Results 11 to 20 of about 255,823 (171)

Summary Grounded Conversation Generation [PDF]

arXiv, 2021
Many conversation datasets have been constructed in the recent years using crowdsourcing. However, the data collection process can be time consuming and presents many challenges to ensure data quality. Since language generation has improved immensely in recent years with the advancement of pre-trained language models, we investigate how such models can
arxiv  

Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networks [PDF]

arXiv, 2022
While rich, open-domain textual data are generally available and may include interesting phenomena (humor, sarcasm, empathy, etc.) most are designed for language processing tasks, and are usually in a non-conversational format. In this work, we take a step towards automatically generating conversational data using Generative Conversational Networks ...
arxiv  

Conversational Entity Linking: Problem Definition and Datasets [PDF]

, 2021
Machine understanding of user utterances in conversational systems is of utmost importance for enabling engaging and meaningful conversations with users. Entity Linking (EL) is one of the means of text understanding, with proven efficacy for various downstream tasks in information retrieval.
arxiv   +1 more source

CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation [PDF]

arXiv, 2023
Conversational search provides a natural interface for information retrieval (IR). Recent approaches have demonstrated promising results in applying dense retrieval to conversational IR. However, training dense retrievers requires large amounts of in-domain paired data.
arxiv  

Reward-free Policy Imitation Learning for Conversational Search [PDF]

arXiv, 2023
Existing conversational search studies mainly focused on asking better clarifying questions and/or improving search result quality. These works aim at retrieving better responses according to the search context, and their performances are evaluated on either single-turn tasks or multi-turn tasks under naive conversation policy settings.
arxiv  

CODY: A graph-based framework for the analysis of COnversation DYnamics in online social networks [PDF]

arXiv, 2023
Conversations are an integral part of online social media, and gaining insights into these conversations is of significant value for many commercial as well as academic use cases. From a computational perspective, however, analyzing conversation data is complex, and numerous aspects must be considered.
arxiv  

Topic Segmentation and Labeling in Asynchronous Conversations [PDF]

Journal Of Artificial Intelligence Research, Volume 47, pages 521-573, 2013, 2014
Topic segmentation and labeling is often considered a prerequisite for higher-level conversation analysis and has been shown to be useful in many Natural Language Processing (NLP) applications. We present two new corpora of email and blog conversations annotated with topics, and evaluate annotator reliability for the segmentation and labeling tasks in ...
arxiv   +1 more source

Fast Conversion Algorithms for Orthogonal Polynomials [PDF]

, 2008
We discuss efficient conversion algorithms for orthogonal polynomials. We describe a known conversion algorithm from an arbitrary orthogonal basis to the monomial basis, and deduce a new algorithm of the same complexity for the converse operation.
arxiv   +1 more source

Ditch the Gold Standard: Re-evaluating Conversational Question Answering [PDF]

arXiv, 2021
Conversational question answering aims to provide natural-language answers to users in information-seeking conversations. Existing conversational QA benchmarks compare models with pre-collected human-human conversations, using ground-truth answers provided in conversational history.
arxiv  

Zero-Shot Joint Modeling of Multiple Spoken-Text-Style Conversion Tasks using Switching Tokens [PDF]

arXiv, 2021
In this paper, we propose a novel spoken-text-style conversion method that can simultaneously execute multiple style conversion modules such as punctuation restoration and disfluency deletion without preparing matched datasets. In practice, transcriptions generated by automatic speech recognition systems are not highly readable because they often ...
arxiv