Information aggregation for multi-head attention with routing-by-agreement

J Li, B Yang, ZY Dou, X Wang, MR Lyu, Z Tu - arXiv preprint arXiv …, 2019 - arxiv.org
… We evaluate the performance of the aggregated representations on both linguistic
probing tasks as well as machine translation tasks. The probing tasks (Conneau et al.…

A distributional and orthographic aggregation model for english derivational morphology

D Deutsch, J Hewitt, D Roth - … of the 56th Annual Meeting of the …, 2018 - aclanthology.org
… In this work, we tackle the task of derived word generation. … We identify two key problems in
generating derived words … a novel aggregation model of derived word generation that learns …

AutoCaption: An approach to generate natural language description from visualization automatically

C Liu, L Xie, Y Han, D Wei… - 2020 IEEE Pacific …, 2020 - ieeexplore.ieee.org
… We derive the fact in natural language from the feature. Specifically, the … charts in natural
language: A caption generation system. … Building applied natural language generation systems. …

Data-driven news generation for automated journalism

L Leppänen, M Munezero… - … language generation, 2017 - aclanthology.org
Aggregation The aggregation component simply checks whether two subsequent templates
contain a common prefix of one or more tokens. If they do, and the first sentence is not …

Knowledge Graph Completion Algorithm Based on Probabilistic Fuzzy Information Aggregation and Natural Language Processing Technology

C Zhang, K Lu - Mathematics, 2022 - mdpi.com
… information aggregation and natural language processing … information aggregation and
natural language processing … fuzzy information aggregation and natural language processing …

Evaluation of text generation: A survey

A Celikyilmaz, E Clark, J Gao - arXiv preprint arXiv:2006.14799, 2020 - arxiv.org
… The paper surveys evaluation methods of natural language generation (NLG) systems that
… they are aggregated. Collating similar sentences to improve readability with a natural flow …

Bold: Dataset and metrics for measuring biases in open-ended language generation

J Dhamala, T Sun, V Kumar, S Krishna… - Proceedings of the …, 2021 - dl.acm.org
… quantify biases in various Natural language processing (NLP) … in open-ended natural
language generation. There are differ… Hence, we propose two alternative ways to aggregate word …

Interacting with financial data using natural language

V Plachouras, C Smiley, H Bretz, O Taylor… - Proceedings of the 39th …, 2016 - dl.acm.org
… Next, the results are passed to the Answer Aggregation and Rendering module, which is
responsible for generating a high quality human-readable description of the results, providing …

CEAN: Contrastive Event Aggregation Network with LLM-based Augmentation for Event Extraction

Z Meng, T Liu, H Zhang, K Feng… - Proceedings of the 18th …, 2024 - aclanthology.org
… Event Extraction is a crucial yet arduous task in natural language processing (NLP), as its
performance is significantly hindered by laborious data annotation. Given this challenge, …

Around the GLOBE: Numerical Aggregation Question-answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks

O Suissa, M Zhitomirsky-Geffet… - ACM Journal on …, 2023 - dl.acm.org
… and require additional aggregation function types that … aggregation QA task in the genealogical
domain. Cultural heritage corpora are highly suitable for using different natural language