Search Results for author:
Found 10 papers, 1 papers with code
Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
This method can reduce the space & memory footprint of ColBERT indexes by 50% with virtually no retrieval performance degradation.
rerankers: A Lightweight Python Library to Unify Ranking Methods
This paper presents rerankers, a Python library which provides an easy-to-use interface to the most commonly used re-ranking approaches.
JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources
Neural Information Retrieval has advanced rapidly in high-resource languages, but progress in lower-resource ones such as Japanese has been hindered by data scarcity, among other challenges.
Towards Better Monolingual Japanese Retrievers with Multi-Vector Models
As language-specific training data tends to be sparsely available compared to English, document retrieval in many languages has been largely relying on multilingual models.
Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matchers
We generate synthetic training data for the entirety of ESCO skills and train a classifier to extract skill mentions from job posts.
Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification
Furthermore, we observe that the wording of the prompt is a critical factor in eliciting the appropriate "reasoning" in the model, and that seemingly minor aspects of the prompt significantly affect the model's performance.
The Unreasonable Effectiveness of the Baseline: Discussing SVMs in Legal Text Classification
We aim to highlight an interesting trend to contribute to the ongoing debate around advances within legal Natural Language Processing.
Ranked #8 on
Natural Language Understanding
on LexGLUE
LegaLMFiT: Efficient Short Legal Text Classification with LSTM Language Model Pre-Training
Large Transformer-based language models such as BERT have led to broad performance improvements on many NLP tasks.
Deep Embeddings of Contextual Assessment Data for Improving Performance Prediction
We introduce DeepPerfEmb, or DPE, a new deep-learning model that captures dense representations of students’ online behaviour and meta-data about students and educational content.
EduBERT: Pretrained Deep Language Models for Learning Analytics
The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks.
