About Me
Hello! I am a PhD student in NLP @ the Machine Intelligence Lab in the Engineering Department, the University of Cambridge. My PhD is under the supervision of Prof. Mark Gales, and I am funded by the Cambridge International & St John's College Scholarship.
Currently, I also work on Typhoon, an open-source Thai large language model.
Previously, I worked as an applied scientist intern at Amazon. Before PhD, I obtained B.A. and M.Eng. degrees in Information and Computer Engineering from Cambridge in 2019.
Research Interests
- Summarization and Text Generation
- Text Evaluation & LLM Hallucination
- Question Generation and Answering
- Low-Resource NLP
Publications
[A complete list of publications is available on Google Scholar]
-
LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models
Adian Liusie, Potsawee Manakul, Mark Gales
EACL 2024
[code]
-
Typhoon: Thai Large Language Models
Kunat Pipatanakul, Phatrasek Jirabovonvisut, Potsawee Manakul, Sittipong Sripaisarnmongkol, Ruangsak Patomwong, Pathomporn Chokchainant, Kasima Tharnpipitchai
arxiv 2023
[model weights]
→ State-of-the-art Open-source Thai LLM
-
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Potsawee Manakul, Adian Liusie, Mark Gales
EMNLP 2023
[project page]
→ Talk at ML Collective - Deep Learning: Classics and Trends (DLCT) in August 2023
→ Interview with the Washington Post about AI Hallucination in May 2023
→ An analysis by Daniel Huynh (from Mithril Security) on SelfCheckGPT
-
MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization
Potsawee Manakul, Adian Liusie, Mark Gales
AACL 2023
[code]
→ Area Chair Paper Award (Generation and Summarization)
-
Mitigating Word Bias in Zero-shot Prompt-based Classifiers
Adian Liusie, Potsawee Manakul, Mark Gales
Findings of AACL 2023
[code]
-
CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models
Potsawee Manakul, Yassir Fathullah, Adian Liusie, Vyas Raina, Vatsal Raina, Mark Gales
BioNLP Workshop @ ACL 2023 [code]
→ Best-performing system on the Problem List Summarization shared task
-
Podcast Summary Assessment: A Resource for Evaluating Summary Assessment Methods
Potsawee Manakul, Mark Gales
arxiv 2022
[data]
-
Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems
Potsawee Manakul, Mark Gales
EMNLP 2021
[code]
-
Long-Span Summarization via Local Attention and Content Selection
Potsawee Manakul, Mark Gales
ACL 2021
[code]
-
CUED_SPEECH at TREC 2020 Podcast Summarisation Track
Potsawee Manakul, Mark Gales
TREC 2020
[code]
→ Won 1st place in the Spotify Podcast Summarisation task 2020
-
Abstractive Spoken Document Summarization using Hierarchical Model with Multi-stage Attention Diversity Optimization
Potsawee Manakul, Mark J. F. Gales, Linlin Wang
Interspeech 2020
[code]
→ Best Student Paper Award Finalist
-
Impact of ASR Performance on Spoken Grammatical Error Detection
Yiting Lu, Mark J. F. Gales, Katherine M. Knill, Potsawee Manakul, Linlin Wang, Yu Wang
Interspeech 2019
-
Automatic grammatical error detection of non-native spoken learner English
Katherine M. Knill, Mark J. F. Gales, Potsawee Manakul, Andrew P. Caines
ICASSP 2019
Professional Acitivity
Reviewer
- ACL Rolling Review 2024
- ICLR 2024
- NeurIPS 2023
- ICML 2023, 2024
- Interspeech 2023
- IEEE Transactions on Audio, Speech, and Language Processing 2022, 2023, 2024
Teaching @ Cambridge
- 3rd-year Undergraduate Supervision: 3F7 Information Theory and Coding
- 2nd-year Undergraduate Supervision: 2P7 Vector Calculus, Linear Algebra, Probability
- MPhil in Machine Learning & Machine Intelligence: Introduction to NLP (Lab demonstration)
- 1st-year Undergraduate: Engineering Lego Lab (Lab demonstration)
- Email: pm574-at-cam.ac.uk
- Address: St John's College, St John's Street, Cambridge, CB2 1TP, United Kingdom