Filters








143 Hits in 5.6 sec

Unsupervised Enrichment of Persona-grounded Dialog with Background Stories [article]

Bodhisattwa Prasad Majumder, Taylor Berg-Kirkpatrick, Julian McAuley, Harsh Jhamtani
2021 arXiv   pre-print
In this work, we equip dialog models with 'background stories' related to a persona by leveraging fictional narratives from existing story datasets (e.g. ROCStories).  ...  Since current dialog datasets do not contain such narratives as responses, we perform an unsupervised adaptation of a retrieved story for generating a dialog response using a gradient-based rewriting technique  ...  Findings and observations are of the authors only and do not necessarily reflect the views of the funding agencies.  ... 
arXiv:2106.08364v1 fatcat:nis6cwddfneivn7n3ndmyffjlm

Unsupervised Enrichment of Persona-grounded Dialog with Background Stories

Bodhisattwa Prasad Majumder, Taylor Berg-Kirkpatrick, Julian McAuley, Harsh Jhamtani
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)   unpublished
In this work, we equip dialog models with 'background stories' related to a persona by leveraging fictional narratives from existing story datasets (e.g. ROC-Stories).  ...  Since current dialog datasets do not contain such narratives as responses, we perform an unsupervised adaptation of a retrieved story for generating a dialog response using a gradient-based rewriting technique  ...  Findings and observations are of the authors only and do not necessarily reflect the views of the funding agencies.  ... 
doi:10.18653/v1/2021.acl-short.74 fatcat:4umvve6jibhkznmsdtq7vi6kay

Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation [article]

Varun Gangal, Harsh Jhamtani, Eduard Hovy, Taylor Berg-Kirkpatrick
2021 arXiv   pre-print
We demonstrate that our automatically expanded reference sets lead to large improvements in correlations of automated metrics with human ratings of system outputs for DailyDialog dataset.  ...  More specifically, we use (1) a commonsense knowledge base to elicit a large number of plausible reactions given the dialog history (2) relevant instances retrieved from dialog corpus, using similar past  ...  Unsupervised enrichment of persona- grounded dialog with background stories. In ACL. Like hiking? you probably enjoy nature: Persona- grounded dialog with commonsense expansions.  ... 
arXiv:2106.02833v1 fatcat:46fppdxzfvhexj5yod2qbpk7o4

Pretrained Language Models for Text Generation: A Survey [article]

Junyi Li, Tianyi Tang, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen
2022 arXiv   pre-print
The resurgence of deep learning has greatly advanced this field, in particular, with the help of neural generation models based on pre-trained language models (PLMs).  ...  We begin with introducing three key aspects of applying PLMs to text generation: 1) how to encode the input into representations preserving input semantics which can be fused into PLMs; 2) how to design  ...  [120] first trained models on large-scale ungrounded dialogs and unstructured knowledge base separately to improve the low-resource knowledge-grounded dialog generation task. Data Augmentation.  ... 
arXiv:2201.05273v4 fatcat:pnffabspsnbhvo44gbaorhxc3a

Deep Learning for Text Style Transfer: A Survey [article]

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 arXiv   pre-print
We also provide discussions on a variety of important topics regarding the future development of this task. Our curated paper list is at https://github.com/zhijing-jin/Text_Style_Transfer_Survey  ...  We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data.  ...  As future work, text style transfer can also be used as part of the pipeline of persona-based dialog generation, where the persona can be categorized into distinctive style types, and then the generated  ... 
arXiv:2011.00416v5 fatcat:wfw3jfh2mjfupbzrmnztsqy4ny

Building A User-Centric and Content-Driven Socialbot [article]

Hao Fang
2020 arXiv   pre-print
Finally, observing that socialbots suffer from the issue of shallow conversations about topics associated with unstructured data, we study the problem of enabling extended socialbot conversations grounded  ...  An important contribution of the system is the synergy between the knowledge base and the dialog management, i.e., the use of a graph structure to organize the knowledge base that makes dialog control  ...  algorithm [178] , both of which are based on unsupervised extractive summarization.  ... 
arXiv:2005.02623v1 fatcat:oxsgfakzbzb7njqgfileddlsry

A Metaverse: taxonomy, components, applications, and open challenges

Sang-Min Park, Young-Gab Kim
2022 IEEE Access  
With the technological development of deep learning-based high-precision recognition models and natural generation models, Metaverse is being strengthened with various factors, from mobile-based always-on  ...  access to connectivity with reality using virtual currency.  ...  Entity-based expansion is a way to enrich user personas by increasing the number of entities.  ... 
doi:10.1109/access.2021.3140175 fatcat:fnraeaz74vh33knfvhzrynesli

Deep Learning for Text Style Transfer: A Survey

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 Computational Linguistics  
We also provide discussions on a variety of important topics regarding the future development of this task.  ...  We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data.  ...  As future work, text style transfer can also be used as part of the pipeline of persona-based dialog generation, where the persona can be categorized into distinctive style types, and then the generated  ... 
doi:10.1162/coli_a_00426 fatcat:v7vmb62ckfcu5k5mpu2pydnrxy

Conversational artificial intelligence - demystifying statistical vs linguistic NLP solutions

Kulvinder Panesar
2020 Journal of Computer-Assisted Linguistic Research  
This paper aims to demystify the hype and attention on chatbots and its association with conversational artificial intelligence.  ...  To demonstrate this, a deep linguistically aware and knowledge aware text based conversational agent (LING-CSA) presents a proof-of-concept of a non-statistical conversational AI solution.  ...  A later unsupervised technique requires no human scoring, but a metric with (1) a referenced part to measure the overlap between the system response and the ground truth, and (2) an unreferenced part to  ... 
doi:10.4995/jclr.2020.12932 fatcat:oogpuyd6zvhixi22k33xawe3dm

Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods [article]

Wei Li, Wenhao Wu, Moye Chen, Jiachen Liu, Xinyan Xiao, Hua Wu
2022 arXiv   pre-print
In this survey, we provide a systematic overview of the research progress on the faithfulness problem of NLG, including problem analysis, evaluation metrics and optimization methods.  ...  Natural Language Generation (NLG) has made great progress in recent years due to the development of deep learning techniques such as pre-trained language models.  ...  Different from other generation tasks like text summarization, various forms of dialog generation tasks include a diversity of background or knowledge inputs, with which the generated utterances should  ... 
arXiv:2203.05227v1 fatcat:q2u3ojyi6vb7pjt6ajwbinjmpa

Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey [article]

Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, Erik Cambria
2022 arXiv   pre-print
As a result, a multitude of novel works on this task are carried out, and most of them are deep learning based due to the outstanding performance.  ...  Specifically, from the angle of model type, we discuss the principles, characteristics, and applications of different models that are widely used in dialogue systems.  ...  In knowledge-grounded systems, RNNs are encoders of outside knowledge sources (e.g., background, persona, topic, etc.) Majumder et al., 2020b; Chen et al., 2020b; Cho and May, 2020) .  ... 
arXiv:2105.04387v5 fatcat:yd3gqg45rjgzxbiwfdlcvf3pye

A Survey of Knowledge-Enhanced Text Generation [article]

Wenhao Yu, Chenguang Zhu, Zaitang Li, Zhiting Hu, Qingyun Wang, Heng Ji, Meng Jiang
2022 arXiv   pre-print
The goal of text generation is to make machines express in human language. It is one of the most important yet challenging tasks in natural language processing (NLP).  ...  In this survey, we present a comprehensive review of the research on knowledge enhanced text generation over the past five years.  ...  Keeping a conversation grounded on a background document is referred as background based conversation (BBC) [9, 85] . Background knowledge plays an important role in human-human conversations.  ... 
arXiv:2010.04389v3 fatcat:vzdtlz4j65g2va7gwkbmzyxkhq

Knowledge-based Conversational Search [article]

Svitlana Vakulenko
2019 arXiv   pre-print
between utterances as well as domain-specific implicit semantic relations from shared background knowledge.  ...  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  ...  We mark values with italics in dialogs: e.g., education, or The City of Vienna.  ... 
arXiv:1912.06859v1 fatcat:rab6kemqujflrobib7lvvy6hue

Ethical and Methodological Issues in Gang Ethnography in the Digital Age: Lessons from Four Studies in an Emerging Field [chapter]

Marta-Marika Urbanik, Robby Roks, Michelle Lyttle Storrod, James Densley
2020 Gangs in the Era of Internet and Social Media  
with a migratory background.  ...  Across the groups, 90-95% of the members were male with a lower educational background, and, except for the biker gangs, the proportion of individuals with a foreign background was much lower than average  ...  In accordance with the Eurogang definition of gang membership, this chapter will focus on juvenile and young adult populations (Weerman et al., 2010  ... 
doi:10.1007/978-3-030-47214-6_2 fatcat:r6q4zplcbnc63b46lgkx76iz3u

Legal Narratives, Therapeutic Narratives: The Invisibility and Omnipresence of Race and Gender

Leslie G. Espinoza
1997 Michigan law review  
And yet the construction of a legal story, the obtaining of the facts, the structuring and development of the background of the case, requires the client to build a narrative.26 And like it or not, the  ...  Alisa, pulling herself together on the tape, then explained that LAB would need some general background information on the his tory of Denise's relationship with Robert.  ... 
doi:10.2307/1290049 fatcat:i7wnr7wg35e5jihz4ssp53rl34
« Previous Showing results 1 — 15 out of 143 results