TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process

Kong, Junsheng; Zhong, Zhicheng; Cai, Yi; Wu, Xin; Da, Ren

doi:10.18653/v1/2020.findings-emnlp.192

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After defining and clarifying the research objectives, types of objects, and specifying object templates, we study knowledge extraction techniques based on domain pre-training models to develop a knowledge architecture primarily based on tree structures and auxiliary attribute classification, as well as a knowledge association network primarily based on triplets [4]. By researching and applying techniques such as topic modeling, label relation mining, semantic representation, and multi-level knowledge integration, we construct an integrated system for identifying and annotating knowledge objects at different granular levels, including phrase-level, sentence-level, and chapter-level, to meet the requirements for annotating and extracting general fine-grained knowledge objects and domainspecific knowledge.…”

Section: Establishing a Standard Knowledge Base Framework Based On Re...mentioning

confidence: 99%

Design and Implementation of Digital Platform Based on Standard Knowledge Map in Oil and Gas Exploration and Development Field

Huang,

Su,

Yue

et al. 2024

HSET

View full text Add to dashboard Cite

This paper introduces the current situation and problems of standardization development in the field of oil and gas exploration and development in China. To solve the problems of large amount of standard knowledge, large professional span and complex level, the concept connotation of ontology and knowledge graph is clarified. A triplet core data model of “standardized object (product) -style (paragraph structure) -index (attribute)” is proposed for oil and gas exploration and development. Based on this, the construction idea, main function, and future direction of digital platform of standard knowledge map in oil and gas exploration and development are studied.

show abstract

Section: Establishing a Standard Knowledge Base Framework Based On Re...mentioning

confidence: 99%

Design and Implementation of Digital Platform Based on Standard Knowledge Map in Oil and Gas Exploration and Development Field

Huang,

Su,

Yue

et al. 2024

HSET

View full text Add to dashboard Cite

show abstract

“…We remove stopwords, and then obtain the Part-Of-Speech (POS) feature for each word. As a content word, its POS tagging should be noun, verb, adjective or adverb [23].…”

Section: First Stage: Visual Impression Constructionmentioning

confidence: 99%

Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation

Shen,

Zhan,

Shen

et al. 2021

Preprint

View full text Add to dashboard Cite

Open-domain dialogue generation in natural language processing (NLP) is by default a pure-language task, which aims to satisfy human need for daily communication on open-ended topics by producing related and informative responses. In this paper, we point out that hidden images, named as visual impressions (VIs), can be explored from the text-only data to enhance dialogue understanding and help generate better responses. Besides, the semantic dependency between an dialogue post and its response is complicated, e.g., few word alignments and some topic transitions. Therefore, the visual impressions of them are not shared, and it is more reasonable to integrate the response visual impressions (RVIs) into the decoder, rather than the post visual impressions (PVIs). However, both the response and its RVIs are not given directly in the test process. To handle the above issues, we propose a framework to explicitly construct VIs based on pure-language dialogue datasets and utilize them for better dialogue understanding and generation. Specifically, we obtain a group of images (PVIs) for each post based on a pre-trained word-image mapping model. These PVIs are used in a co-attention encoder to get a post representation with both visual and textual information. Since the RVIs are not provided directly during testing, we design a cascade decoder that consists of two sub-decoders. The first sub-decoder predicts the content words in response, and applies the word-image mapping model to get those RVIs. Then, the second sub-decoder generates the response based on the post and RVIs. Experimental results on two open-domain dialogue datasets show that our proposed approach achieves superior performance over competitive baselines. CCS CONCEPTS• Computing methodologies → Discourse, dialogue and pragmatics; Natural language generation;

show abstract

: A Multilingual Humor-aided Multiparty Dialogue Generation in multimodal conversational setting

Chauhan,

Singh,

Ekbal

et al. 2023

Knowledge-Based Systems

View full text Add to dashboard Cite

TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process

Cited by 4 publications

References 15 publications

Design and Implementation of Digital Platform Based on Standard Knowledge Map in Oil and Gas Exploration and Development Field

Design and Implementation of Digital Platform Based on Standard Knowledge Map in Oil and Gas Exploration and Development Field

Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation

: A Multilingual Humor-aided Multiparty Dialogue Generation in multimodal conversational setting

Contact Info

Product

Resources

About