Search Results for author: Adam Jatowt

Found 41 papers, 9 papers with code

Generator-Retriever-Generator Approach for Open-Domain Question Answering

1 code implementation21 Jul 2023 Abdelrahman Abdallah, Adam Jatowt

Open-domain question answering (QA) tasks usually require the retrieval of relevant information from a large corpus to generate accurate answers.

Language Modelling Large Language Model +3

ArabicaQA: A Comprehensive Dataset for Arabic Question Answering

1 code implementation26 Mar 2024 Abdelrahman Abdallah, Mahmoud Kasem, Mahmoud Abdalla, Mohamed Mahmoud, Mohamed Elkasaby, Yasser Elbendary, Adam Jatowt

In conclusion, ArabicaQA, AraDPR, and the benchmarking of LLMs in Arabic question answering offer significant advancements in the field of Arabic NLP.

Benchmarking Machine Reading Comprehension +4

ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages

1 code implementation26 Mar 2024 Bhawna Piryani, Jamshid Mozafari, Adam Jatowt

Therefore, to enable realistic testing of QA models, our dataset can be used in three different ways: answering questions from raw and noisy content, answering questions from cleaner, corrected version of the content, as well as answering questions from scanned images of newspaper pages.

Machine Reading Comprehension Optical Character Recognition (OCR) +1

Citation Recommendation: Approaches and Datasets

1 code implementation17 Feb 2020 Michael Färber, Adam Jatowt

In recent years, several approaches and evaluation data sets have been presented.

Citation Recommendation

A Neural Conversation Generation Model via Equivalent Shared Memory Investigation

1 code implementation20 Aug 2021 Changzhen Ji, Yating Zhang, Xiaozhong Liu, Adam Jatowt, Changlong Sun, Conghui Zhu, Tiejun Zhao

Nevertheless, few works utilized the knowledge extracted from similar conversations for utterance generation.

Text Generation

Temporal Blind Spots in Large Language Models

1 code implementation22 Jan 2024 Jonas Wallat, Adam Jatowt, Avishek Anand

In this study, we aim to investigate the underlying limitations of general-purpose LLMs when deployed for tasks that require a temporal understanding.

Natural Language Understanding

TriviaHG: A Dataset for Automatic Hint Generation from Factoid Questions

1 code implementation27 Mar 2024 Jamshid Mozafari, Anubhav Jangra, Adam Jatowt

To evaluate the TriviaHG dataset and the proposed evaluation method, we enlisted 10 individuals to annotate 2, 791 hints and tasked 6 humans with answering questions using the provided hints.

TriviaQA

A Multi-Attention based Neural Network with External Knowledge for Story Ending Predicting Task

no code implementations COLING 2018 Qian Li, Ziwei Li, Jin-Mao Wei, Yanhui Gu, Adam Jatowt, Zhenglu Yang

Enabling a mechanism to understand a temporal story and predict its ending is an interesting issue that has attracted considerable attention, as in case of the ROC Story Cloze Task (SCT).

Common Sense Reasoning Feature Engineering +1

HistoryComparator: Interactive Across-Time Comparison in Document Archives

no code implementations COLING 2016 Adam Jatowt, Marc Bron

Recent years have witnessed significant increase in the number of large scale digital collections of archival documents such as news articles, books, etc.

Clustering Decision Making +1

Spatio-Temporal Prediction of Dialectal Variant Usage

no code implementations WS 2019 P{\'e}ter Jeszenszky, Panote Siriaraya, Philipp Stoeckle, Adam Jatowt

With the assumption of the {`}contact effect{'}, i. e. contact possibility (contact and isolation) between speaker communities being responsible for language change, and the apparent time hypothesis, we aim to predict the usage of dialectal variants.

Joint Event Extraction along Shortest Dependency Paths using Graph Convolutional Networks

no code implementations19 Mar 2020 Ali Balali, Masoud Asadpour, Ricardo Campos, Adam Jatowt

Also, an attention-based graph convolutional network is proposed, to carry syntactically related information along the shortest paths between argument candidates that captures and aggregates the latent associations between arguments; a problem that has been overlooked by most of the literature.

Event Extraction Information Retrieval +3

ECIR 2020 Workshops: Assessing the Impact of Going Online

no code implementations14 May 2020 Sérgio Nunes, Suzanne Little, Sumit Bhatia, Ludovico Boratto, Guillaume Cabanac, Ricardo Campos, Francisco M. Couto, Stefano Faralli, Ingo Frommholz, Adam Jatowt, Alípio Jorge, Mirko Marras, Philipp Mayr, Giovanni Stilo

In this report, we describe the experience of organizing the ECIR 2020 Workshops in this scenario from two perspectives: the workshop organizers and the workshop participants.

Multi-Modal Summary Generation using Multi-Objective Optimization

no code implementations19 May 2020 Anubhav Jangra, Sriparna Saha, Adam Jatowt, Mohammad Hasanuzzaman

Significant development of communication technology over the past few years has motivated research in multi-modal summarization techniques.

Dataset for Temporal Analysis of English-French Cognates

no code implementations LREC 2020 Esteban Frossard, Mickael Coustaty, Antoine Doucet, Adam Jatowt, Simon Hengchen

Languages change over time and, thanks to the abundance of digital corpora, their evolutionary analysis using computational techniques has recently gained much research attention.

Annotating and Analyzing Biased Sentences in News Articles using Crowdsourcing

no code implementations LREC 2020 Sora Lim, Adam Jatowt, Michael F{\"a}rber, Masatoshi Yoshikawa

In this paper, we propose a novel news bias dataset which facilitates the development and evaluation of approaches for detecting subtle bias in news articles and for understanding the characteristics of biased sentences.

Bias Detection Fake News Detection +1

GMH: A General Multi-hop Reasoning Model for KG Completion

no code implementations EMNLP 2021 Yao Zhang, Hongru Liang, Adam Jatowt, Wenqiang Lei, Xin Wei, Ning Jiang, Zhenglu Yang

To the best of our knowledge, there lacks a general framework that approaches multi-hop reasoning in mixed long-short distance reasoning scenarios.

Knowledge Graphs

Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction

no code implementations22 Dec 2020 Yao Zhang, Xu Zhang, Jun Wang, Hongru Liang, Wenqiang Lei, Zhe Sun, Adam Jatowt, Zhenglu Yang

The current methods for the link prediction taskhavetwonaturalproblems:1)the relation distributions in KGs are usually unbalanced, and 2) there are many unseen relations that occur in practical situations.

Knowledge Graphs Link Prediction +1

Fact-Tree Reasoning for N-ary Question Answering over Knowledge Graphs

no code implementations Findings (ACL) 2022 Yao Zhang, Peiyao Li, Hongru Liang, Adam Jatowt, Zhenglu Yang

In the question answering(QA) task, multi-hop reasoning framework has been extensively studied in recent years to perform more efficient and interpretable answer reasoning on the Knowledge Graph(KG).

Knowledge Graphs Question Answering

ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections

no code implementations8 Sep 2021 Jiexin Wang, Adam Jatowt, Masatoshi Yoshikawa

In the last few years, open-domain question answering (ODQA) has advanced rapidly due to the development of deep learning techniques and the availability of large-scale QA datasets.

Open-Domain Question Answering

A Survey on Multi-modal Summarization

no code implementations11 Sep 2021 Anubhav Jangra, Sourajit Mukherjee, Adam Jatowt, Sriparna Saha, Mohammad Hasanuzzaman

The new era of technology has brought us to the point where it is convenient for people to share their opinions over an abundance of platforms.

Multi-TimeLine Summarization (MTLS): Improving Timeline Summarization by Generating Multiple Summaries

no code implementations ACL 2021 Yi Yu, Adam Jatowt, Antoine Doucet, Kazunari Sugiyama, Masatoshi Yoshikawa

In this paper, we address a novel task, Multiple TimeLine Summarization (MTLS), which extends the flexibility and versatility of Time-Line Summarization (TLS).

Timeline Summarization

Multilingual Epidemiological Text Classification: A Comparative Study

no code implementations COLING 2020 Stephen Mutuvi, Emanuela Boros, Antoine Doucet, Adam Jatowt, Ga{\"e}l Lejeune, Moses Odeo

We conduct a comparative study of different machine and deep learning text classification models using a dataset comprising news articles related to epidemic outbreaks from six languages, four low-resourced and two high-resourced, in order to analyze the influence of the nature of the language, the structure of the document, and the size of the data.

Multilingual text classification text-classification +1

A Survey on Multi-hop Question Answering and Generation

no code implementations19 Apr 2022 Vaibhav Mavi, Anubhav Jangra, Adam Jatowt

This implies that different datasets and models differ significantly which makes the field challenging to generalize and survey.

Multi-hop Question Answering Question Answering +1

Fine-tuning de modèles de langues pour la veille épidémiologique multilingue avec peu de ressources (Fine-tuning Language Models for Low-resource Multilingual Epidemic Surveillance)

no code implementations JEP/TALN/RECITAL 2022 Stephen Mutuvi, Emanuela Boros, Antoine Doucet, Adam Jatowt, Gaël Lejeune, Moses Odeo

Dans cet article, nous explorons plusieurs hypothèses concernant les facteurs qui pourraient avoir une influence sur les performances d’un système d’extraction d’événements épidémiologiques dans un scénario multilingue à faibles ressources : le type de modèle pré-entraîné, la qualité du tokenizer ainsi que les caractéristiques des entités à extraire.

MAKED: Multi-lingual Automatic Keyword Extraction Dataset

no code implementations LREC 2022 Yash Verma, Anubhav Jangra, Sriparna Saha, Adam Jatowt, Dwaipayan Roy

Keyword extraction is an integral task for many downstream problems like clustering, recommendation, search and classification.

Clustering Keyword Extraction

A Survey of Automatic Text Summarization Using Graph Neural Networks

no code implementations COLING 2022 Marco Ferdinand Salchner, Adam Jatowt

Although automatic text summarization (ATS) has been researched for several decades, the application of graph neural networks (GNNs) to this task started relatively recently.

Text Summarization

A Survey on Medical Document Summarization

no code implementations3 Dec 2022 Raghav Jain, Anubhav Jangra, Sriparna Saha, Adam Jatowt

The internet has had a dramatic effect on the healthcare industry, allowing documents to be saved, shared, and managed digitally.

Document Summarization

Predicting Companies' ESG Ratings from News Articles Using Multivariate Timeseries Analysis

no code implementations13 Nov 2022 Tanja Aue, Adam Jatowt, Michael Färber

Environmental, social and governance (ESG) engagement of companies moved into the focus of public attention over recent years.

An Overview Of Temporal Commonsense Reasoning and Acquisition

no code implementations28 Jul 2023 Georg Wenzel, Adam Jatowt

Temporal commonsense reasoning refers to the ability to understand the typical temporal context of phrases, actions, and events, and use it to reason over problems requiring such knowledge.

Common Sense Reasoning Language Modelling +3

Measuring Variety, Balance, and Disparity: An Analysis of Media Coverage of the 2021 German Federal Election

no code implementations7 Aug 2023 Michael Färber, Jannik Schwade, Adam Jatowt

Determining and measuring diversity in news articles is important for a number of reasons, including preventing filter bubbles and fueling public discourse, especially before elections.

Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation

no code implementations25 Oct 2023 Jiexin Wang, Liuwen Cao, Xitong Luo, Zhiping Zhou, Jiayuan Xie, Adam Jatowt, Yi Cai

Moreover, our study identifies weaknesses in existing models' ability to repair vulnerable code, even when provided with vulnerability information.

Code Generation Code Repair

Temporal Validity Change Prediction

no code implementations1 Jan 2024 Georg Wenzel, Adam Jatowt

Temporal validity is an important property of text that is useful for many downstream applications, such as recommender systems, conversational AI, or story understanding.

Benchmarking Recommendation Systems +1

Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis

no code implementations6 Mar 2024 Abdelrahman Abdallah, Daniel Eberharter, Zoe Pfister, Adam Jatowt

This paper presents a comprehensive survey of research works on the topic of form understanding in the context of scanned documents.

Cannot find the paper you are looking for? You can Submit a new open access paper.