Pinzhen Chen
35 papers · 2020–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
🐝 Cross-Pollinator (10) 🌍 Conference Polyglot (8) 🏃 Academic Marathon (5) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5)
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(8)
🏃
Academic Marathon
(5)
🤝
Dynamic Duo
(12)
🏆
Keyword Champion
(2)
👥
Mega-Team
(35)
🔬
Deep Specialist
(18)
❓
The Questioner
(4)
💎
Century Club
(34)
⚡
Prolific Year
(5)
🗃️
Keyword Collector
(147)
🔥
Unstoppable
(6)
Conferences
EMNLP (16)
ACL (5)
NAACL (5)
COLING (3)
EACL (3)
AACL (1)
IJCNLP (1)
SEMEVAL (1)
Top co-authors
Keywords
machine translation
(13)
large language model
(10)
neural machine translation
(7)
multi-task learning
(5)
multilingual model
(4)
reverse dictionary
(4)
cross-lingual transfer
(3)
multilingual language model
(3)
constrained decoding
(3)
instruction tuning
(3)
word embedding
(3)
parallel corpus
(3)
low-resource translation
(3)
domain adaptation
(3)
definition modeling
(3)
definition generation
(3)
terminology translation
(2)
parallel datum
(2)
translation quality
(2)
pre-trained language model
(2)
Papers
When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation
EACL 2026
How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM
COLING 2025
AveniBench: Accessible and Versatile Evaluation of Finance Intelligence
COLING 2025
Findings of the WMT25 Terminology Translation Task: Terminology is Useful Especially for Good MTs
EMNLP 2025
An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT)
ACL 2025
DocHPLT: A Massively Multilingual Document-Level Translation Dataset
EMNLP 2025
Fine-Tuning Large Language Models with Sequential Instructions
NAACL 2025
XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation
EMNLP 2025
Findings of the WMT25 Multilingual Instruction Shared Task: Persistent Hurdles in Reasoning, Generation, and Evaluation
EMNLP 2025
Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?
EMNLP 2024
The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics
NAACL 2024
Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?
EMNLP 2024
Pitfalls and Outlooks in Using COMET
EMNLP 2024
Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation
EMNLP 2024
Cher at KSAA-CAD 2024: Compressing Words and Definitions into the Same Space for Arabic Reverse Dictionary
ACL 2024
EEE-QA: Exploring Effective and Efficient Question-Answer Representations
COLING 2024
Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca
EACL 2024
Exploring Very Low-Resource Translation with LLMs: The University of Edinburgh’s Submission to AmericasNLP 2024 Translation Task
NAACL 2024
UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing
NAACL 2024
Towards Effective Disambiguation for Machine Translation with Large Language Models
EMNLP 2023
Exploring Data Augmentation for Code Generation Tasks
EACL 2023
PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India
EMNLP 2023
Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting
EMNLP 2023
Edinburgh at SemEval-2022 Task 1: Jointly Fishing for Word Embeddings and Definitions
NAACL 2022
A Unified Model for Reverse Dictionary and Definition Modelling
AACL 2022
The University of Edinburgh’s Submission to the WMT22 Code-Mixing Shared Task (MixMT)
EMNLP 2022
Edinburgh at SemEval-2022 Task 1: Jointly Fishing for Word Embeddings and Definitions
SEMEVAL 2022
A Unified Model for Reverse Dictionary and Definition Modelling
IJCNLP 2022
The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task
EMNLP 2021
Efficient Machine Translation with Model Pruning and Quantization
EMNLP 2021
The University of Edinburgh’s Bengali-Hindi Submissions to the WMT21 News Translation Task
EMNLP 2021
The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation
EMNLP 2021
ParaCrawl: Web-Scale Acquisition of Parallel Corpora
ACL 2020
Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System
ACL 2020
Parallel Sentence Mining by Constrained Decoding
ACL 2020