QuASE: Question-Answer Driven Sentence Encoding

He, Hangfeng; Ning, Qiang; Roth, Dan

doi:10.48550/arxiv.1909.00333

Cited by 3 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also note that question data has been proposed as a resource for encoding generally useful language models [Jia et al, 2021, He et al, 2019. While this goal is different from the one pursued here, it shares the intuition that the factual content of documents is summarized well by questions and answers.…”

Section: Repaq Qamat and Other Uses Of Qa Datamentioning

confidence: 92%

QA Is the New KR: Question-Answer Pairs as Knowledge Bases

Chen¹,

Cohen²,

Jong³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this position paper, we propose a new approach to generating a type of knowledge base (KB) from text, based on question generation and entity linking. We argue that the proposed type of KB has many of the key advantages of a traditional symbolic KB: in particular, it consists of small modular components, which can be combined compositionally to answer complex queries, including relational queries and queries involving "multi-hop" inferences. However, unlike a traditional KB, this information store is well-aligned with common user information needs.

show abstract

Section: Repaq Qamat and Other Uses Of Qa Datamentioning

confidence: 92%

QA Is the New KR: Question-Answer Pairs as Knowledge Bases

Chen¹,

Cohen²,

Jong³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Li et al [ 21 ] introduced external knowledge to improve domain-specific event extraction. Recently, some works have adopted a generative method [ 22 , 23 ] to solve event extraction problems. QA frameworks have been adapted for event extraction and can also effectively solve the problem of few-shot event extraction [ 10 , 11 ].…”

Section: Related Workmentioning

confidence: 99%

Movie Scene Event Extraction with Graph Attention Network Based on Argument Correlation Information

Qian

Zhang

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

Movie scene event extraction is a practical task in media analysis, which aims at extracting structured events from unstructured movie scripts. However, although there have been many studies regarding open domain event extraction, there have only been a few studies focusing on movie scene event extraction. Specifically aimed at instances where different argument roles have the same characteristics in a movie scene, we propose the utilization of the correlation between different argument roles, which is beneficial for both movie scene trigger extraction (trigger identification and classification) and movie scene argument extraction (argument identification and classification) in event extraction. To model the correlation between different argument roles, we propose the superior role concept (SRC), a high-level role concept based upon the ordinary argument role. In this paper, we introduce a new movie scene event extraction model with two main features: (1) an attentive high-level argument role module to capture SRC information and (2) an SRC-based graph attention network (GAT) to fuse the argument role correlation information into semantic embeddings. To evaluate the performance of our model, we constructed a movie scene event extraction dataset named MovieSceneEvent and also conducted experiments on a widely used dataset to compare the results with other models. The experimental results show that our model outperforms competitive models, and the correlation information of argument roles helps to improve the performance of movie scene event extraction.

show abstract

“…Because cross-document co-reference is one of several components in a QEDB, our proposal is broader in scope, but the results of (Weiss et al 2021) support our general claim that there are synergies between the various subtasks involved in building (or using) a QEDB. Question data has also been proposed as a resource for encoding generally useful language models (Jia, Lewis, and Zettlemoyer 2021;He, Ning, and Roth 2019) as well. While this goal is different from the one pursued here, it shares the intuition that the factual content of documents is summarized well by questions and answers.…”

Section: Question-based Document Annotationmentioning

confidence: 99%

QA Is the New KR: Question-Answer Pairs as Knowledge Bases

Cohen

Chen

Jong

et al. 2023

AAAI

View full text Add to dashboard Cite

We propose a new knowledge representation (KR) based on knowledge bases (KBs) derived from text, based on question generation and entity linking. We argue that the proposed type of KB has many of the key advantages of a traditional symbolic KB: in particular, it consists of small modular components, which can be combined compositionally to answer complex queries, including relational queries and queries involving ``multi-hop'' inferences. However, unlike a traditional KB, this information store is well-aligned with common user information needs. We present one such KB, called a QEDB, and give qualitative evidence that the atomic components are high-quality and meaningful, and that atomic components can be combined in ways similar to the triples in a symbolic KB. We also show experimentally that questions reflective of typical user questions are more easily answered with a QEDB than a symbolic KB.

show abstract

QuASE: Question-Answer Driven Sentence Encoding

Cited by 3 publications

References 30 publications

QA Is the New KR: Question-Answer Pairs as Knowledge Bases

QA Is the New KR: Question-Answer Pairs as Knowledge Bases

Movie Scene Event Extraction with Graph Attention Network Based on Argument Correlation Information

QA Is the New KR: Question-Answer Pairs as Knowledge Bases

Contact Info

Product

Resources

About