Dialogue Graph Modeling for Conversational Machine Reading

Ouyang, Siru; Zhang, Zhuosheng; Zhao, Hai

doi:10.18653/v1/2021.findings-acl.279

Cited by 25 publications

(36 citation statements)

References 31 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This graph is suitable for information aggregation with the help of coreference resolution that substantially compresses the input. Besides, in conversational machine reading, Ouyang et al [136] formulated the input text as two complementary graphs, i.e., explicit and implicit discourse graphs, to fully capture the complicated interactions among all the elementary discourse units (EDUs).…”

Section: Paragraph Representation Learningmentioning

confidence: 99%

See 1 more Smart Citation

Pretrained Language Models for Text Generation: A Survey

Li¹,

Tang²,

Zhao³

et al. 2022

Preprint

View full text Add to dashboard Cite

Text Generation aims to produce plausible and readable text in human language from input data. The resurgence of deep learning has greatly advanced this field by neural generation models, especially the paradigm of pretrained language models (PLMs). Grounding text generation on PLMs is seen as a promising direction in both academia and industry. In this survey, we present the recent advances achieved in the topic of PLMs for text generation. In detail, we begin with introducing three key points of applying PLMs to text generation: 1) how to encode the input data as representations preserving input semantics which can be fused into PLMs; 2) how to design a universal and performant architecture of PLMs served as generation models; and 3) how to optimize PLMs given the reference text and ensure the generated text satisfying special text properties. Then, we figure out several challenges and future directions within each key point. Next, we present a summary of various useful resources and typical text generation applications to work with PLMs. Finally, we conclude and summarize the contribution of this survey.CCS Concepts: • Computing methodologies → Natural language generation.

show abstract

Section: Paragraph Representation Learningmentioning

confidence: 99%

“…RL: DialogBERT[61]; Li et al[109]; Graph-based RL: BASS[191]; Ouyang et al[136] Document Encoding Inter-Sentential Semantics: BERTSumExt[119]; HIBERT et al[219]; Capturing Critical Semantics: Nguyen et al[134]; Liu et al[114]; RL Efficiency: Huang et al…”

mentioning

confidence: 99%

Pretrained Language Models for Text Generation: A Survey

Li¹,

Tang²,

Zhao³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Subsequent work (Gao et al, 2020) focused on segmenting documents into elementary discourse units (EDUs) which are tracked through the conversation. Going further, recent work built on this by explicitly modeling the conversational structure using Graph Convolutional Networks (GCNs) (Ouyang et al, 2021). The results show that using both explicit and implicit graph representations allows the model to more effectively address conversations with complex types of discourse structure.…”

Section: Procedural Question Answeringmentioning

confidence: 99%

Conversational Information Seeking

Zamani¹,

Trippas²,

Dalton³

et al. 2022

Preprint

View full text Add to dashboard Cite

Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system. Interactions in CIS are primarily based on natural language dialogue, while they may include other types of interactions, such as click, touch, and body gestures. This monograph provides a thorough overview of CIS definitions, applications, interactions, interfaces, design, implementation, and evaluation. This monograph views CIS applications as including conversational search, conversational question answering, and conversational recommendation. Our aim is to provide an overview of past research related to CIS, introduce the current state-of-the-art in CIS, highlight the challenges still being faced in the community. and suggest future directions.

show abstract

“…Efforts had also been made on enriching the pretrained models with specific syntactic/semantic information Zhang et al, 2020b). Another trend was to fine-tune the pre-trained model and added additional layers to incorporate taskspecific information to gain better representation, in particular the coreference information (Ouyang et al, 2021;Liu et al, 2021).…”

Section: Background and Related Workmentioning

confidence: 99%

Tracing Origins: Coreference-aware Machine Reading Comprehension

Huang¹,

Zhang²,

Zhang³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Machine reading comprehension is a heavilystudied research and test field for evaluating new pre-trained models and fine-tuning strategies, and recent studies have enriched the pre-trained models with syntactic, semantic and other linguistic information to improve the performance of the model. In this paper, we imitated the human's reading process in connecting the anaphoric expressions and explicitly leverage the coreference information to enhance the word embeddings from the pre-trained model, in order to highlight the coreference mentions that must be identified for coreference-intensive question answering in QUOREF, a relatively new dataset that is specifically designed to evaluate the coreference-related performance of a model. We used an additional BERT layer to focus on the coreference mentions, and a Relational Graph Convolutional Network to model the coreference relations. We demonstrated that the explicit incorporation of the coreference information in fine-tuning stage performed better than the incorporation of the coreference information in training a pre-trained language models.

show abstract

Dialogue Graph Modeling for Conversational Machine Reading

Cited by 25 publications

References 31 publications

Pretrained Language Models for Text Generation: A Survey

Pretrained Language Models for Text Generation: A Survey

Conversational Information Seeking

Tracing Origins: Coreference-aware Machine Reading Comprehension

Contact Info

Product

Resources

About