Papers by Kris Cao
Factorising AMR generation through syntax (N19-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic annotation framework which abstracts away from the surface form of text to capture the core 'who did what to whom' structure. |
| Approach: | They propose to decompose the generation process into two steps: first generate a syntactic structure, and then generate the surface form. |
| Outcome: | The proposed approach generates meaning-preserving syntactic paraphrases of the same graph, as judged by humans. |
What is the best recipe for character-level encoder-only modelling? (2023.acl-long)
Copied to clipboard
| Challenge: | aims to benchmark recent progress in language understanding models that output contextualised representations at the character level. |
| Approach: | They aim to find the best way to build and train character-level BERT-like models by comparing architectural innovations with pretraining objectives. |
| Outcome: | The proposed model outperforms a token-based model on a set of evaluation tasks with a fixed training procedure. |
You should evaluate your language model on marginal likelihood over tokenisations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Neural language models typically tokenise input text into sub-word units to achieve an open vocabulary. |
| Approach: | They propose that language models should be evaluated on their marginal likelihood over tokenisations instead. |
| Outcome: | The proposed approach is unsatisfactory and may bottleneck model out-of-domain performance. |
Seshat: a Tool for Managing and Verifying Annotation Campaigns of Audio Data (2020.lrec-1)
Copied to clipboard
Hadrien Titeux, Rachid Riad, Xuan-Nga Cao, Nicolas Hamilakis, Kris Madden, Alejandrina Cristia, Anne-Catherine Bachoud-Lévi, Emmanuel Dupoux
| Challenge: | Seshat is a software for the automated management of annotation campaigns for audio/speech data. |
| Approach: | They propose a system for the automated management of annotation campaigns for audio/speech data which addresses these challenges. |
| Outcome: | The proposed system computes an associated inter-annotator agreement with the gamma measure taking into account the categorisation and segmentation discrepancies. |
One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers (2026.acl-long)
Copied to clipboard
Diana Abagyan, Alejandro R. Salamanca, Andres Felipe Cruz-Salinas, Kris Cao, Hangyu Lin, Acyr Locatelli, Marzieh Fadaee, Ahmet Üstün, Sara Hooker
| Challenge: | Existing approaches to train multilingual large language models for many languages at once are limited due to limited model capacity, scarce high-quality data, and compute constraints. |
| Approach: | They propose to use a universal tokenizer to improve language plasticity and adaptability to new languages by up to 20%. |
| Outcome: | The proposed tokenizer improves language plasticity and improves plasticity towards languages that are completely unseen in the tokenizer and pretraining, by up to 5% win rate gain. |
Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance (2024.findings-acl)
Copied to clipboard
| Challenge: | Despite being the cornerstone of BPE, the importance of compression in the tokenization process is still unclear. |
| Approach: | They argue for the theoretical importance of compression in the tokenization process . they also demonstrate the empirical importance of compressing tokenizers for downstream success of pre-trained language models. |
| Outcome: | The proposed method can be viewed as 0-gram language modeling where equal probability is assigned to all tokens. |