Results 21 to 30 of about 544,328 (310)
SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization [PDF]
Conference on Empirical Methods in Natural Language Processing, 2019 This paper introduces the SAMSum Corpus, a new dataset with abstractive dialogue summaries. We investigate the challenges it poses for automated summarization by testing several models and comparing their results with those obtained on a corpus of news ...
Bogdan Gliwa +3 more
semanticscholar +1 more source
Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset [PDF]
AAAI Conference on Artificial Intelligence, 2019 Virtual assistants such as Google Assistant, Alexa and Siri provide a conversational interface to a large number of services and APIs spanning multiple domains.
Abhinav Rastogi +4 more
semanticscholar +1 more source
MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines [PDF]
NLP4CONVAI, 2020 MultiWOZ is a well-known task-oriented dialogue dataset containing over 10,000 annotated dialogues spanning 8 domains. It is extensively used as a benchmark for dialogue state tracking. However, recent works have reported presence of substantial noise in
Xiaoxue Zang +3 more
semanticscholar +1 more source
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems [PDF]
Annual Meeting of the Association for Computational Linguistics, 2019 Over-dependence on domain ontology and lack of sharing knowledge across domains are two practical and yet less studied problems of dialogue state tracking.
Chien-Sheng Wu +5 more
semanticscholar +1 more source
TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue [PDF]
Conference on Empirical Methods in Natural Language Processing, 2020 The use of pre-trained language models has emerged as a promising direction for improving dialogue systems. However, the underlying difference of linguistic patterns between conversational data and general text makes the existing pre-trained language ...
Chien-Sheng Wu +3 more
semanticscholar +1 more source
FaithDial: A Faithful Benchmark for Information-Seeking Dialogue [PDF]
Transactions of the Association for Computational Linguistics, 2022 The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources. However, dialogue systems often produce unsupported utterances, a phenomenon known as hallucination.
Nouha Dziri +6 more
semanticscholar +1 more source
Deep Reinforcement Learning for Dialogue Generation [PDF]
Conference on Empirical Methods in Natural Language Processing, 2016 Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes.
Jiwei Li +5 more
semanticscholar +1 more source
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models [PDF]
AAAI Conference on Artificial Intelligence, 2015 We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up the ...
Iulian Serban +4 more
semanticscholar +1 more source
Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Emotion detection in dialogues is challenging as it often requires the identification of thematic topics underlying a conversation, the relevant commonsense knowledge, and the intricate transition patterns between the affective states.
Lixing Zhu +4 more
semanticscholar +1 more source
Generative Spoken Dialogue Language Modeling [PDF]
Transactions of the Association for Computational Linguistics, 2022 We introduce dGSLM, the first “textless” model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on ...
Tu Nguyen +10 more
semanticscholar +1 more source