Jung Jae Kim

Also published as: Jung-Jae Kim, Jung-jae Kim


2023

pdf bib
From Speculation Detection to Trustworthy Relational Tuples in Information Extraction
Kuicai Dong | Aixin Sun | Jung-jae Kim | Xiaoli Li
Findings of the Association for Computational Linguistics: EMNLP 2023

Speculation detection is an important NLP task to identify text factuality. However, the extracted speculative information (e.g., speculative polarity, cue, and scope) lacks structure and poses challenges for direct utilization in downstream tasks. Open Information Extraction (OIE), on the other hand, extracts structured tuples as facts, without examining the certainty of these tuples. Bridging this gap between speculation detection and information extraction becomes imperative to generate structured speculative information and trustworthy relational tuples. Existing studies on speculation detection are defined at sentence level; but even if a sentence is determined to be speculative, not all factual tuples extracted from it are speculative. In this paper, we propose to study speculations in OIE tuples and determine whether a tuple is speculative. We formally define the research problem of tuple-level speculation detection. We then conduct detailed analysis on the LSOIE dataset which provides labels for speculative tuples. Lastly, we propose a baseline model SpecTup for this new research task.

pdf bib
Semantists at ImageArg-2023: Exploring Cross-modal Contrastive and Ensemble Models for Multimodal Stance and Persuasiveness Classification
Kanagasabai Rajaraman | Hariram Veeramani | Saravanan Rajamanickam | Adam Maciej Westerski | Jung-Jae Kim
Proceedings of the 10th Workshop on Argument Mining

In this paper, we describe our system for ImageArg-2023 Shared Task that aims to identify an image’s stance towards a tweet and determine its persuasiveness score concerning a specific topic. In particular, the Shared Task proposes two subtasks viz. subtask (A) Multimodal Argument Stance (AS) Classification, and subtask (B) Multimodal Image Persuasiveness (IP) Classification, using a dataset composed of tweets (images and text) from controversial topics, namely gun control and abortion. For subtask A, we employ multiple transformer models using a text based approach to classify the argumentative stance of the tweet. For sub task B we adopted text based as well as multimodal learning methods to classify image persuasiveness of the tweet. Surprisingly, the text-based approach of the tweet overall performed better than the multimodal approaches considered. In summary, our best system achieved a F1 score of 0.85 for sub task (A) and 0.50 for subtask (B), and ranked 2nd in subtask (A) and 4th in subtask (B), among all teams submissions.

pdf bib
Open Information Extraction via Chunks
Kuicai Dong | Aixin Sun | Jung-jae Kim | Xiaoli Li
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Open Information Extraction (OIE) aims to extract relational tuples from open-domain sentences. Existing OIE systems split a sentence into tokens and recognize token spans as tuple relations and arguments. We instead propose Sentence as Chunk sequence (SaC) and recognize chunk spans as tuple relations and arguments. We argue that SaC has better properties for OIE than sentence as token sequence, and evaluate four choices of chunks (i.e., CoNLL chunks, OIA simple phrases, noun phrases, and spans from SpanOIE). Also, we propose a simple end-to-end BERT-based model, Chunk-OIE, for sentence chunking and tuple extraction on top of SaC. Chunk-OIE achieves state-of-the-art results on multiple OIE datasets, showing that SaC benefits the OIE task.

pdf bib
Speech-Aware Multi-Domain Dialogue State Generation with ASR Error Correction Modules
Ridong Jiang | Wei Shi | Bin Wang | Chen Zhang | Yan Zhang | Chunlei Pan | Jung Jae Kim | Haizhou Li
Proceedings of The Eleventh Dialog System Technology Challenge

Prior research on dialogue state tracking (DST) is mostly based on written dialogue corpora. For spoken dialogues, the DST model trained on the written text should use the results (or hypothesis) of automatic speech recognition (ASR) as input. But ASR hypothesis often includes errors, which leads to significant performance drop for spoken dialogue state tracking. We address the issue by developing the following ASR error correction modules. First, we train a model to convert ASR hypothesis to ground truth user utterance, which can fix frequent patterns of errors. The model takes ASR hypotheses of two ASR models as input and fine-tuned in two stages. The corrected hypothesis is fed into a large scale pre-trained encoder-decoder model (T5) for DST training and inference. Second, if an output slot value from the encoder-decoder model is a name, we compare it with names in a dictionary crawled from Web sites and, if feasible, replace with the crawled name of the shortest edit distance. Third, we fix errors of temporal expressions in ASR hypothesis by using hand-crafted rules. Experiment results on the DSTC 11 speech-aware dataset, which is built on the popular MultiWOZ task (version 2.1), show that our proposed method can effectively mitigate the performance drop when moving from written text to spoken conversations.

2022

pdf bib
taochen at SemEval-2022 Task 5: Multimodal Multitask Learning and Ensemble Learning
Chen Tao | Jung-jae Kim
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

We present a multi-modal deep learning system for the Multimedia Automatic Misogyny Identification (MAMI) challenge, a SemEval task of identifying and classifying misogynistic messages in online memes. We adapt multi-task learning for the multimodal subtasks of the MAMI challenge to transfer knowledge among the correlated subtasks. We also leverage on ensemble learning for synergistic integration of models individually trained for the subtasks. We finally discuss about errors of the system to provide useful insights for future work.

pdf bib
Syntactic Multi-view Learning for Open Information Extraction
Kuicai Dong | Aixin Sun | Jung-Jae Kim | Xiaoli Li
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Open Information Extraction (OpenIE) aims to extract relational tuples from open-domain sentences. Traditional rule-based or statistical models were developed based on syntactic structure of sentence, identified by syntactic parsers. However, previous neural OpenIE models under-explored the useful syntactic information. In this paper, we model both constituency and dependency trees into word-level graphs, and enable neural OpenIE to learn from the syntactic structures. To better fuse heterogeneous information from the two graphs, we adopt multi-view learning to capture multiple relationships from them. Finally, the finetuned constituency and dependency representations are aggregated with sentential semantic representations for tuple generation. Experiments show that both constituency and dependency information, and the multi-view learning are effective.

2021

pdf bib
DocOIE: A Document-level Context-Aware Dataset for OpenIE
Kuicai Dong | Zhao Yilin | Aixin Sun | Jung-Jae Kim | Xiaoli Li
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Analyzing Code Embeddings for Coding Clinical Narratives
Wei Shi | Jiewen Wu | Xiwen Yang | Nancy Chen | Ivan Ho Mien | Jung-Jae Kim | Pavitra Krishnaswamy
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generation
Xin Huang | Jung-Jae Kim | Bowei Zou
Findings of the Association for Computational Linguistics: EMNLP 2021

Complex question answering over knowledge base remains as a challenging task because it involves reasoning over multiple pieces of information, including intermediate entities/relations and other constraints. Previous methods simplify the SPARQL query of a question into such forms as a list or a graph, missing such constraints as “filter” and “order_by”, and present models specialized for generating those simplified forms from a given question. We instead introduce a novel approach that directly generates an executable SPARQL query without simplification, addressing the issue of generating unseen entities. We adapt large scale pre-trained encoder-decoder models and show that our method significantly outperforms the previous methods and also that our method has higher interpretability and computational efficiency than the previous methods.

2015

pdf bib
Incorporating Trustiness and Collective Synonym/Contrastive Evidence into Taxonomy Construction
Anh Tuan Luu | Jung-jae Kim | See Kiong Ng
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

2014

pdf bib
Taxonomy Construction Using Syntactic Contextual Evidence
Anh Tuan Luu | Jung-jae Kim | See Kiong Ng
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Parse Ranking with Semantic Dependencies and WordNet
Xiaocheng Yin | Jung-Jae Kim | Zinaida Pozen | Francis Bond
Proceedings of the Seventh Global Wordnet Conference

2013

pdf bib
Proceedings of the BioNLP Shared Task 2013 Workshop
Claire Nédellec | Robert Bossy | Jin-Dong Kim | Jung-jae Kim | Tomoko Ohta | Sampo Pyysalo | Pierre Zweigenbaum
Proceedings of the BioNLP Shared Task 2013 Workshop

pdf bib
Overview of BioNLP Shared Task 2013
Claire Nédellec | Robert Bossy | Jin-Dong Kim | Jung-jae Kim | Tomoko Ohta | Sampo Pyysalo | Pierre Zweigenbaum
Proceedings of the BioNLP Shared Task 2013 Workshop

pdf bib
GRO Task: Populating the Gene Regulation Ontology with events and relations
Jung-jae Kim | Xu Han | Vivian Lee | Dietrich Rebholz-Schuhmann
Proceedings of the BioNLP Shared Task 2013 Workshop

2010

pdf bib
A Statistical NLP Approach for Feature and Sentiment Identification from Chinese Reviews
Zhen Hai | Kuiyu Chang | Qinbao Song | Jung-jae Kim
CIPS-SIGHAN Joint Conference on Chinese Language Processing

2009

pdf bib
How Feasible and Robust is the Automatic Extraction of Gene Regulation Events? A Cross-Method Evaluation under Lab and Real-Life Conditions
Udo Hahn | Katrin Tomanek | Ekaterina Buyko | Jung-jae Kim | Dietrich Rebholz-Schuhmann
Proceedings of the BioNLP 2009 Workshop

2004

pdf bib
BioAR: Anaphora Resolution for Relating Protein Names to Proteome Database Entries
Jung-Jae Kim | Jong C. Park
Proceedings of the Conference on Reference Resolution and Its Applications

2000

pdf bib
Phrase-Pattern-based Korean to English Machine Translation using Two Level Translation Pattern Selection
Jung-jae Kim | Key-Sun Choi | Young-Soog Chae
Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics