Papers by Haiyue Song
Video-guided Machine Translation with Spatial Hierarchical Attention Network (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing studies use pretrained motion detection models as verb sense ambiguity representations to solve the verb sense problem. |
| Approach: | They propose to use video contents as auxiliary information to address the word sense ambiguity problem in machine translation. |
| Outcome: | Experiments on the VATEX dataset show that the proposed system achieves 35.86 BLEU-4 score, which is 0.51 score higher than the single model of the SOTA method. |
PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Pre-trained sequence-to-sequence models are typically pretrained on extensive raw text corpora and fine-tuned on task-specific data. |
| Approach: | They introduce a pre-trained sequence-to-sequence model trained from scratch for Khmer using carefully curated Khmer and English corpora. |
| Outcome: | The proposed model outperforms existing models on three generative tasks and is data-efficient and effective in enhancing performance across various natural language generation tasks. |
Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods ignore the intrinsic noise of distant supervision during the pre-training stage. |
| Approach: | They propose a weighted contrastive learning method that explicitly reduces noise . they leverage supervised data to estimate reliability and reduce noise compared to non-weighted baselines . |
| Outcome: | The proposed method reduces the noise of distant supervision and estimates reliability of pre-training instances. |
JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation (2020.lrec-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) requires large parallel corpora for training robust and high quality models. |
| Approach: | They propose a Japanese-specific sequence to sequence pre-training alternative to MASS for NMT . they use Japanese as the source or target language to train their models . |
| Outcome: | The proposed approach can give competitive results over MASS and BRSS, and significantly surpass the individual methods. |
Pre-training via Leveraging Assisting Languages for Neural Machine Translation (2020.acl-srw)
Copied to clipboard
| Challenge: | Sequence-to-sequence (S2S) pre-training with large monolingual data is not always available for the languages of interest (LOI). |
| Approach: | They propose to use monolingual corpora of other languages to complement the scarce monolingual LOI by script mapping (Chinese to Japanese) . Using only Chinese and French monolinguals, they improve Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios. |
| Outcome: | The proposed approach improves Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios. |
Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation (2020.lrec-1)
Copied to clipboard
| Challenge: | Lectures translation is a case of spoken language translation and there is nil available corpus for this purpose. |
| Approach: | They propose a framework for mining a parallel corpus from publicly available lectures at Coursera . they use machine translation and cosine similarity over continuous-space sentence representations to determine sentence alignments . |
| Outcome: | The proposed framework improves translation performance when used with out-of-domain parallel corpora . it also addresses noise in the mined data, and creates high-quality evaluation splits . |
CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation (2025.findings-emnlp)
Copied to clipboard
Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, Kareem Elzeky, Henok Biadglign Ademtew, Alham Fikri Aji, Vladimir Araujo, Israel Abebe Azime, Jinheon Baek, Frederico Belcavello, Fermin Cristobal, Jan Christian Blaise Cruz, Mary Dabre, Raj Dabre, Toqeer Ehsan, Naome A Etori, Fauzan Farooqui, Jiahui Geng, Guido Ivetta, Thanmay Jayakumar, Soyeong Jeong, Zheng Wei Lim, Aishik Mandal, Sofía Martinelli, Mihail Minkov Mihaylov, Daniil Orel, Aniket Pramanick, Sukannya Purkayastha, Israfel Salazar, Haiyue Song, Tiago Timponi Torrent, Debela Desalegn Yadeta, Injy Hamed, Atnafu Lambebo Tonja, Thamar Solorio
| Challenge: | a human-curated benchmark of over 5,800 triples of images is used to evaluate multimodal translation systems. |
| Approach: | They introduce a human-curated benchmark of over 5,800 triples of images along with parallel captions in English and regional languages. |
| Outcome: | The results show that visual context improves translation quality in culturally-specific items . |
GPT-RE: In-context Learning for Relation Extraction using Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to in-context learning (ICL) are lacking in relation extraction (RE) . emergence of large language models (LLMs) such as GPT-3 represents a significant advancement in natural language processing. |
| Approach: | They propose to incorporate task-aware representations into demonstration retrieval and enrich the demonstrations with gold label-induced reasoning logic. |
| Outcome: | The proposed model achieves SOTA and competitive performances on the Semeval and SciERC datasets. |
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation? (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to improve pre-training for many-to-many neural machine translation use manual cleaning of bilingual dictionaries, which are unavailable for most language pairs. |
| Approach: | They propose a word-level contrastive objective to leverage word alignments for many-to-many neural machine translation (NMT) Empirical results show that this leads to 0.8 BLEU gains for several language pairs. |
| Outcome: | Empirical results show that the proposed objective leads to 0.8 BLEU gains for several language pairs. |
Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing knowledge enhancement techniques for pre-trained language models (PLMs) introduce noisy entity representations. |
| Approach: | They propose a knowledge enhancement filter that integrates external knowledge bases to enhance PLMs' ability to capture entity knowledge. |
| Outcome: | The proposed method achieves the highest F1-score and accuracy while reducing the computational cost by 1.7-2.5x. |
NGLUEni: Benchmarking and Adapting Pretrained Language Models for Nguni Languages (2024.lrec-main)
Copied to clipboard
| Challenge: | Nguni languages have over 20 million home language speakers in South Africa . there has been considerable growth in the datasets for these languages, but no analysis of the performance of NLP models for these language has been reported across languages and tasks. |
| Approach: | They compile publicly available datasets for natural language understanding and generation, spanning 6 tasks and 11 datasets. |
| Outcome: | The proposed models outperform existing models and large-scale adapted models on cross-lingual transfer and machine translation. |
Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation (2023.acl-short)
Copied to clipboard
| Challenge: | Recent studies have shown that layer normalization (LayerNorm) overfits training data and therefore has low generalizability for ZST. |
| Approach: | They propose to use the Transformer architecture to set the default layer normalization setting for zero-shot translation (ZST) they also propose to set LayerNorm after residual connections to outperform PreNorm by 12.3 BLEU points. |
| Outcome: | The proposed model outperforms the current model by 12.3 BLEU points on 54 directions on OPUS, IWSLT, and Europarl datasets. |
BERTSeg: BERT Based Unsupervised Subword Segmentation for Neural Machine Translation (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing subword segmenters are frequency-based without semantics information or neural-based but trained on parallel corpora. |
| Approach: | They propose an unsupervised neural subword segmenter for neural machine translation that utilizes contextualized semantic embeddings of words from characterBERT and maximizes the generation probability of subword segments. |
| Outcome: | The proposed method improves translation performance on ALT, IWSLT15 Vi->En, WMT16 Ro->En and WMT15 Fi->En datasets. |