Leveraging Abstract Meaning Representation for Knowledge Base Question Answering

Kapanipathi, Pavan; Abdelaziz, Ibrahim; Ravishankar, Srinivas; Roukos, Salim; Gray, Alexander G.; Astudillo, Ramón Fernandez; Chang, Maria Hsia; Cornelio, Cristina; Dana, Saswati; Fokoue, Achille; Garg, Dinesh; Gliozzo, Alfio; Gurajada, Sairam; Karanam, Hima; Khan, Naweed; Khandelwal, Dinesh; Lee, Young-Suk; Li, Yunyao; Luus, Francois; Makondo, Ndivhuwo; Mihindukulasooriya, Nandana; Naseem, Tahira; Neelam, Sumit; Popa, Lucian; Reddy, Revanth Gangi; Riegel, Ryan; Rossiello, Gaetano; Sharma, Udit; Bhargav, G P Shrivatsa; Yu, Mo

doi:10.18653/v1/2021.findings-acl.339

Cited by 57 publications

(45 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One the one hand, the use of AMR as an intermediate representation for e.g. inferencing for question answering (Sachan and Xing, 2016;Kapanipathi et al, 2021) and human-robot interaction (Bastianelli et al, 2013) has been proven. So far, inferencing from AMRs has necessarily remained limited to sentence-level information, or has been based on ad-hoc meaning representations spanning multiple sentence-level AMRs.…”

Section: Goals Of Umr Annotationmentioning

confidence: 99%

Theoretical and Practical Issues in the Semantic Annotation of Four Indigenous Languages

Gysel¹,

Vigus²,

Denk³

et al. 2021

Proceedings of the Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop

View full text Add to dashboard Cite

Computational resources such as semantically annotated corpora can play an important role in enabling speakers of indigenous minority languages to participate in government, education, and other domains of public life in their own language. However, many languagesmainly those with small native speaker populations and without written traditions -have little to no digital support. One hurdle in creating such resources is that for many languages, few speakers would be capable of annotating texts -a task which requires literacy and some linguistic training -and that these experts' time is typically in high demand for language planning work. This paper assesses whether typologically trained non-speakers of an indigenous language can feasibly perform semantic annotation using Uniform Meaning Representations, thus allowing for the creation of computational materials without putting further strain on community resources. 1

show abstract

Section: Goals Of Umr Annotationmentioning

confidence: 99%

Theoretical and Practical Issues in the Semantic Annotation of Four Indigenous Languages

Gysel¹,

Vigus²,

Denk³

et al. 2021

Proceedings of the Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop

View full text Add to dashboard Cite

show abstract

“…12 We also include the QALD-9-AMR corpus, 13 containing human annotated gold AMRs in AMR3.0 style from the QALD-9 corpus. 14 QALD-9 (Usbeck et al, 2018) is a corpus of natural language questions for executable semantic parsing, used in (Kapanipathi et al, 2021), among other works. BioAMR is distinct from AMR2.0 treebank data mostly in terms of vocabulary and named entities.…”

Section: Domain Adaptationmentioning

confidence: 99%

Maximum Bayes Smatch Ensemble Distillation for AMR Parsing

Lee¹,

Astudillo²,

Hoang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

AMR parsing has experienced an unprecendented increase in performance in the last three years, due to a mixture of effects including architecture improvements and transfer learning. Self-learning techniques have also played a role in pushing performance forward. However, for most recent high performant parsers, the effect of self-learning and silver data generation seems to be fading. In this paper we show that it is possible to overcome this diminishing returns of silver data by combining Smatch-based ensembling techniques with ensemble distillation. In an extensive experimental setup, we push single model English parser performance above 85 Smatch for the first time and return to substantial gains. We also attain a new state-of-the-art for crosslingual AMR parsing for Chinese, German, Italian and Spanish. Finally we explore the impact of the proposed distillation technique on domain adaptation, and show that it can produce gains rivaling those of human annotated data for QALD-9 and achieve a new state-ofthe-art for BioAMR.

show abstract

“…However, the richness of the information included in AMR graphs, as well as their obvious applications as an interface between human and machines, make both AMR parsing and generation very rewarding problems to solve. As a matter of fact, AMR has been successfully applied to diverse downstream applications, such as Machine Translation (Song et al, 2019), Text Summarization (Hardy and Vlachos, 2018;Liao et al, 2018), Human-Robot Interaction (Bonial et al, 2020a), Information Extraction (Rao et al, 2017) and, more recently, Question Answering (Lim et al, 2020;Bonial et al, 2020b;Kapanipathi et al, 2021). However, since AMR graphs for such applications are obtained automatically through an AMR parser, the benefits of AMR integration are highly correlated with the performance of the underlying parser across various data distributions and domains.…”

Section: Introductionmentioning

confidence: 99%

SPRING Goes Online: End-to-End AMR Parsing and Generation

Blloshmi¹,

Bevilacqua²,

Fabiano³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

View full text Add to dashboard Cite

In this paper we present SPRING Online Services, a Web interface and RESTful APIs for our state-of-the-art AMR parsing and generation system, SPRING (Symmetric PaRs-Ing aNd Generation). The Web interface has been developed to be easily used by the Natural Language Processing community, as well as by the general public. It provides, among other things, a highly interactive visualization platform and a feedback mechanism to obtain user suggestions for further improvements of the system's output. Moreover, our RESTful APIs enable easy integration of SPRING in downstream applications where AMR structures are needed. Finally, we make SPRING Online Services freely available at http://nlp.uniroma1.it/spring and, in addition, we release extra model checkpoints to be used with the original SPRING Python code. 1

show abstract

Leveraging Abstract Meaning Representation for Knowledge Base Question Answering

Cited by 57 publications

References 32 publications

Theoretical and Practical Issues in the Semantic Annotation of Four Indigenous Languages

Theoretical and Practical Issues in the Semantic Annotation of Four Indigenous Languages

Maximum Bayes Smatch Ensemble Distillation for AMR Parsing

SPRING Goes Online: End-to-End AMR Parsing and Generation

Contact Info

Product

Resources

About