Hanna Abi Akl | Other (original) (raw)

Papers by Hanna Abi Akl

arXiv (Cornell University), Oct 18, 2023

Proceedings of the ... AAAI Conference on Artificial Intelligence, Mar 24, 2024

arXiv (Cornell University), May 30, 2024

Lecture notes in networks and systems, Dec 31, 2022

arXiv (Cornell University), Oct 12, 2023

We present the tasks and the newly created dataset associated with the FinCausal Shared task on C... more We present the tasks and the newly created dataset associated with the FinCausal Shared task on Causality modelling and automatic detection in Financial news.

This document explains the annotation schemes used to label the data for the FinCausal Shared Tas... more This document explains the annotation schemes used to label the data for the FinCausal Shared Task (Mariko et al., 2020). This task is associated to the Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020), to be held at The 28th International Conference on Computational Linguistics (COLING'2020), on December 12, 2020.

Cornell University - arXiv, Nov 4, 2022

We present the FinCausal 2020 Shared Task on Causality Detection in Financial Documents and the a... more We present the FinCausal 2020 Shared Task on Causality Detection in Financial Documents and the associated FinCausal dataset, and discuss the participating systems and results. Two sub-tasks are proposed: a binary classification task (Task 1) and a relation extraction task (Task 2). A total of 16 teams submitted runs across the two Tasks and 13 of them contributed with a system description paper. This workshop is associated to the Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020), held at The 28th International Conference on Computational Linguistics (COLING'2020), Barcelona, Spain on September 12, 2020.

In this paper, we explore strategies to detect and evaluate counterfactual sentences. We describe... more In this paper, we explore strategies to detect and evaluate counterfactual sentences. We describe our system for SemEval-2020 Task 5: Modeling Causal Reasoning in Language: Detecting Counterfactuals. We use a BERT base model for the classification task and build a hybrid BERT Multi-Layer Perceptron system to handle the sequence identification task. Our experiments show that while introducing syntactic and semantic features does little in improving the system in the classification task, using these types of features as cascaded linear inputs to fine-tune the sequence-delimiting ability of the model ensures it outperforms other similar-purpose complex systems like BiLSTM-CRF in the second task. Our system achieves an F1 score of 85.00% in Task 1 and 83.90% in Task 2.

As part of FNP Workshop Series, “Title Detection” is one of the two shared tasks proposed on Fina... more As part of FNP Workshop Series, “Title Detection” is one of the two shared tasks proposed on Financial Document Structure Extraction. The objective of the task was to classify a given text block, that had been extracted from financial prospectuses in pdf format, as a title. Our DNN-based approach scored a weighted F1 of 97.16% on the test data.

ArXiv, 2020

In this paper, we explore strategies to detect and evaluate counterfactual sentences. Since causa... more In this paper, we explore strategies to detect and evaluate counterfactual sentences. Since causal insight is an inherent characteristic of a counterfactual, is it possible to use this information in order to locate antecedent and consequent fragments in counterfactual statements? We thus propose to compare and evaluate models to correctly identify and chunk counterfactual sentences. In our experiments, we attempt to answer the following questions: First, can a learned model discern counterfactual statements reasonably well? Second, is it possible to clearly identify antecedent and consequent parts of counterfactual sentences?

This paper presents a multi-modal approach to FinTOC-2021 Shared Task. With help of a finetuned F... more This paper presents a multi-modal approach to FinTOC-2021 Shared Task. With help of a finetuned Faster-RCNN our solution achieved a Precision score comparatively better than other participants.

In this paper, we present our approaches for the FinSim-3 Shared Task 2021: Learning Semantic Sim... more In this paper, we present our approaches for the FinSim-3 Shared Task 2021: Learning Semantic Similarities for the Financial Domain. The aim of this shared task is to correctly classify a list of given terms from the financial domain into the most relevant hypernym (or top-level) concept in an external ontology. For our system submission, we evaluate two methods: a Sentence-RoBERTa (SRoBERTa) embeddings model pre-trained on a custom corpus, and a dual word-sentence embeddings model that builds on the first method by improving the proposed baseline word embeddings construction using the FastText model to boost the classification performance. Our system ranks 2 overall on both metrics, scoring 0.917 on Average Accuracy and 1.141 on Mean Rank.