Papers by Girishkumar Ponkiya

4 papers
FrameNet-assisted Noun Compound Interpretation (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods for predicting semantic labels for noun compound interpretation are difficult.
Approach: They propose to predict semantic labels in a continuous embedding space using FrameNet data.
Outcome: The proposed method performs well on unseen labels, with 5% and 2% improvement over baselines for frame and FE prediction.
Treat us like the sequences we are: Prepositional Paraphrasing of Noun Compounds using LSTM (C18-1)

Copied to clipboard

Challenge: Using prepositions, noun compounds are interpreted in two ways: labelling and paraphrasing.
Approach: They propose to paraphrase noun compounds using prepositions by using parallelly aligned sequences of words.
Outcome: The proposed approach performs well on datasets manually annotated with prepositions.
Looking inside Noun Compounds: Unsupervised Prepositional and Free Paraphrasing (2020.findings-emnlp)

Copied to clipboard

Challenge: Noun compound interpretation is the task of uncovering the semantic relation between the components of a noun compound.
Approach: They propose an unsupervised method for identifying such relations between the components of a noun compound using pre-trained contextualized language models.
Outcome: The proposed method outperforms supervised approaches for free paraphrasing and prepositional paraphrases using pre-trained language models to uncover ‘missing’ words.
Towards a Standardized Dataset for Noun Compound Interpretation (L18-1)

Copied to clipboard

Challenge: Noun compounds are interesting constructs in Natural Language Processing . lack of standardized set of relation inventories and annotated datasets hinders interpretation .
Approach: They propose a dataset that uses FrameNet as its semantic relation inventory to examine noun compounds.
Outcome: The proposed dataset is linguistically grounded and uses FrameNet as its semantic relation inventory.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations