[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/kai-wei-chang/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Kai-Wei Chang

# Kai-Wei Chang

2 paper cards in Mova's library · 2022–2023

Kai-Wei Chang wrote 2 of the papers Mova reads, in 2022–2023, most of them on [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/); often with [Anoop Kumar](https://md.mova.elamur.ai/free/en/docs/papers/authors/anoop-kumar/), [Aram Galstyan](https://md.mova.elamur.ai/free/en/docs/papers/authors/aram-galstyan/), [Kuan-Hao Huang](https://md.mova.elamur.ai/free/en/docs/papers/authors/kuan-hao-huang/).

[OpenAlex](https://openalex.org/A5087096372) · [ORCID](https://orcid.org/0000-0001-5365-0072) · [**h-index 54**](https://openalex.org/authors/A5087096372) · [17628 citations](https://openalex.org/authors/A5087096372) · [433 works](https://openalex.org/works?filter=author.id:A5087096372) — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Kai-Wei+Chang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Kai-Wei+Chang) · [dblp](https://dblp.org/search?q=Kai-Wei+Chang) · [ACL Anthology](https://aclanthology.org/search/?q=Kai-Wei+Chang) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Kai-Wei+Chang)

Topics: [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/) 2

## Papers

1. **[ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation](https://md.mova.elamur.ai/free/en/docs/papers/huang-2023-paraamr-large-scale-syntactically-diverse/)** *(2023)* ParaAMR builds about 15 million paraphrase pairs by AMR back-translation. Each source sentence is parsed to an AMR graph; a different node is chosen as the focus (the main assertion); the modified graph is linearised and a sentence is generated from it. Candidates with high perplexity under a language model are…
2. **[Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations](https://md.mova.elamur.ai/free/en/docs/papers/huang-2022-unsupervised-syntactically-controlled-paraphrase-generation/)** *(2022)* AMRPG generates a paraphrase that follows a requested syntactic form without any paraphrase pairs. It encodes the input twice: an AMR graph gives a semantic embedding, and the constituency parse gives a syntactic embedding. A decoder learns to reconstruct the input from the two. At test time the syntactic embedding…

## Co-authors (6)

- [Anoop Kumar](https://md.mova.elamur.ai/free/en/docs/papers/authors/anoop-kumar/) ×2
- [Aram Galstyan](https://md.mova.elamur.ai/free/en/docs/papers/authors/aram-galstyan/) ×2
- [Kuan-Hao Huang](https://md.mova.elamur.ai/free/en/docs/papers/authors/kuan-hao-huang/) ×2
- [Varun Iyer](https://md.mova.elamur.ai/free/en/docs/papers/authors/varun-iyer/) ×2
- I-Hung Hsu
- Sriram Venkatapathy
- [← previous Kaheer Suleman](https://md.mova.elamur.ai/free/en/docs/papers/authors/kaheer-suleman/)
- [next → Kais Dukes](https://md.mova.elamur.ai/free/en/docs/papers/authors/kais-dukes/)
- [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)