Papers by Haoyang Ma

7 papers
Multilingual Agreement for Multilingual Neural Machine Translation (2021.acl-short)

Copied to clipboard

Challenge: Existing models that only use auxiliary languages to encourage multilingual agreement ignore the relationships between different language pairs.
Approach: They propose a multilingual agreement-based method which explicitly models the agreement between different translation directions by randomly substituting some fragments of the source language with their counterpart translations of auxiliary languages.
Outcome: The proposed method improves on the multilingual translation task of 10 language pairs.
GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator (2023.acl-long)

Copied to clipboard

Challenge: Existing pre-training methods underutilize the benefits of language understanding for generation.
Approach: They propose a GAN-style model for encoder-decoder pre-training with an auxiliary discriminator.
Outcome: The proposed model outperforms existing pre-trained models and achieves state-of-the-art performance.
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)

Copied to clipboard

Challenge: Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity.
Approach: They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems.
Outcome: The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging.
TRIP: Accelerating Document-level Multilingual Pre-training via Triangular Document-level Pre-training on Parallel Data Triplets (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to multilingual sequence-to-sequence pre-training rely on monolingual corpora and sometimes synthetic document-level bilingual corporata.
Approach: They propose to leverage document-level trilingual parallel corpora to improve sequence-to-sequence multilingual pre-training by using a novel method called Grafting.
Outcome: The proposed method achieves strong state-of-the-art (SOTA) scores on three multilingual document-level machine translation benchmarks and one cross-lingual abstractive summarization benchmark.
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation (2022.naacl-main)

Copied to clipboard

Challenge: Standard evaluation metrics, e.g., BLEU, TER and METEOR, focus on the quality of translations at the sentence level and do not consider discourse-level features.
Approach: They propose to use a metric to take discourse coherence into consideration by categorizing discourse-related spans and calculating the similarity-based F1 measure of categorized spans.
Outcome: The proposed metric possesses better selectivity and interpretability at the document-level, and is more sensitive to document- level nuances.
From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs (2025.acl-long)

Copied to clipboard

Challenge: Recent studies in formal mathematical reasoning have shown an unstoppable growth trend.
Approach: They constructed 18k high-quality instruction-response pairs across five mainstream formal specification languages and evaluated them against ten open-sourced LLMs.
Outcome: The proposed model compared instruction-response pairs across five formal specification languages and found that the LLMs were good at writing proof segments when given either the code, or the detailed description of proof steps.
Improving Multilingual Neural Machine Translation with Auxiliary Source Languages (2021.findings-emnlp)

Copied to clipboard

Challenge: Prior work has shown that translating from multiple source languages improves translation quality.
Approach: They propose to exploit multiple source sentences from auxiliary languages to improve multilingual translation in a more common scenario by using synthetic multi-source corpora.
Outcome: Extensive experiments on Chinese/English-Japanese and a large-scale multilingual translation benchmark show that the proposed model outperforms the baseline model significantly by +4.0 BLEU.

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