IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions

1 code implementation • 11 Dec 2023 • Ziheng Zeng, Kellen Tan Cheng, Srihari Venkat Nanniyur, Jianing Zhou, Suma Bhat

Unlike prior works that enable IE comprehension through fine-tuning PTLMs with sentences containing IEs, in this work, we construct IEKG, a commonsense knowledge graph for figurative interpretations of IEs.

Natural Language Understanding

Unified Representation for Non-compositional and Compositional Expressions

1 code implementation • 29 Oct 2023 • Ziheng Zeng, Suma Bhat

Accurate processing of non-compositional language relies on generating good representations for such expressions.

Language Modelling

Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions

1 code implementation • 8 Jul 2022 • Ziheng Zeng, Suma Bhat

Idiomatic expressions (IEs), characterized by their non-compositionality, are an important part of natural language.

Clustering

Idiomatic Expression Paraphrasing without Strong Supervision

no code implementations • 16 Dec 2021 • Jianing Zhou, Ziheng Zeng, Hongyu Gong, Suma Bhat

In this paper, we study the task of idiomatic sentence paraphrasing (ISP), which aims to paraphrase a sentence with an IE by replacing the IE with its literal paraphrase.

Machine Translation Sentence +1

Idiomatic Expression Identification using Semantic Compatibility

1 code implementation • 19 Oct 2021 • Ziheng Zeng, Suma Bhat

Idiomatic expressions are an integral part of natural language and constantly being added to a language.

Sentence

Recurrent Inference in Text Editing

1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ning Shi, Ziheng Zeng, Haotian Zhang, Yichen Gong

In neural text editing, prevalent sequence-to-sequence based approaches directly map the unedited text either to the edited text or the editing operations, in which the performance is degraded by the limited source text encoding and long, varying decoding steps.