Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy
            with Frame Embeddings

Botschen, Teresa; Sergieh, Hatem Mousselly; Gurevych, Iryna

doi:10.18653/v1/w17-2618

Cited by 5 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the annotation process, we found some difficulties because of the coverage issue of the FrameNet. The wordto-frame mapping in FrameNet has a coverage issue, and it has been widely reported in the literature (Pavlick et al, 2015;Botschen et al, 2017).…”

Section: Manual Annotationmentioning

confidence: 99%

FrameNet-assisted Noun Compound Interpretation

Ponkiya

Kanojia

Bhattacharyya

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Given a noun compound (NC), we address the problem of predicting the appropriate semantic label linking the constituents of the NC. This problem is called Noun Compound Interpretation (NCI). We use FrameNet as a semantic label repository. For example, given the noun compound (board approval), we predict the frame (DENY OR GRANT PERMISSION, as per FrameNet) as appropriate and the semantic role of the modifier word (AUTHORITY) as the semantic label linking board and approval; the resulting label is DENY OR GRANT PERMISSION:AUTHORITY.Our semantic label repository is very large (≈ 11k labels) compared to the NC data available for training (approx 1900). Thus, learning in this case, especially for unseen semantic labels, is hard. We propose to solve this problem by predicting semantic labels in a continuous label embedding space, which is novel. This embedding space is created by learning label embeddings using the FrameNet data. The embeddings are then used to train two separate models -one for predicting Frames and the other for FEs. As the label embedding space captures the semantics of the labels, using these embeddings enables generalizing well on unseen labels, thus achieving zero-shot learning. Our preliminary investigations show that the proposed approach performs well for unseen labels, achieving 5% and 2% points improvements over baselines for the frame and FE prediction, respectively. The study shows the promise of the use of continuous space embeddings for noun compound interpretation and points to the need for further investigation.

show abstract

Section: Manual Annotationmentioning

confidence: 99%

FrameNet-assisted Noun Compound Interpretation

Ponkiya

Kanojia

Bhattacharyya

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

show abstract

“…As for frames, there has been some work on using distributional similarity between vectors for their unsupervised induction (Ustalov et al, 2018), for comparing frames across languages (Sikos and Padó, 2018), and even for the automatic identification of the semantic relations holding between them (Botschen et al, 2017).…”

Section: Some Other Arguments In Favor Of a Distributional Cxgmentioning

confidence: 99%

Distributional Semantics Meets Construction Grammar. towards a Unified Usage-Based Model of Grammar and Meaning

Rambelli¹,

Chersoni²,

Blache³

et al. 2019

Proceedings of the First International Workshop on Designing Meaning Representations

View full text Add to dashboard Cite

In this paper, we propose a new type of semantic representation of Construction Grammar that combines constructions with the vector representations used in Distributional Semantics. We introduce a new framework, Distributional Construction Grammar, where grammar and meaning are systematically modeled from language use, and finally, we discuss the kind of contributions that distributional models can provide to CxG representation from a linguistic and cognitive perspective.

show abstract

“…Subsequent FrameID models followed, including a system that constructed frame embeddings using the Word2Vec model (Botschen et al, 2017). More recent state-of-the-art models use contextualized embeddings of frames in the BERT framework (Sikos and Padó, 2019) or joint models with semantic dependencies and frames (Peng et al, 2018).…”

Section: Neural Architectures For Frame Identificationmentioning

confidence: 99%

Graph Embeddings for Frame Identification

Попов

Sikos²

2019

Proceedings - Natural Language Processing in a Deep Learning World

View full text Add to dashboard Cite

Lexical resources such as WordNet (Miller, 1995) and FrameNet (Baker et al., 1998) are organized as graphs, where relationships between words are made explicit via the structure of the resource. This work explores how structural information from these lexical resources can lead to gains in a downstream task, namely frame identification. While much of the current work in frame identification uses various neural architectures to predict frames, those neural architectures only use representations of frames based on annotated corpus data. We demonstrate how incorporating knowledge directly from the FrameNet graph structure improves the performance of a neural network-based frame identification system. Specifically, we construct a bidirectional LSTM with a loss function that incorporates various graph-and corpus-based frame embeddings for learning and ultimately achieves strong performance gains with the graphbased embeddings over corpus-based embeddings alone.

show abstract

Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings

Cited by 5 publications

References 20 publications

FrameNet-assisted Noun Compound Interpretation

FrameNet-assisted Noun Compound Interpretation

Distributional Semantics Meets Construction Grammar. towards a Unified Usage-Based Model of Grammar and Meaning

Graph Embeddings for Frame Identification

Contact Info

Product

Resources

About