Filters








25,974 Hits in 5.0 sec

A Compare Aggregate Transformer for Understanding Document-grounded Dialogue [article]

Longxuan Ma and Weinan Zhang and Runxin Sun and Ting Liu
2020 arXiv   pre-print
In this paper, we propose a Compare Aggregate Transformer (CAT) to jointly denoise the dialogue context and aggregate the document information for response generation.  ...  In addition, we propose two metrics for evaluating document utilization efficiency based on word overlap.  ...  In this paper, we propose a novel Transformer-based [28] model for understanding the dialogues and generate informative responses in the DGD, named Compare Aggregate Transformer (CAT).  ... 
arXiv:2010.00190v1 fatcat:3dmytwlto5afzget7f3yz6orb4

A Compare Aggregate Transformer for Understanding Document-grounded Dialogue

Longxuan Ma, Wei-Nan Zhang, Runxin Sun, Ting Liu
2020 Findings of the Association for Computational Linguistics: EMNLP 2020   unpublished
In this paper, we propose a Compare Aggregate Transformer (CAT) to jointly denoise the dialogue context and aggregate the document information for response generation.  ...  In addition, we propose two metrics for evaluating document utilization efficiency based on word overlap.  ...  Conclusion We propose the Compare Aggregate method to understand Document-grounded Dialogue (DGD). The dialogue is divided into the last utterance and the dialogue history.  ... 
doi:10.18653/v1/2020.findings-emnlp.122 fatcat:ld53czcf6jd35bve6xpnd2tgdy

Exploiting Text Matching Techniques for Knowledge-Grounded Conversation

Yeonchan Ahn, Sang-Goo Lee, Jaehui Park
2020 IEEE Access  
Knowledge-grounded conversation models aim at generating informative responses for the given dialogue context, based on external knowledge.  ...  Also, our best model based on Reduce-Match outperforms them with the CMU Document Grounded Conversations dataset.  ...  It is collected from crowd-sourced workers' conversations grounded on documents regarding movies. This online 3 dataset comprises 3,373 dialogues for training, 229 for validation, and 619 for test.  ... 
doi:10.1109/access.2020.3007893 fatcat:jyu3rvorwjhbrfsjafnwct5eiu

G^2: Enhance Knowledge Grounded Dialogue via Ground Graph [article]

Yizhe Yang, Yang Gao, Jiawei Li, Heyan Huang
2022 arXiv   pre-print
Besides, a Ground Graph Aware Transformer (G^2AT) is proposed to enhance knowledge grounded response generation.  ...  Knowledge grounded dialogue system is designed to generate responses that convey information from given knowledge documents.  ...  Given the ground-truth response Y = [y 1 , y 2 , . . . , y n ] for a dialogue context C, a sequence of knowledge documents KD, and a G 2 KG.  ... 
arXiv:2204.12681v1 fatcat:4344dnprsregrhvjdxlxtdieda

Beyond Aggregation: "The Wisdom of Crowds" Meets Dialogue in the Case Study of Shaping America's Youth

Renee G. Heath, Ninon Lewis, Brit Schneider, Elisa Majors
2017 Journal of Deliberative Democracy  
Accordingly this study has implications for deliberative practice as it provides a heuristic for eliciting the voice of nonexperts.  ...  In particular we describe empirically grounded dialogic principles that underlay a successful participation process: voice, diversity, transparency, preparedness, and neutrality.  ...  Additionally we are grateful to Kenneth Cissna and anonymous reviewers for their advice on this manuscript.  ... 
doi:10.16997/jdd.279 fatcat:zihierrd7ffzbpq4avl5rtnx3u

Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation [article]

Feilong Chen, Fandong Meng, Xiuyi Chen, Peng Li, Jie Zhou
2021 arXiv   pre-print
Visual dialogue is a challenging task since it needs to answer a series of coherent questions on the basis of understanding the visual environment.  ...  Therefore, in this paper we propose a Multimodal Incremental Transformer with Visual Grounding, named MITVG, which consists of two key parts: visual grounding and multimodal incremental transformer.  ...  devise an incremental transformer to encode multi-turn utterances along with knowledge in related documents for document grounded conversations.  ... 
arXiv:2109.08478v1 fatcat:4eyihunr7ngvzfciezw7qxlxkq

DAPPER: Learning Domain-Adapted Persona Representation Using Pretrained BERT and External Memory

Prashanth Vijayaraghavan, Eric Chu, Deb Roy
2020 International Joint Conference on Natural Language Processing  
Research in building intelligent agents have emphasized the need for understanding characteristic behavior of people.  ...  Our comparative study demonstrates the capability of our method over other approaches towards learning rich transferable persona embeddings.  ...  Here, a document refers to a list of sentences from the personal essays or forum Posts corpus and dialogue snippets in case of movies dialogue corpus (explained in Section 3).  ... 
dblp:conf/ijcnlp/VijayaraghavanC20 fatcat:a2begbciafbpvkcy4sg7huxjju

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
In this survey, we present a comprehensive review of the research on knowledge enhanced text generation over the past five years.  ...  The main content includes two parts: (i) general methods and architectures for integrating knowledge into text generation; (ii) specific techniques and applications according to different forms of knowledge  ...  To compare with RNN-Seq2Seq, we summarize the Transformer decoder using recurrent notation: S = Transformer-Decoder(S −1 , e( −1 ), H), (8) where S = [(K (1) , V (1) ), · · · , (K ( ) , V ( ) )], where  ... 
arXiv:2010.04389v3 fatcat:vzdtlz4j65g2va7gwkbmzyxkhq

Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection

Sheng-syun Shen, Hung-Yi Lee
2016 Interspeech 2016  
In the sequence labeling tasks, the model input is a sequence, and the output is the label of the input sequence.  ...  In this paper, neural attention model is applied on two sequence labeling tasks, dialogue act detection and key term extraction.  ...  The MAP score for a set of documents is the mean of the average precision scores for each document.  ... 
doi:10.21437/interspeech.2016-1359 dblp:conf/interspeech/ShenL16 fatcat:tm6tusaplvan5jqz6dznvrc5c4

Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection [article]

Sheng-syun Shen, Hung-yi Lee
2016 arXiv   pre-print
In the sequence labeling tasks, the model input is a sequence, and the output is the label of the input sequence.  ...  In this paper, neural attention model is applied on two sequence classification tasks, dialogue act detection and key term extraction.  ...  The MAP score for a set of documents is the mean of the average precision scores for each document.  ... 
arXiv:1604.00077v1 fatcat:yj3h24r2gvgrdffoc4lvtwc3gq

A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots [article]

Xueliang Zhao, Chongyang Tao, Wei Wu, Can Xu, Dongyan Zhao, Rui Yan
2019 arXiv   pre-print
We present a document-grounded matching network (DGMN) for response selection that can power a knowledge-aware retrieval-based chatbot system.  ...  The challenges of building such a model lie in how to ground conversation contexts with background documents and how to recognize important information in the documents for matching.  ...  Figure 1 : 1 Architecture of the document-grounded matching network. Transformer: a variant of the model proposed by Vaswani et al. (2017) for machine translation.  ... 
arXiv:1906.04362v1 fatcat:5m3sz6nlajggbfurmrdfs3bziq

Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization [article]

Jiaao Chen, Diyi Yang
2020 arXiv   pre-print
Experiments on a large-scale dialogue summarization corpus demonstrated that our methods significantly outperformed previous state-of-the-art models via both automatic evaluations and human judgment.  ...  multi-view decoder to incorporate different views to generate dialogue summaries.  ...  Acknowledgment We would like to thank the anonymous reviewers for their helpful comments, and the members of Georgia Tech SALT group for their feedback.  ... 
arXiv:2010.01672v1 fatcat:g737tdkd7zcormud5oq5jsocxu

SummerTime: Text Summarization Toolkit for Non-experts [article]

Ansong Ni, Zhangir Azerbayev, Mutethia Mutuma, Troy Feng, Yusen Zhang, Tao Yu, Ahmed Hassan Awadallah, Dragomir Radev
2021 arXiv   pre-print
Such models now exist for a number of summarization tasks, including query-based summarization, dialogue summarization, and multi-document summarization.  ...  We also provide explanations for models and evaluation metrics to help users understand the model behaviors and select models that best suit their needs.  ...  This work is supported in part by a grant from Microsoft Research.  ... 
arXiv:2108.12738v2 fatcat:eb2cirootfformxegvwqcetjni

A Survey of Document Grounded Dialogue Systems (DGDS) [article]

Longxuan Ma and Wei-Nan Zhang and Mingda Li and Ting Liu
2020 arXiv   pre-print
Specifically, study the latest DS based on the unstructured document(s). We define Document Grounded Dialogue System (DGDS) as the DS that the dialogues are centering on the given document(s).  ...  For example, movie discussion can change from chit-chat to QA, the conversational recommendation can transform from chit-chat to recommendation, etc.  ...  The DBD takes advantage of document information to generate a reply based on understanding historical dialogue.  ... 
arXiv:2004.13818v1 fatcat:euhtfpjccvestgfeimbmpc7fma

Keyphrase Generation with Cross-Document Attention [article]

Shizhe Diao, Yan Song, Tong Zhang
2020 arXiv   pre-print
In this paper, we propose CDKGen, a Transformer-based keyphrase generator, which expands the Transformer to global attention with cross-document attention networks to incorporate available documents as  ...  Keyphrase generation aims to produce a set of phrases summarizing the essentials of a given document.  ...  Title: A study on meaning processing of dialogue with an example of development of travel consultation system.  ... 
arXiv:2004.09800v1 fatcat:qhfzwdnd5bgwzcrnjwt755bxz4
« Previous Showing results 1 — 15 out of 25,974 results