1 code implementation • Findings (NAACL) 2022 • Viet Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Nguyen
This work presents a new human-annotated corpus, called BehancePR, for punctuation restoration in livestreaming video transcripts.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • NAACL (NLPMC) 2021 • Khalil Mrini, Franck Dernoncourt, Walter Chang, Emilia Farcas, Ndapa Nakashole
Understanding the intent of medical questions asked by patients, or Consumer Health Questions, is an essential skill for medical Conversational AI systems.
no code implementations • NAACL (BioNLP) 2021 • Khalil Mrini, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Emilia Farcas, Ndapa Nakashole
We show that both transfer learning methods combined achieve the highest ROUGE scores.
no code implementations • Findings (ACL) 2022 • Amir Pouran Ben Veyseh, Ning Xu, Quan Tran, Varun Manjunatha, Franck Dernoncourt, Thien Nguyen
Toxic span detection is the task of recognizing offensive spans in a text snippet.
no code implementations • Findings (ACL) 2022 • Amir Pouran Ben Veyseh, Minh Van Nguyen, Franck Dernoncourt, Bonan Min, Thien Nguyen
Event Argument Extraction (EAE) is one of the sub-tasks of event extraction, aiming to recognize the role of each entity mention toward a specific event trigger.
no code implementations • SemEval (NAACL) 2022 • Viet Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Nguyen
We describe Symlink, a SemEval shared task of extracting mathematical symbols and their descriptions from LaTeX source of scientific documents.
no code implementations • Findings (NAACL) 2022 • Adyasha Maharana, Quan Tran, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Mohit Bansal
We construct and present a new multimodal dataset consisting of software instructional livestreams and containing manual annotations for both detailed and abstract procedural intent that enable training and evaluation of joint video and text understanding models.
no code implementations • COLING 2022 • Amir Pouran Ben Veyseh, Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen
As such, the challenges of EE in informal and noisy texts are not adequately studied.
no code implementations • COLING 2022 • Amir Pouran Ben Veyseh, Quan Hung Tran, Seunghyun Yoon, Varun Manjunatha, Hanieh Deilamsalehy, Rajiv Jain, Trung Bui, Walter W. Chang, Franck Dernoncourt, Thien Huu Nguyen
To this end, this work studies new challenges of KP in transcripts of videos, an understudied domain for KP that involves informal texts and non-cohesive presentation styles.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • Findings (NAACL) 2022 • Luis Guzman-Nateras, Viet Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Nguyen
In particular, we introduce SuicideED: a new dataset for the ED task that features seven suicidal event types to comprehensively capture suicide actions and ideation, and general risk and protective factors.
no code implementations • LREC 2022 • Viet Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Nguyen
Livestreaming videos have become an effective broadcasting method for both video sharing and educational purposes.
1 code implementation • EMNLP 2021 • Viet Lai, Franck Dernoncourt, Thien Huu Nguyen
We address the sampling bias and outlier issues in few-shot learning for event detection, a subtask of information extraction.
no code implementations • EMNLP 2021 • Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer
While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored.
1 code implementation • EMNLP (Eval4NLP) 2020 • Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Kyomin Jung
In this paper, we propose an evaluation metric for image captioning systems using both image and text information.
no code implementations • COLING 2022 • Cesa Salaam, Franck Dernoncourt, Trung Bui, Danda Rawat, Seunghyun Yoon
The prevalent use of offensive content in social media has become an important reason for concern for online platforms (customer service chat-boxes, social media platforms, etc).
1 code implementation • LREC 2022 • Amir Pouran Ben Veyseh, Viet Lai, Franck Dernoncourt, Thien Nguyen
Question-Answer (QA) is one of the effective methods for storing knowledge which can be used for future retrieval.
no code implementations • TU (COLING) 2022 • Minh Van Nguyen, Franck Dernoncourt, Thien Nguyen
As a result, such MT systems could fail to translate livestreaming video transcripts, where text is often shorter and might be grammatically incorrect.
1 code implementation • COLING 2022 • Viet Dac Lai, Amir Pouran Ben Veyseh, Minh Van Nguyen, Franck Dernoncourt, Thien Huu Nguyen
Our dataset thus enable a new research direction on cross-lingual transfer learning for ECI.
1 code implementation • COLING 2022 • Yeon Seonwoo, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, Alice Oh
We conduct three experiments 1) domain-specific document retrieval, 2) comparison of our virtual knowledge graph construction method with previous approaches, and 3) ablation study on each component of our virtual knowledge graph.
no code implementations • NAACL 2022 • Minh Van Nguyen, Bonan Min, Franck Dernoncourt, Thien Nguyen
However, previous JointIE models often assume heuristic manually-designed dependency between the task instances and mean-field factorization for the joint distribution of instance labels, thus unable to capture optimal dependencies among instances and labels to improve representation learning and IE performance.
no code implementations • NAACL 2022 • Puneet Mathur, Vlad Morariu, Verena Kaynig-Fittkau, Jiuxiang Gu, Franck Dernoncourt, Quan Tran, Ani Nenkova, Dinesh Manocha, Rajiv Jain
We introduce DocTime - a novel temporal dependency graph (TDG) parser that takes as input a text document and produces a temporal dependency graph.
no code implementations • 23 Apr 2024 • Sanat Sharma, David Seunghyun Yoon, Franck Dernoncourt, Dewang Sultania, Karishma Bagga, Mengjiao Zhang, Trung Bui, Varun Kotte
Question answering (QA) has become an important application in the advanced development of large language models.
no code implementations • 4 Apr 2024 • Dawit Mureja Argaw, Seunghyun Yoon, Fabian Caba Heilbron, Hanieh Deilamsalehy, Trung Bui, Zhaowen Wang, Franck Dernoncourt, Joon Son Chung
Long-form video content constitutes a significant portion of internet traffic, making automated video summarization an essential research problem.
no code implementations • 23 Feb 2024 • Hyunjae Kim, Seunghyun Yoon, Trung Bui, Handong Zhao, Quan Tran, Franck Dernoncourt, Jaewoo Kang
Contrastive language-image pre-training (CLIP) models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval, where the model is required to effectively process natural language input to produce an accurate visual output.
no code implementations • 3 Feb 2024 • Isabel O. Gallegos, Ryan A. Rossi, Joe Barrow, Md Mehrab Tanjim, Tong Yu, Hanieh Deilamsalehy, Ruiyi Zhang, Sungchul Kim, Franck Dernoncourt
Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases.
no code implementations • 30 Nov 2023 • Linzi Xing, Quan Tran, Fabian Caba, Franck Dernoncourt, Seunghyun Yoon, Zhaowen Wang, Trung Bui, Giuseppe Carenini
Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks.
no code implementations • 29 Nov 2023 • Puja Trivedi, Ryan Rossi, David Arbour, Tong Yu, Franck Dernoncourt, Sungchul Kim, Nedim Lipka, Namyong Park, Nesreen K. Ahmed, Danai Koutra
Most real-world networks are noisy and incomplete samples from an unknown target distribution.
no code implementations • 7 Nov 2023 • Zhongfen Deng, Seunghyun Yoon, Trung Bui, Franck Dernoncourt, Quan Hung Tran, Shuaiqi Liu, Wenting Zhao, Tao Zhang, Yibo Wang, Philip S. Yu
Then we merge the sentences selected for a specific aspect as the input for the summarizer to produce the aspect-based summary.
2 code implementations • 23 Sep 2023 • Siva Uday Sampreeth Chebolu, Franck Dernoncourt, Nedim Lipka, Thamar Solorio
Aspect-based sentiment analysis (ABSA) delves into understanding sentiments specific to distinct elements within a user-generated review.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • 17 Sep 2023 • Thuat Nguyen, Chien Van Nguyen, Viet Dac Lai, Hieu Man, Nghia Trung Ngo, Franck Dernoncourt, Ryan A. Rossi, Thien Huu Nguyen
However, when it comes to training datasets for these LLMs, especially the recent state-of-the-art models, they are often not fully disclosed.
no code implementations • 16 Sep 2023 • Jon Saad-Falcon, Joe Barrow, Alexa Siu, Ani Nenkova, David Seunghyun Yoon, Ryan A. Rossi, Franck Dernoncourt
Representing such structured documents as plain text is incongruous with the user's mental model of these documents with rich structure.
no code implementations • 15 Sep 2023 • Meryem M'hamdi, Jonathan May, Franck Dernoncourt, Trung Bui, Seunghyun Yoon
Our approach leverages meta-distillation learning based on MAML, an optimization-based Model-Agnostic Meta-Learner.
1 code implementation • 2 Sep 2023 • Isabel O. Gallegos, Ryan A. Rossi, Joe Barrow, Md Mehrab Tanjim, Sungchul Kim, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, Nesreen K. Ahmed
Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere.
2 code implementations • 29 Jul 2023 • Viet Dac Lai, Chien Van Nguyen, Nghia Trung Ngo, Thuat Nguyen, Franck Dernoncourt, Ryan A. Rossi, Thien Huu Nguyen
Okapi introduces instruction and response-ranked data in 26 diverse languages to facilitate the experiments and development of future multilingual LLM research.
no code implementations • 24 Jul 2023 • Viet Dac Lai, Abel Salinas, Hao Tan, Trung Bui, Quan Tran, Seunghyun Yoon, Hanieh Deilamsalehy, Franck Dernoncourt, Thien Huu Nguyen
Punctuation restoration is an important task in automatic speech recognition (ASR) which aim to restore the syntactic structure of generated ASR texts to improve readability.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • ICCV 2023 • Yicong Hong, Yang Zhou, Ruiyi Zhang, Franck Dernoncourt, Trung Bui, Stephen Gould, Hao Tan
Being able to perceive the semantics and the spatial structure of the environment is essential for visual navigation of a household robot.
no code implementations • 8 Jul 2023 • April Chen, Ryan A. Rossi, Namyong Park, Puja Trivedi, Yu Wang, Tong Yu, Sungchul Kim, Franck Dernoncourt, Nesreen K. Ahmed
In this article, we examine and categorize fairness techniques for improving the fairness of GNNs.
no code implementations • 2 Jun 2023 • Oriol Nieto, Zeyu Jin, Franck Dernoncourt, Justin Salamon
Spoken language recognition (SLR) is the task of automatically identifying the language present in a speech signal.
1 code implementation • 27 May 2023 • Yebowen Hu, Tim Ganter, Hanieh Deilamsalehy, Franck Dernoncourt, Hassan Foroosh, Fei Liu
However, there is a crucial lack of annotated meeting corpora for developing this technology, as it can be hard to collect meetings, especially when the topics discussed are confidential.
no code implementations • 12 Apr 2023 • Viet Dac Lai, Nghia Trung Ngo, Amir Pouran Ben Veyseh, Hieu Man, Franck Dernoncourt, Trung Bui, Thien Huu Nguyen
The answer to this question requires a thorough evaluation of ChatGPT over multiple tasks with diverse languages and large datasets (i. e., beyond reported anecdotes), which is still missing or limited in current research.
1 code implementation • 15 Feb 2023 • Catherine Yeh, Nedim Lipka, Franck Dernoncourt
People read digital documents on a daily basis to share, exchange, and understand information in electronic settings.
no code implementations • 2 Feb 2023 • Sajad Sotudeh, Nazli Goharian, Hanieh Deilamsalehy, Franck Dernoncourt
Automatically generating short summaries from users' online mental health posts could save counselors' reading time and reduce their fatigue so that they can provide timely responses to those seeking help for improving their mental state.
no code implementations • 2 Feb 2023 • Sajad Sotudeh, Hanieh Deilamsalehy, Franck Dernoncourt, Nazli Goharian
Recent Transformer-based summarization models have provided a promising approach to abstractive summarization.
no code implementations • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 • Puneet Mathur, Rajiv Jain, Ashutosh Mehra, Jiuxiang Gu, Franck Dernoncourt, Anandhavelu N, Quan Tran, Verena Kaynig-Fittkau, Ani Nenkova, Dinesh Manocha, Vlad I. Morariu
Experiments show that our approach outperforms competitive baselines by 10-15% on three diverse datasets of forms and mobile app screen layouts for the tasks of spatial region classification, higher-order group identification, layout hierarchy extraction, reading order detection, and word grouping.
1 code implementation • ICCV 2023 • Ioana Croitoru, Simion-Vlad Bogolin, Samuel Albanie, Yang Liu, Zhaowen Wang, Seunghyun Yoon, Franck Dernoncourt, Hailin Jin, Trung Bui
To study this problem, we propose the first dataset of untrimmed, long-form tutorial videos for the task of Moment Detection called the Behance Moment Detection (BMD) dataset.
no code implementations • 11 Nov 2022 • Amir Pouran Ben Veyseh, Javid Ebrahimi, Franck Dernoncourt, Thien Huu Nguyen
Event Extraction (EE) is one of the fundamental tasks in Information Extraction (IE) that aims to recognize event mentions and their arguments (i. e., participants) from text.
no code implementations • NAACL 2022 • Amir Pouran Ben Veyseh, Minh Van Nguyen, Franck Dernoncourt, Thien Huu Nguyen
Event Detection (ED) is the task of identifying and classifying trigger words of event mentions in text.
1 code implementation • 1 Nov 2022 • Phung Lai, NhatHai Phan, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios
In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models (NLMs).
no code implementations • 12 Oct 2022 • JieLin Qiu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Ding Zhao, Hailin Jin
Livestream videos have become a significant part of online learning, where design, digital marketing, creative painting, and other skills are taught by experienced experts in the sessions, making them valuable materials.
no code implementations • 10 Oct 2022 • JieLin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin
Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding.
1 code implementation • COLING 2022 • Khalil Mrini, Harpreet Singh, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Emilia Farcas, Ndapa Nakashole
The system first matches the summarized user question with an FAQ from a trusted medical knowledge base, and then retrieves a fixed number of relevant sentences from the corresponding answer document.
no code implementations • 11 Sep 2022 • Amir Pouran Ben Veyseh, Nicole Meister, Franck Dernoncourt, Thien Huu Nguyen
Keyphrase extraction is one of the essential tasks for document understanding in NLP.
no code implementations • 11 Sep 2022 • Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen
In order to alleviate this issue, one solution is to link the streaming videos with the relevant tutorial available for the tools used in the streaming video.
1 code implementation • CVPR 2023 • Ziyan Yang, Kushal Kafle, Franck Dernoncourt, Vicente Ordonez
We propose a margin-based loss for tuning joint vision-language models so that their gradient-based explanations are consistent with region-level annotations provided by humans for relatively smaller grounding datasets.
1 code implementation • Findings (NAACL) 2022 • Jaemin Cho, Seunghyun Yoon, Ajinkya Kale, Franck Dernoncourt, Trung Bui, Mohit Bansal
Toward more descriptive and distinctive caption generation, we propose using CLIP, a multimodal encoder trained on huge image-text pairs from web, to calculate multimodal similarity and use it as a reward function.
Ranked #26 on Image Captioning on COCO Captions
no code implementations • 26 Apr 2022 • Viet Dac Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen
Mathematical symbols and descriptions appear in various forms across document section boundaries without explicit markup.
no code implementations • 18 Apr 2022 • Hwanhee Lee, Cheoneum Park, Seunghyun Yoon, Trung Bui, Franck Dernoncourt, Juae Kim, Kyomin Jung
In this paper, we propose an efficient factual error correction system RFEC based on entities retrieval post-editing process.
1 code implementation • 11 Apr 2022 • Siva Uday Sampreeth Chebolu, Franck Dernoncourt, Nedim Lipka, Thamar Solorio
Aspect-based sentiment analysis (ABSA) is a natural language processing problem that requires analyzing user-generated reviews to determine: a) The target entity being reviewed, b) The high-level aspect to which it belongs, and c) The sentiment expressed toward the targets and the aspects.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)
no code implementations • 7 Apr 2022 • JieLin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin
Multimedia summarization with multimodal output can play an essential role in real-world applications, i. e., automatically generating cover images and titles for news articles or providing introductions to online videos.
1 code implementation • 20 Mar 2022 • Xiaolei Huang, Franck Dernoncourt, Mark Dredze
Clinical notes in Electronic Health Records (EHR) present rich documented information of patients to inference phenotype for disease diagnosis and study patient characteristics for cohort selection.
1 code implementation • 24 Feb 2022 • Hyounghun Kim, Doo Soon Kim, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, Mohit Bansal
To our knowledge, this is the first dataset that provides conversational image search and editing annotations, where the agent holds a grounded conversation with users and helps them to search and edit images according to their requests.
no code implementations • 19 Feb 2022 • Viet Dac Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen
Given the increasing number of livestreaming videos, automatic speech recognition and post-processing for livestreaming video transcripts are crucial for efficient data management as well as knowledge mining.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • COLING 2022 • Amir Pouran Ben Veyseh, Nicole Meister, Seunghyun Yoon, Rajiv Jain, Franck Dernoncourt, Thien Huu Nguyen
Acronym extraction is the task of identifying acronyms and their expanded forms in texts that is necessary for various NLP applications.
1 code implementation • 5 Oct 2021 • Siva Uday Sampreeth Chebolu, Franck Dernoncourt, Nedim Lipka, Thamar Solorio
Aspect-based sentiment analysis (ABSA) is an NLP task that entails processing user-generated reviews to determine (i) the target being evaluated, (ii) the aspect category to which it belongs, and (iii) the sentiment expressed towards the target and aspect pair.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
1 code implementation • EMNLP (newsum) 2021 • Sajad Sotudeh, Hanieh Deilamsalehy, Franck Dernoncourt, Nazli Goharian
Recent models in developing summarization systems consist of millions of parameters and the model performance is highly dependent on the abundance of training data.
Ranked #1 on Extreme Summarization on TLDR9+
no code implementations • 29 Sep 2021 • Phung Lai, Hai Phan, Li Xiong, Khang Phuc Tran, My Thai, Tong Sun, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios, Rajiv Jain
In this paper, we develop BitRand, a bit-aware randomized response algorithm, to preserve local differential privacy (LDP) in federated learning (FL).
1 code implementation • EMNLP 2021 • Sangwoo Cho, Franck Dernoncourt, Tim Ganter, Trung Bui, Nedim Lipka, Walter Chang, Hailin Jin, Jonathan Brandt, Hassan Foroosh, Fei Liu
With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into this wealth of knowledge.
1 code implementation • Findings (EMNLP) 2021 • Hwanhee Lee, Thomas Scialom, Seunghyun Yoon, Franck Dernoncourt, Kyomin Jung
A Visual-QA system is necessary for QACE-Img.
no code implementations • SEMEVAL 2021 • Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen
To this end, in this paper, we propose a novel model for the task of measurement relation extraction (MRE) whose goal is to recognize the relation between measured entities, quantities, and conditions mentioned in a document.
no code implementations • ACL 2021 • Amir Pouran Ben Veyseh, Viet Lai, Franck Dernoncourt, Thien Huu Nguyen
To prevent the noises inevitable in automatically generated data from hampering training process, we propose to exploit a teacher-student architecture in which the teacher is supposed to learn anchor knowledge from the original data.
no code implementations • ACL 2021 • Joe Barrow, Rajiv Jain, Nedim Lipka, Franck Dernoncourt, Vlad Morariu, Varun Manjunatha, Douglas Oard, Philip Resnik, Henning Wachsmuth
Approaches to computational argumentation tasks such as stance detection and aspect detection have largely focused on the text of independent claims, losing out on potentially valuable context provided by the rest of the collection.
no code implementations • ACL 2021 • Puneet Mathur, Rajiv Jain, Franck Dernoncourt, Vlad Morariu, Quan Hung Tran, Dinesh Manocha
We present TIMERS - a TIME, Rhetorical and Syntactic-aware model for document-level temporal relation classification in the English language.
Ranked #3 on Temporal Relation Classification on TB-Dense
1 code implementation • ACL 2021 • Khalil Mrini, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Emilia Farcas, Ndapa Nakashole
Users of medical question answering systems often submit long and detailed questions, making it hard to achieve high recall in answer retrieval.
1 code implementation • ACL 2021 • Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, Kyomin Jung
Also, we observe critical problems of the previous benchmark dataset (i. e., human annotations) on image captioning metric, and introduce a new collection of human annotations on the generated captions.
1 code implementation • CVPR 2021 • Jing Shi, Ning Xu, Yihang Xu, Trung Bui, Franck Dernoncourt, Chenliang Xu
Recently, language-guided global image editing draws increasing attention with growing application potentials.
1 code implementation • NAACL 2021 • Meryem M'hamdi, Doo Soon Kim, Franck Dernoncourt, Trung Bui, Xiang Ren, Jonathan May
We extensively evaluate our framework on two challenging cross-lingual NLU tasks: multilingual task-oriented dialog and typologically diverse question answering.
1 code implementation • 14 Apr 2021 • Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer
While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored.
1 code implementation • NAACL 2021 • Tuan Lai, Heng Ji, Trung Bui, Quan Hung Tran, Franck Dernoncourt, Walter Chang
Event coreference resolution is an important research problem with many applications.
no code implementations • NAACL 2021 • Mengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu
These two observations are further employed to formulate a measurement which can quantify the shortcut degree of each training sample.
1 code implementation • EACL (AdaptNLP) 2021 • Xiaolei Huang, Michael J. Paul, Robin Burke, Franck Dernoncourt, Mark Dredze
In this study, we treat the user interest as domains and empirically examine how the user language can vary across the user factor in three English social media datasets.
1 code implementation • EACL 2021 • Amir Pouran Ben Veyseh, Franck Dernoncourt, Walter Chang, Thien Huu Nguyen
However, none of the existing works provide a unified solution capable of processing acronyms in various domains and to be publicly available.
no code implementations • 2 Jan 2021 • Amirreza Shirani, Giai Tran, Hieu Trinh, Franck Dernoncourt, Nedim Lipka, Paul Asente, Jose Echevarria, Thamar Solorio
We evaluate a range of state-of-the-art models on this novel dataset by organizing a shared task and inviting multiple researchers to model emphasis in this new domain.
no code implementations • 22 Dec 2020 • Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen, Walter Chang, Leo Anthony Celi
To push forward research in this direction, we have organized two shared task for acronym identification and acronym disambiguation in scientific documents, named AI@SDU and AD@SDU, respectively.
no code implementations • COLING 2020 • Quan Tran, Nhan Dam, Tuan Lai, Franck Dernoncourt, Trung Le, Nham Le, Dinh Phung
Interpretability and explainability of deep neural networks are challenging due to their scale, complexity, and the agreeable notions on which the explaining process rests.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ziyan Yang, Leticia Pinto-Alva, Franck Dernoncourt, Vicente Ordonez
Our work aims to leverage visual feature space to pass information across languages.
2 code implementations • COLING 2020 • Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Hung Tran, Thien Huu Nguyen
The proposed model outperforms the state-of-the-art models on the new AD dataset, providing a strong baseline for future research on this dataset.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Amir Pouran Ben Veyseh, Nasim Nour, Franck Dernoncourt, Quan Hung Tran, Dejing Dou, Thien Huu Nguyen
In addition, we propose a mechanism to obtain the importance scores for each word in the sentences based on the dependency trees that are then injected into the model to improve the representation vectors for ABSA.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • EMNLP 2020 • Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Dejing Dou, Thien Huu Nguyen
In this work, we propose to incorporate the syntactic structures of the sentences into the deep learning models for TOWE, leveraging the syntax-based opinion possibility scores and the syntactic connections between the words.
Aspect-Based Sentiment Analysis Aspect-oriented Opinion Extraction +1
1 code implementation • Asian Chapter of the Association for Computational Linguistics 2020 • Logan Lebanoff, Franck Dernoncourt, Doo Soon Kim, Walter Chang, Fei Liu
We present an empirical study in favor of a cascade architecture to neural text summarization.
1 code implementation • EMNLP 2020 • Logan Lebanoff, Franck Dernoncourt, Doo Soon Kim, Lidan Wang, Walter Chang, Fei Liu
The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Xuanli He, Quan Hung Tran, Gholamreza Haffari, Walter Chang, Trung Bui, Zhe Lin, Franck Dernoncourt, Nhan Dam
In this paper, we explore the novel problem of graph modification, where the systems need to learn how to update an existing scene graph given a new user's command.
no code implementations • 5 Oct 2020 • Jing Shi, Ning Xu, Trung Bui, Franck Dernoncourt, Zheng Wen, Chenliang Xu
To solve this new task, we first present a new language-driven image editing dataset that supports both local and global editing with editing operation and mask annotations.
no code implementations • SEMEVAL 2020 • Sasha Spala, Nicholas A. Miller, Franck Dernoncourt, Carl Dockhorn
Research on definition extraction has been conducted for well over a decade, largely with significant constraints on the type of definitions considered.
no code implementations • SEMEVAL 2020 • Amirreza Shirani, Franck Dernoncourt, Nedim Lipka, Paul Asente, Jose Echevarria, Thamar Solorio
In this paper, we present the main findings and compare the results of SemEval-2020 Task 10, Emphasis Selection for Written Text in Visual Media.
no code implementations • 2 Aug 2020 • Lidan Wang, Franck Dernoncourt, Trung Bui
The performance of many machine learning models depends on their hyper-parameter settings.
no code implementations • ACL 2020 • Amir Pouran Ben Veyseh, Franck Dernoncourt, Dejing Dou, Thien Huu Nguyen
In order to overcome these issues, we propose a novel deep learning model for RE that uses the dependency trees to extract the syntax-based importance scores for the words, serving as a tree representation to introduce syntactic information into the models with greater generalization.
1 code implementation • WS 2020 • Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen
In this work, weformulate event detection as a few-shot learn-ing problem to enable to extend event detec-tion to new event types.
1 code implementation • ACL 2020 • Logan Lebanoff, John Muchovej, Franck Dernoncourt, Doo Soon Kim, Lidan Wang, Walter Chang, Fei Liu
We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences.
no code implementations • NAACL 2021 • Jinfeng Xiao, Lidan Wang, Franck Dernoncourt, Trung Bui, Tong Sun, Jiawei Han
Our reader-retriever first uses an offline reader to read the corpus and generate collections of all answerable questions associated with their answers, and then uses an online retriever to respond to user queries by searching the pre-constructed question spaces for answers that are most likely to be asked in the given way.
no code implementations • WS 2020 • Anthony Colas, Trung Bui, Franck Dernoncourt, Moumita Sinha, Doo Soon Kim
Many users communicate with chatbots and AI assistants in order to help them with various tasks.
no code implementations • 18 May 2020 • Sean MacAvaney, Franck Dernoncourt, Walter Chang, Nazli Goharian, Ophir Frieder
We present an elegant and effective approach for addressing limitations in existing multi-label classification models by incorporating interaction matching, a concept shown to be useful for ad-hoc search result ranking.
2 code implementations • ACL 2020 • Amirreza Shirani, Franck Dernoncourt, Jose Echevarria, Paul Asente, Nedim Lipka, Thamar Solorio
In this paper, we aim to learn associations between visual attributes of fonts and the verbal context of the texts they are typically applied to.
1 code implementation • NAACL 2021 • Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Joongbo Shin, Kyomin Jung
To evaluate our metric, we create high-quality human judgments of correctness on two GenQA datasets.
no code implementations • 1 Apr 2020 • Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Kyomin Jung
Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog.
no code implementations • LREC 2020 • Edward T. Moseley, Joy T. Wu, Jonathan Welt, John Foote, Patrick D. Tyler, David W. Grant, Eric T. Carlson, Sebastian Gehrmann, Franck Dernoncourt, Leo Anthony Celi
In this paper, we introduce a dataset for patient phenotyping, a task that is defined as the identification of whether a patient has a given medical condition (also referred to as clinical indication or phenotype) based on their patient note.
2 code implementations • LREC 2020 • Xiaolei Huang, Linzi Xing, Franck Dernoncourt, Michael J. Paul
Existing research on fairness evaluation of document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes.
no code implementations • 13 Feb 2020 • Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen
The existing event classification (EC) work primarily focuseson the traditional supervised learning setting in which models are unableto extract event mentions of new/unseen event types.
1 code implementation • EMNLP 2020 • Kang Min Yoo, Hanbit Lee, Franck Dernoncourt, Trung Bui, Walter Chang, Sang-goo Lee
Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks.
2 code implementations • LREC 2020 • Anthony Colas, Seokhwan Kim, Franck Dernoncourt, Siddhesh Gupte, Daisy Zhe Wang, Doo Soon Kim
The results indicate that the task is challenging and call for the investigation of new algorithms.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • Khalil Mrini, Franck Dernoncourt, Quan Tran, Trung Bui, Walter Chang, Ndapa Nakashole
Finally, we find that the Label Attention heads learn relations between syntactic categories and show pathways to analyze errors.
Ranked #1 on Dependency Parsing on Penn Treebank
no code implementations • WS 2020 • Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen
To address this issue, in this paper, we propose a novel method to incorporate the contextual information in two different levels, i. e., representation level and task-specific (i. e., label) level.
Ranked #5 on Intent Detection on SNIPS
1 code implementation • 5 Nov 2019 • Amir Pouran Ben Veyseh, Franck Dernoncourt, Dejing Dou, Thien Huu Nguyen
In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies.
no code implementations • WS 2019 • Tuan Ngo Nguyen, Franck Dernoncourt, Thien Huu Nguyen
Deep learning models have achieved state-of-the-art performances on many relation extraction datasets.
no code implementations • WS 2019 • Nabah Rizvi, Sebastian Gehrmann, Franck Dernoncourt
We present Margin Call, a web-based text viewer that automatically generates short summaries for each paragraph of the text and displays the summaries in the margin of the text next to the corresponding paragraph.
no code implementations • WS 2019 • Logan Lebanoff, John Muchovej, Franck Dernoncourt, Doo Soon Kim, Seokhwan Kim, Walter Chang, Fei Liu
While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences.
1 code implementation • LREC 2020 • Seunghyun Yoon, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Kyomin Jung
In this study, we propose a novel graph neural network called propagate-selector (PS), which propagates information over sentences to understand information that cannot be inferred when considering sentences in isolation.
no code implementations • 8 Aug 2019 • Subhadeep Dey, Petr Motlicek, Trung Bui, Franck Dernoncourt
In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • WS 2019 • Sasha Spala, Nicholas A. Miller, Yiming Yang, Franck Dernoncourt, Carl Dockhorn
Definition extraction has been a popular topic in NLP research for well more than a decade, but has been historically limited to well-defined, structured, and narrow conditions.
1 code implementation • ACL 2019 • Amirreza Shirani, Franck Dernoncourt, Paul Asente, Nedim Lipka, Seokhwan Kim, Jose Echevarria, Thamar Solorio
In visual communication, text emphasis is used to increase the comprehension of written text to convey the author{'}s intent.
1 code implementation • ACL 2019 • Hao Tan, Franck Dernoncourt, Zhe Lin, Trung Bui, Mohit Bansal
To push forward the research in this direction, we first introduce a new language-guided image editing dataset that contains a large number of real image pairs with corresponding editing instructions.
3 code implementations • ACL 2019 • Logan Lebanoff, Kaiqiang Song, Franck Dernoncourt, Doo Soon Kim, Seokhwan Kim, Walter Chang, Fei Liu
There is thus a crucial gap between sentence selection and fusion to support summarizing by both compressing single sentences and fusing pairs.
no code implementations • 30 May 2019 • Seunghyun Yoon, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Kyomin Jung
In this paper, we propose a novel method for a sentence-level answer-selection task that is a fundamental problem in natural language processing.
Ranked #8 on Question Answering on TrecQA
no code implementations • NAACL 2019 • Sebastian Gehrmann, Steven Layne, Franck Dernoncourt
Titles of short sections within long documents support readers by guiding their focus towards relevant passages and by providing anchor-points that help to understand the progression of the document.
no code implementations • COLING 2018 • Sasha Spala, Franck Dernoncourt, Walter Chang, Carl Dockhorn
Automatically highlighting a text aims at identifying key portions that are the most important to a reader.
no code implementations • SEMEVAL 2018 • Di Jin, Franck Dernoncourt, Elena Sergeeva, Matthew McDermott, Geeticka Chauhan
SemEval 2018 Task 7 tasked participants to build a system to classify two entities within a sentence into one of the 6 possible relation types.
2 code implementations • NAACL 2018 • Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, Nazli Goharian
Neural abstractive summarization models have led to promising results in summarizing relatively short documents.
Ranked #4 on Unsupervised Extractive Summarization on Pubmed
10 code implementations • IJCNLP 2017 • Franck Dernoncourt, Ji Young Lee
First, the majority of datasets for sequential short-text classification (i. e., classification of short texts that appear in sequences) are small: we hope that releasing a new large dataset will help develop more accurate algorithms for this task.
no code implementations • LREC 2018 • Ji Young Lee, Franck Dernoncourt, Peter Szolovits
In particular, we demonstrate that transferring an ANN model trained on a large labeled dataset to another dataset with a limited number of labels improves upon the state-of-the-art results on two different datasets for patient note de-identification.
1 code implementation • EMNLP 2017 • Franck Dernoncourt, Ji Young Lee, Peter Szolovits
Named-entity recognition (NER) aims at identifying entities of interest in a text.
no code implementations • SEMEVAL 2017 • Ji Young Lee, Franck Dernoncourt, Peter Szolovits
Over 50 million scholarly articles have been published: they constitute a unique repository of knowledge.
no code implementations • 25 Mar 2017 • Sebastian Gehrmann, Franck Dernoncourt, Yeran Li, Eric T. Carlson, Joy T. Wu, Jonathan Welt, John Foote Jr., Edward T. Moseley, David W. Grant, Patrick D. Tyler, Leo Anthony Celi
We assess the performance of deep learning algorithms and compare them with classical NLP approaches.
5 code implementations • EACL 2017 • Franck Dernoncourt, Ji Young Lee, Peter Szolovits
Existing models based on artificial neural networks (ANNs) for sentence classification often do not incorporate the context in which sentences appear, and classify sentences individually.
no code implementations • WS 2016 • Ji Young Lee, Franck Dernoncourt, Ozlem Uzuner, Peter Szolovits
In this work, we explore a method to incorporate human-engineered features as well as features derived from EHRs to a neural-network-based de-identification system.
1 code implementation • 27 Sep 2016 • Franck Dernoncourt, Ji Young Lee
Therefore it is a useful technique for tuning ANN models to yield the best performances for natural language processing tasks.
1 code implementation • 11 Jul 2016 • Franck Dernoncourt
Word embeddings have been shown to be useful across state-of-the-art systems in many natural language processing tasks, ranging from question answering systems to dependency parsing.
1 code implementation • 10 Jun 2016 • Franck Dernoncourt, Ji Young Lee, Ozlem Uzuner, Peter Szolovits
It yields an F1-score of 97. 85 on the i2b2 2014 dataset, with a recall 97. 38 and a precision of 97. 32, and an F1-score of 99. 23 on the MIMIC de-identification dataset, with a recall 99. 25 and a precision of 99. 06.
no code implementations • 7 May 2016 • Franck Dernoncourt, Ji Young Lee, Trung H. Bui, Hung H. Bui
The Dialog State Tracking Challenge 4 (DSTC 4) proposes several pilot tasks.
no code implementations • 7 May 2016 • Franck Dernoncourt, Ji Young Lee, Trung H. Bui, Hung H. Bui
The Dialog State Tracking Challenge 4 (DSTC 4) differentiates itself from the previous three editions as follows: the number of slot-value pairs present in the ontology is much larger, no spoken language understanding output is given, and utterances are labeled at the subdialog level.
2 code implementations • NAACL 2016 • Ji Young Lee, Franck Dernoncourt
Recent approaches based on artificial neural networks (ANNs) have shown promising results for short-text classification.
Ranked #11 on Dialogue Act Classification on Switchboard corpus