Papers by Diego Antognini

9 papers
Rationalization through Concepts (2021.findings-acl)

Copied to clipboard

Challenge: Existing models that explain complex decisions are limited because of their lack of interpretability.
Approach: They propose a model that extracts text snippets as concepts and infers which ones are described in the document.
Outcome: The proposed model outperforms state-of-the-art methods trained on each aspect label independently.
pNLP-Mixer: an Efficient all-MLP Architecture for Language (2023.acl-industry)

Copied to clipboard

Challenge: large pre-trained language models are impractical for on-device applications due to their size and inference cost.
Approach: They propose an embedding-free MLP-Mixer model for on-device NLP that achieves high weight-efficiency thanks to a novel projection layer.
Outcome: The proposed model beats state-of-the-art of tiny models by 97.8% on two datasets . it beats mBERT on MTOP and multiATIS, while using 170x less parameters .
GameWikiSum: a Novel Large Multi-Document Summarization Dataset (2020.lrec-1)

Copied to clipboard

Challenge: Existing datasets contain only hundreds of samples, resulting in heavy reliance on hand-crafted features or manually annotated data.
Approach: They propose a new domain-specific dataset for multi-document summarization that is 100 times larger than commonly used datasets.
Outcome: The proposed dataset is 100 times larger than commonly used datasets and in another domain than news.
Assistive Recipe Editing through Critiquing (2023.eacl-main)

Copied to clipboard

Challenge: Existing methods for generating recipes that satisfy dietary restrictions are inconsistent or incoherent and paired datasets are not available at scale.
Approach: They propose to build a hierarchical denoising auto-encoder that edits recipes given ingredient-level critiques by interacting with the predicted ingredients.
Outcome: The proposed model can more effectively edit recipes compared to strong language models and iteratively rewrites recipes to satisfy user feedback.
Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization (D19-54)

Copied to clipboard

Challenge: Existing methods for summarizing documents rely on hand-crafted features or additional annotated data.
Approach: They propose a method that makes use of two types of sentence embeddings . the method uses universal embeddable and domain-specific embeddible features .
Outcome: The proposed method achieves competitive results on two types of summary, consisting of 665 bytes and 100 words.
HotelRec: a Novel Very Large-Scale Hotel Recommendation Dataset (2020.lrec-1)

Copied to clipboard

Challenge: State-of-the-art deep learning-based recommender systems require large datasets to achieve their best performance.
Approach: They propose to use TripAdvisor to build a large-scale hotel recommendation dataset with 50 million reviews.
Outcome: The proposed dataset is the largest publicly available hotel recommendation dataset, based on TripAdvisor, with 50 million reviews.
Unsupervised Term Extraction for Highly Technical Domains (2022.emnlp-industry)

Copied to clipboard

Challenge: Term extraction is an important task for knowledge discovery platforms because domain specific terms are the linguistic representation of domainspecific concepts.
Approach: They propose a term extraction subsystem that uses an unsupervised annotator to generate training data to fine-tune transformer models.
Outcome: The proposed system can generalize across domains while reducing latency and inference time while preserving the high performance of the existing system.
Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Despite the impressive performance of large-scale language models, their ability to reason through complex problems remains a bottleneck.
Approach: They propose a method which diversifies reasoning paths from specific surface forms of the problem to improve mathematical reasoning performance.
Outcome: The proposed approach improves mathematical reasoning performance over vanilla self-consistency, especially for problems initially deemed unsolvable.
Extracting Text Representations for Terms and Phrases in Technical Domains (2023.acl-industry)

Copied to clipboard

Challenge: Large pre-trained language models are extensively used in modern NLP systems.
Approach: They propose an unsupervised approach to encoding using character-based models and pre-trained sentence encoders to reconstruct large pre-trained embedding matrices.
Outcome: The proposed approach matches the quality of sentence encoders in technical domains and is 5 times smaller and up to 10 times faster on high-end GPUs.

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