversation

S. VakulenkoM. De RijkeM. CochezV. SavenkovA. PolleresD. VrandečićK. BontchevaM.c. Suárez-figueroaV. PresuttiI. CelinoM. SabouL.-a. KaffeeE. Simperl

subject

FOS: Computer and information sciencesWord embeddingComputer scienceComputer Science - Artificial Intelligencemedia_common.quotation_subjectihmisen ja tietokoneen vuorovaikutus02 engineering and technologycomputer.software_genrekeskustelu020204 information systems0202 electrical engineering electronic engineering information engineeringConversationconversational systemsmedia_commonComputer Science - Computation and Languagebusiness.industrykoneoppiminenArtificial Intelligence (cs.AI)Knowledge graphsemantiikkaGraph (abstract data type)020201 artificial intelligence & image processingArtificial intelligencebusinesssemantic coherencecomputerComputation and Language (cs.CL)Natural language processing

description

Conversational systems have become increasingly popular as a way for humans to interact with computers. To be able to provide intelligent responses, conversational systems must correctly model the structure and semantics of a conversation. 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 a conversation. 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 background knowledge. We demonstrate how these approaches are able to uncover different coherence patterns in conversations on the Ubuntu Dialogue Corpus.

yearjournalcountryeditionlanguage
2018-06-17
http://arxiv.org/abs/1806.06411