Papers by Tom Sherborne

8 papers
Compositional Generalisation for Explainable Hate Speech Detection (2025.emnlp-main)

Copied to clipboard

Challenge: Hate speech detection models struggle to generalise beyond their training data . dataset biases and the use of sentence-level labels fail to teach the underlying structure of hate speech.
Approach: They propose to use a dataset to train models with fine-grained, span-level annotations . they find that combinations of expressions that deviate from those seen during training are difficult to detect .
Outcome: The proposed model can generalise to a dataset with equal frequency across all contexts while achieving state-of-the-art performance on the human-sourced PLEAD.
Meta-Learning a Cross-lingual Manifold for Semantic Parsing (2023.tacl-1)

Copied to clipboard

Challenge: Recent work has found success with machine translation or zero-shot methods . however, these approaches can struggle to model how native speakers ask questions .
Approach: They propose a meta-learning algorithm to leverage minimal annotated examples in new languages for few-shot cross-lingual semantic parsing.
Outcome: The proposed approach trains a parser with maximum sample efficiency in six languages on ATIS.
Extrinsic Evaluation of Machine Translation Metrics (2023.acl-long)

Copied to clipboard

Challenge: MT metrics are widely used to distinguish the quality of machine translation systems across relatively large test sets.
Approach: They evaluate the segment-level performance of the most widely used MT metrics by correlating them with how useful they are for downstream tasks.
Outcome: The MT metrics are widely used to distinguish the quality of machine translation systems across relatively large test sets.
Scalable Data Ablation Approximations for Language Models through Modular Training and Merging (2024.emnlp-main)

Copied to clipboard

Challenge: Training data compositions for Large Language Models (LLMs) can significantly affect their downstream performance.
Approach: They propose a method which trains individual models on subsets of a training corpus and reuses them across evaluations of combinations of subset.
Outcome: The proposed method improves training efficiency by scaling only linearly with respect to new data.
Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing (2023.tacl-1)

Copied to clipboard

Challenge: Existing work on cross-lingual semantic parsing has focused on English . a few-shot approach to parse from natural languages is comparatively unexplored .
Approach: They propose a method that minimizes cross-lingual divergence between probabilistic latent variables by Optimal Transport.
Outcome: The proposed method improves performance even without parallel input translations on two datasets.
Zero-Shot Cross-lingual Semantic Parsing (2022.acl-long)

Copied to clipboard

Challenge: Recent work in cross-lingual semantic parsing assumes access to high-quality machine translation systems and word alignment tools.
Approach: They propose a multi-task encoder-decoder model to transfer parsing knowledge to additional languages using only English-logical form paired data and in-domain natural language corpora.
Outcome: The proposed model performs significantly above translation-based baselines and competes with the supervised upper-bound.
Bootstrapping a Crosslingual Semantic Parser (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in semantic parsing are limited to English but professional translation can be prohibitively expensive.
Approach: They adapt a semantic parser trained on a single language to new languages and multiple domains with minimal annotation.
Outcome: The proposed approach achieves parsing accuracy within 2% of translation using only 50% of training data.
On Leakage of Code Generation Evaluation Datasets (2024.findings-emnlp)

Copied to clipboard

Challenge: In this paper, we discuss contamination by code generation test sets in large language models.
Approach: They propose to use Python to test code generation test sets for contamination . they find that code generation is an important skill for large language models to master .
Outcome: The proposed benchmarks are uncontaminated and provide a new insight into code generation.

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