Papers by Francesca Bonin

9 papers
Know Who Your Friends Are: Understanding Social Connections from Unstructured Text (N18-5)

Copied to clipboard

Challenge: Having an understanding of interpersonal relationships is helpful in many contexts.
Approach: They propose a system that extracts qualitative and quantitative information from texts and aggregates it to provide a condensed view of relationships.
Outcome: The proposed system extracts qualitative and quantitative information elements about interactions and aggregates those to provide a condensed view of relationships.
Accelerating the Discovery of Semantic Associations from Medical Literature: Mining Relations Between Diseases and Symptoms (2022.emnlp-industry)

Copied to clipboard

Challenge: Existing methods to extract semantic associations from medical literature do not take into account the semantics of sentences from which entity co-occurrences are extracted.
Approach: They propose a system for the automatic discovery of semantic associations between different entities such as diseases and their symptoms using a semantic network and a binary relation classification model trained with distant supervision.
Outcome: The proposed system validates the extracted associations against a publicly available list of disease-symptom pairs against 14M PubMed abstracts.
Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction (P19-1)

Copied to clipboard

Challenge: Recent years have witnessed a significant increase in laboratory-based evaluation benchmarks in many scientific disciplines.
Approach: They propose to use NLP datasets to extract task, dataset, metric and score from NLP papers to build automatic leaderboards.
Outcome: The proposed model outperforms baselines in the NLP domain by a large margin.
HBCP Corpus: A New Resource for the Analysis of Behavioural Change Intervention Reports (2020.lrec-1)

Copied to clipboard

Challenge: Automated extraction of the reports’ intervention content, population, settings and their results is essential in synthesising and summarising the literature.
Approach: They propose to build a corpus of published behaviour change intervention evaluation reports aimed at smoking cessation and to release an annotation dataset.
Outcome: The proposed corpus and annotation dataset are being made available to the community.
Decision Conversations Decoded (N18-5)

Copied to clipboard

Challenge: a system that tracks the decision process is aimed at group decision making facilitation . the system tracks the options being considered, why they are proposed, by whom and with whose support.
Approach: They propose a system that tracks the decision process and organizes collective thoughts into a summary . the system is based on the scientific field of Decision Analysis .
Outcome: The proposed system can help identify agreement and dissent or recommend an alternative based on this information.
A Summarization System for Scientific Documents (D19-3)

Copied to clipboard

Challenge: a qualitative user study identified the most valuable scenarios for scientific content consumption.
Approach: They propose a system that retrieves and summarizes scientific documents for a given information need.
Outcome: The proposed system ingested 270,000 scientific papers and validated with human experts.
SLIDE - a Sentiment Lexicon of Common Idioms (L18-1)

Copied to clipboard

Challenge: Compositional solutions for phrase sentiment are not able to handle idioms because their sentiment is not derived from the sentiment of the individual words.
Approach: They propose a crowdsourcing approach for collecting sentiment annotations of idiomatic expressions using crowdsourcing.
Outcome: The proposed approach is able to capture sentiment strength and ambiguity in idiomatic expressions using crowdsourcing.
TDMSci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and Metrics (2021.eacl-main)

Copied to clipboard

Challenge: Recent efforts to extract tasks, datasets and evaluation metrics from scientific literature focus on abstracts only.
Approach: They propose a corpus that contains domain expert annotations for Task (T), Dataset (D), Metric (M) entities extracted from NLP papers.
Outcome: The proposed corpus contains domain expert annotations for Task (T), Dataset (D), Metric (M) entities extracted from NLP papers.
Towards a music-language mapping (L18-1)

Copied to clipboard

Challenge: a novel research idea investigates the possibility of musical input to speech interaction systems.
Approach: They propose a musical language processing idea that investigates the possibility of musical input to speech interaction systems.
Outcome: The proposed method could be used to map musical pieces and dialogues based on frequency of musical patterns . the proposed method is universal among different languages and easy to learn for musicians .

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