Semantic Representation for Dialogue Modeling

Bai, Xuefeng; Chen, Yulong; Song, Linfeng; Zhang, Yue

doi:10.18653/v1/2021.acl-long.342

Cited by 25 publications

(21 citation statements)

References 49 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Use of gold graphs also alleviates the need for alignments between gold and predicted graphs for the purpose of evaluation. Bai et al (2021) constructed dialogue-level AMR graphs from multiple utterance level AMRs by incorporating inter-sentence coreference, speaker and identical concept information into sentence-level AMRs.…”

Section: Resultsmentioning

confidence: 99%

DocAMR: Multi-Sentence AMR Representation and Evaluation

Naseem¹,

Blodgett²,

Kumaravel³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Despite extensive research on parsing of English sentences into Abstract Meaning Representation (AMR) graphs, full-document parsing into a unified graph representation lacks welldefined representation and evaluation. Taking advantage of a super-sentential level of AMR coreference annotation from previous work, we introduce a simple algorithm for deriving a unified graph representation, avoiding the pitfalls of information loss from over-merging and lack of coherence from under-merging. Next, we describe improvements to the Smatch metric to make it tractable for comparing document-level graphs, and use it to re-evaluate the best published document-level AMR parser. We also present a pipeline approach combining the top performing AMR parser and coreference resolution systems, providing a strong baseline for future research.

show abstract

Section: Resultsmentioning

confidence: 99%

DocAMR: Multi-Sentence AMR Representation and Evaluation

Naseem¹,

Blodgett²,

Kumaravel³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…Sachan and Xing (2016) represented text and questions as AMR graphs and reduced the machine comprehension problem to a graph containment problem. We have seen a growing body of work that makes use of AMR in other applications such as dialogue modeling, information extraction and commonsense reasoning (Bai et al, 2021;Lim et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

AMR-DA: Data Augmentation by Abstract Meaning Representation

Shou¹,

Jiang²,

Lin³

2022

Findings of the Association for Computational Linguistics: ACL 2022

View full text Add to dashboard Cite

Meaning Representation (AMR) is a semantic representation for NLP/NLU. In this paper, we propose to use it for data augmentation in NLP. Our proposed data augmentation technique, called AMR-DA, converts a sample sentence to an AMR graph, modifies the graph according to various data augmentation policies, and then generates augmentations from graphs. Our method combines both sentence-level techniques like back translation and token-level techniques like EDA (Easy Data Augmentation). To evaluate the effectiveness of our method, we apply it to the English tasks of semantic textual similarity (STS) and text classification. For STS, our experiments show that AMR-DA boosts the performance of the state-of-the-art models on several STS benchmarks. For text classification, AMR-DA outperforms EDA and AEDA and leads to more robust improvements. 1

show abstract

“…One example is shown in Figure 1(a), with the corresponding sentence in Figure 1(b). Serving as a structural representation, AMR has been shown useful for NLP tasks such as text summarization (Liu et al, 2015;Liao et al, 2018;, machine translation (Song et al, 2019), information extraction (Huang et al, 2016;Zhang and Ji, 2021) and dialogue systems (Bai et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Graph Pre-training for AMR Parsing and Generation

Bai¹,

Chen²,

Zhang³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

meaning representation (AMR) highlights the core semantic information of text in a graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation, respectively. However, PLMs are typically pretrained on textual data, thus are sub-optimal for modeling structural knowledge. To this end, we investigate graph self-supervised training to improve the structure awareness of PLMs over AMR graphs. In particular, we introduce two graph auto-encoding strategies for graph-to-graph pre-training and four tasks to integrate text and graph information during pre-training. We further design a unified framework to bridge the gap between pretraining and fine-tuning tasks. Experiments on both AMR parsing and AMR-to-text generation show the superiority of our model. To our knowledge, we are the first to consider pretraining on semantic graphs.

show abstract

Semantic Representation for Dialogue Modeling

Cited by 25 publications

References 49 publications

DocAMR: Multi-Sentence AMR Representation and Evaluation

DocAMR: Multi-Sentence AMR Representation and Evaluation

AMR-DA: Data Augmentation by Abstract Meaning Representation

Graph Pre-training for AMR Parsing and Generation

Contact Info

Product

Resources

About