AIConfPaper
← Search

Haiyue Song

7 accepted papers

2025

CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation

Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, Kareem Elzeky, Henok Biadglign Ademtew, Alham Fikri Aji +29
EMNLP 2025

Translating cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey sufficient context to capture region-specific meanings. In this work, we investigate whether images can act as cultural

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation

Hour Kaing, Raj Dabre, Haiyue Song, Van-Hien Tran, Hideki Tanaka, Masao Utiyama
COLING 2025main

This work introduces PrahokBART, a compact pre-trained sequence-to-sequence model trained from scratch for Khmer using carefully curated Khmer and English corpora. We focus on improving the pre-training corpus quality and addressing the linguistic issues of Khmer, which are ignored in existing multi…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

David Orlando Romero Mogrovejo, Chenyang Lyu, Haryo Akbarianto Wibowo, Santiago Góngora, Aishik Mandal, Sukannya Purkayastha +70
NeurIPS 2024oral

Visual Question Answering~(VQA) is an important task in multimodal AI, which requires models to understand and reason on knowledge present in visual and textual data. However, most of the current VQA datasets and models are primarily focused on English and a few major world languages, with images th…

Cited by 34Source ↗PDF ↗Scholar ↗
2024

NGLUEni: Benchmarking and Adapting Pretrained Language Models for Nguni Languages

Francois Meyer, Haiyue Song, Abhisek Chakrabarty, Jan Buys, Raj Dabre, Hideki Tanaka
COLING 2024main

The Nguni languages have over 20 million home language speakers in South Africa. There has been considerable growth in the datasets for Nguni languages, but so far no analysis of the performance of NLP models for these languages has been reported across languages and tasks. In this paper we study pr…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation

Zhuoyuan Mao, Raj Dabre, Qianying Liu, Haiyue Song, Chenhui Chu, Sadao Kurohashi
ACL 2023short

This paper studies the impact of layer normalization (LayerNorm) on zero-shot translation (ZST). Recent efforts for ZST often utilize the Transformer architecture as the backbone, with LayerNorm at the input of layers (PreNorm) set as the default. However, Xu et al. (2019) has revealed that PreNorm…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2023

GPT-RE: In-context Learning for Relation Extraction using Large Language Models

Zhen Wan, Fei Cheng, Zhuoyuan Mao, Qianying Liu, Haiyue Song, Jiwei Li +1
EMNLP 2023long main

In spite of the potential for ground-breaking achievements offered by large language models (LLMs) (e.g., GPT-3) via in-context learning (ICL), they still lag significantly behind fully-supervised baselines (e.g., fine-tuned BERT) in relation extraction (RE). This is due to the two major shortcoming…

Cited by 0Source ↗code ↗Scholar ↗
2022

When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?

Zhuoyuan Mao, Chenhui Chu, Raj Dabre, Haiyue Song, Zhen Wan, Sadao Kurohashi
NAACL 2022findings

Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs. Meanwhile, the contrastive objective can implicitly utilize auto…

Cited by 6Source ↗PDF ↗Scholar ↗