BERTopic: Neural topic modeling with a class-based TF-IDF procedure

M Grootendorst - arXiv preprint arXiv:2203.05794, 2022 - arxiv.org
Topic models can be useful tools to discover latent topics in collections of documents.
Recent studies have shown the feasibility of approach topic modeling as a clustering task …

Decomposing nerf for editing via feature field distillation

S Kobayashi, E Matsumoto… - Advances in Neural …, 2022 - proceedings.neurips.cc
Emerging neural radiance fields (NeRF) are a promising scene representation for computer
graphics, enabling high-quality 3D reconstruction and novel view synthesis from image …

What Makes Good In-Context Examples for GPT-?

J Liu, D Shen, Y Zhang, B Dolan, L Carin… - arXiv preprint arXiv …, 2021 - arxiv.org
GPT-$3 $ has attracted lots of attention due to its superior performance across a wide range
of NLP tasks, especially with its powerful and versatile in-context few-shot learning ability …

Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models

J Ni, GH Abrego, N Constant, J Ma, KB Hall… - arXiv preprint arXiv …, 2021 - arxiv.org
We provide the first exploration of sentence embeddings from text-to-text transformers (T5).
Sentence embeddings are broadly useful for language processing tasks. While T5 achieves …

Language-agnostic BERT sentence embedding

F Feng, Y Yang, D Cer, N Arivazhagan… - arXiv preprint arXiv …, 2020 - arxiv.org
While BERT is an effective method for learning monolingual sentence embeddings for
semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019) …

A brief overview of universal sentence representation methods: A linguistic view

R Li, X Zhao, MF Moens - ACM Computing Surveys (CSUR), 2022 - dl.acm.org
How to transfer the semantic information in a sentence to a computable numerical
embedding form is a fundamental problem in natural language processing. An informative …

Unifiedskg: Unifying and multi-tasking structured knowledge grounding with text-to-text language models

T Xie, CH Wu, P Shi, R Zhong, T Scholak… - arXiv preprint arXiv …, 2022 - arxiv.org
Structured knowledge grounding (SKG) leverages structured knowledge to complete user
requests, such as semantic parsing over databases and question answering over …

Amazon-m2: A multilingual multi-locale shopping session dataset for recommendation and text generation

W Jin, H Mao, Z Li, H Jiang, C Luo… - Advances in …, 2024 - proceedings.neurips.cc
Modeling customer shopping intentions is a crucial task for e-commerce, as it directly
impacts user experience and engagement. Thus, accurately understanding customer …

Results of the WMT21 metrics shared task: Evaluating metrics with expert-based human evaluations on TED and news domain

M Freitag, R Rei, N Mathur, C Lo… - Proceedings of the …, 2021 - aclanthology.org
This paper presents the results of the WMT21 Metrics Shared Task. Participants were asked
to score the outputs of the translation systems competing in the WMT21 News Translation …

Ai psychometrics: Assessing the psychological profiles of large language models through psychometric inventories

M Pellert, CM Lechner, C Wagner… - Perspectives on …, 2024 - journals.sagepub.com
We illustrate how standard psychometric inventories originally designed for assessing
noncognitive human traits can be repurposed as diagnostic tools to evaluate analogous …