no code implementations • LREC 2012 • Xuansong Li, Stephanie Strassel, Heng Ji, Kira Griffitt, Joe Ellis
To advance information extraction and question answering technologies toward a more realistic path, the U. S. NIST (National Institute of Standards and Technology) initiated the KBP (Knowledge Base Population) task as one of the TAC (Text Analysis Conference) evaluation tracks.
no code implementations • LREC 2014 • Hai-Bo Li, Masato Hagiwara, Qi Li, Heng Ji
As long as (2) is ensured, the performance of word segmentation does not have appreciable impact on Chinese and Japanese name tagging.
no code implementations • 28 Apr 2015 • Hongzhao Huang, Larry Heck, Heng Ji
Entity Disambiguation aims to link mentions of ambiguous entities to a knowledge base (e. g., Wikipedia).
no code implementations • IJCNLP 2015 • Yang Liu, Furu Wei, Sujian Li, Heng Ji, Ming Zhou, Houfeng Wang
Previous research on relation classification has verified the effectiveness of using dependency shortest paths or subtrees.
Ranked #5 on Relation Classification on SemEval 2010 Task 8
3 code implementations • 17 Feb 2016 • Xiang Ren, Wenqi He, Meng Qu, Clare R. Voss, Heng Ji, Jiawei Han
Current systems of fine-grained entity typing use distant supervision in conjunction with existing knowledge bases to assign categories (type labels) to entity mentions.
no code implementations • 10 Mar 2016 • Lifu Huang, Jonathan May, Xiaoman Pan, Heng Ji
Recent research has shown great progress on fine-grained entity typing.
no code implementations • NAACL 2016 • Di Lu, Clare Voss, Fangbo Tao, Xiang Ren, Rachel Guan, Rostyslav Korolov, Tongtao Zhang, Dongang Wang, Hongzhi Li, Taylor Cassidy, Heng Ji, Shih-Fu Chang, Jiawei Han, William Wallace, James Hendler, Mei Si, Lance Kaplan
no code implementations • 27 Sep 2016 • Tao Ge, Qing Dou, Xiaoman Pan, Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Ming Zhou
We introduce a novel Burst Information Network (BINet) representation that can display the most important information and illustrate the connections among bursty entities, events and keywords in the corpus.
2 code implementations • 27 Oct 2016 • Xiang Ren, Zeqiu Wu, Wenqi He, Meng Qu, Clare R. Voss, Heng Ji, Tarek F. Abdelzaher, Jiawei Han
We propose a novel domain-independent framework, called CoType, that runs a data-driven text segmentation algorithm to extract entity mentions, and jointly embeds entity mentions, relation mentions, text features and type labels into two low-dimensional spaces (for entity and relation mentions respectively), where, in each space, objects whose types are close will also have similar representations.
Ranked #11 on Relation Extraction on NYT11-HRL
no code implementations • WS 2016 • Yu Hong, Liang Yao, Mengyi Liu, Tongtao Zhang, Wenxuan Zhou, Jianmin Yao, Heng Ji
We present a novel method of comparable corpora construction.
no code implementations • COLING 2016 • Dongxu Zhang, Boliang Zhang, Xiaoman Pan, Xiaocheng Feng, Heng Ji, Weiran Xu
Instead of directly relying on word alignment results, this framework combines advantages of rule-based methods and deep learning methods by implementing two steps: First, generates a high-confidence entity annotation set on IL side with strict searching methods; Second, uses this high-confidence set to weakly supervise the model training.
no code implementations • ACL 2017 • Ying Lin, Chin-Yew Lin, Heng Ji
Traditional Entity Linking (EL) technologies rely on rich structures and properties in the target knowledge base (KB).
no code implementations • ACL 2017 • Yixin Cao, Lifu Huang, Heng Ji, Xu Chen, Juanzi Li
Integrating text and knowledge into a unified semantic space has attracted significant research interests recently.
no code implementations • ACL 2017 • Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Nothman, Kevin Knight, Heng Ji
The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia.
1 code implementation • EMNLP 2017 • Liyuan Liu, Xiang Ren, Qi Zhu, Shi Zhi, Huan Gui, Heng Ji, Jiawei Han
These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance.
no code implementations • EMNLP 2017 • Lifu Huang, Avirup Sil, Heng Ji, Radu Florian
Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:cities\_of\_residence) for a given entity from a large collection of source documents.
1 code implementation • ACL 2018 • Lifu Huang, Heng Ji, Kyunghyun Cho, Clare R. Voss
Most previous event extraction studies have relied heavily on features derived from annotated event mentions, thus cannot be applied to new event types without annotation effort.
no code implementations • EMNLP 2017 • Min Yang, Jincheng Mei, Heng Ji, Wei Zhao, Zhou Zhao, Xiaojun Chen
We study the problem of identifying the topics and sentiments and tracking their shifts from social media texts in different geographical regions during emergencies and disasters.
no code implementations • 16 Sep 2017 • Ying Lin, Joe Hoover, Morteza Dehghani, Marlon Mooijman, Heng Ji
In this paper, we address the problem of detecting expressions of moral values in tweets using content analysis.
no code implementations • WS 2017 • Zhihao Zhou, Lifu Huang, Heng Ji
Learning phrase representations has been widely explored in many Natural Language Processing (NLP) tasks (e. g., Sentiment Analysis, Machine Translation) and has shown promising improvements.
no code implementations • IJCNLP 2017 • Dian Yu, Lifu Huang, Heng Ji
Previous open Relation Extraction (open RE) approaches mainly rely on linguistic patterns and constraints to extract important relational triples from large-scale corpora.
no code implementations • IJCNLP 2017 • Boliang Zhang, Di Lu, Xiaoman Pan, Ying Lin, Halidanmu Abudukelimu, Heng Ji, Kevin Knight
Current supervised name tagging approaches are inadequate for most low-resource languages due to the lack of annotated data and actionable linguistic knowledge.
no code implementations • WS 2015 • Yue Liu, Tao Ge, Kusum S. Mathews, Heng Ji, Deborah L. McGuinness
In the medical domain, identifying and expanding abbreviations in clinical texts is a vital task for both better human and machine understanding.
no code implementations • EMNLP 2018 • Di Lu, Spencer Whitehead, Lifu Huang, Heng Ji, Shih-Fu Chang
Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images.
no code implementations • EMNLP 2018 • Lifu Huang, Kyunghyun Cho, Boliang Zhang, Heng Ji, Kevin Knight
We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space to enable knowledge and resource transfer across languages.
no code implementations • 21 Apr 2018 • Tongtao Zhang, Heng Ji
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN).
2 code implementations • ACL 2018 • Qingyun Wang, Zhi-Hao Zhou, Lifu Huang, Spencer Whitehead, Boliang Zhang, Heng Ji, Kevin Knight
We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract.
Ranked #1 on Paper generation on ACL Title and Abstract Dataset
1 code implementation • WS 2018 • Zhiying Jiang, Boliang Zhang, Lifu Huang, Heng Ji
We present a neural recommendation model for Chengyu, which is a special type of Chinese idiom.
no code implementations • NAACL 2018 • Boliang Zhang, Ying Lin, Xiaoman Pan, Di Lu, Jonathan May, Kevin Knight, Heng Ji
We demonstrate ELISA-EDL, a state-of-the-art re-trainable system to extract entity mentions from low-resource languages, link them to external English knowledge bases, and visualize locations related to disaster topics on a world heatmap.
no code implementations • ACL 2018 • Ying Lin, Cash Costello, Boliang Zhang, Di Lu, Heng Ji, James Mayfield, Paul McNamee
We demonstrate two annotation platforms that allow an English speaker to annotate names for any language without knowing the language.
no code implementations • ACL 2018 • Avi Sil, Heng Ji, Dan Roth, Silviu-Petru Cucerzan
We will then proceed to Cross-lingual EL and discuss methods that work across languages.
no code implementations • ACL 2018 • Di Lu, Leonardo Neves, Vitor Carvalho, Ning Zhang, Heng Ji
Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram.
1 code implementation • ACL 2018 • Ying Lin, Shengqi Yang, Veselin Stoyanov, Heng Ji
We propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling.
3 code implementations • 4 Jul 2018 • Yue Liu, Tongtao Zhang, Zhicheng Liang, Heng Ji, Deborah L. McGuinness
Inspired by recent successes in neural machine translation, we treat the triples within a given knowledge graph as an independent graph language and propose an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings.
no code implementations • COLING 2018 • Heng Ji, Kevin Knight
People often create obfuscated language for online communication to avoid Internet censorship, share sensitive information, express strong sentiment or emotion, plan for secret actions, trade illegal products, or simply hold interesting conversations.
1 code implementation • WS 2018 • Qingyun Wang, Xiaoman Pan, Lifu Huang, Boliang Zhang, Zhiying Jiang, Heng Ji, Kevin Knight
We aim to automatically generate natural language descriptions about an input structured knowledge base (KB).
no code implementations • EMNLP 2018 • Ge Shi, Chong Feng, Lifu Huang, Boliang Zhang, Heng Ji, Lejian Liao, He-Yan Huang
Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions.
no code implementations • EMNLP 2018 • Spencer Whitehead, Heng Ji, Mohit Bansal, Shih-Fu Chang, Clare Voss
We develop an approach that uses video meta-data to retrieve topically related news documents for a video and extracts the events and named entities from these documents.
no code implementations • EMNLP 2018 • Tao Ge, Qing Dou, Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Furu Wei, Ming Zhou
This paper proposes to study fine-grained coordinated cross-lingual text stream alignment through a novel information network decipherment paradigm.
no code implementations • EMNLP 2018 • Ni Zhang, Tongtao Zhang, Indrani Bhattacharya, Heng Ji, Rich Radke
Group discussions are usually aimed at sharing opinions, reaching consensus and making good decisions based on group knowledge.
1 code implementation • WS 2019 • Xiaoman Pan, Kai Sun, Dian Yu, Jianshu Chen, Heng Ji, Claire Cardie, Dong Yu
We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus.
1 code implementation • NAACL 2019 • Ronald Cardenas, Ying Lin, Heng Ji, Jonathan May
We also show extrinsically that incorporating our POS tagger into a name tagger leads to state-of-the-art tagging performance in Sinhalese and Kinyarwanda, two languages with nearly no labeled POS data available.
2 code implementations • ACL 2019 • Qingyun Wang, Lifu Huang, Zhiying Jiang, Kevin Knight, Heng Ji, Mohit Bansal, Yi Luan
We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with predicted related entities to generate a paper abstract, from the abstract to generate conclusion and future work, and finally from future work to generate a title for a follow-on paper.
no code implementations • WS 2019 • Kevin Blissett, Heng Ji
Clustering unlinkable entity mentions across documents in multiple languages (cross-lingual NIL Clustering) is an important task as part of Entity Discovery and Linking (EDL).
no code implementations • NAACL 2019 • Manling Li, Ying Lin, Joseph Hoover, Spencer Whitehead, Clare Voss, Morteza Dehghani, Heng Ji
This paper demonstrates a state-of-the-art end-to-end multilingual (English, Russian, and Ukrainian) knowledge extraction system that can perform entity discovery and linking, relation extraction, event extraction, and coreference.
no code implementations • NAACL 2019 • Lifu Huang, Heng Ji, Jonathan May
We focus on improving name tagging for low-resource languages using annotations from related languages.
no code implementations • NAACL 2019 • Diya Li, Lifu Huang, Heng Ji, Jiawei Han
Event extraction for the biomedical domain is more challenging than that in the general news domain since it requires broader acquisition of domain-specific knowledge and deeper understanding of complex contexts.
no code implementations • ACL 2019 • Manling Li, Lingyu Zhang, Heng Ji, Richard J. Radke
Transcripts of natural, multi-person meetings differ significantly from documents like news articles, which can make Natural Language Generation models for generating summaries unfocused.
1 code implementation • ACL 2019 • Ying Lin, Liyuan Liu, Heng Ji, Dong Yu, Jiawei Han
We design a set of word frequency-based reliability signals to indicate the quality of each word embedding.
1 code implementation • 14 Aug 2019 • Liyuan Liu, Zihan Wang, Jingbo Shang, Dandong Yin, Heng Ji, Xiang Ren, Shaowen Wang, Jiawei Han
Our model neither requires the conversion from character sequences to word sequences, nor assumes tokenizer can correctly detect all word boundaries.
1 code implementation • IJCNLP 2019 • Yixin Cao, Zikun Hu, Tat-Seng Chua, Zhiyuan Liu, Heng Ji
Name tagging in low-resource languages or domains suffers from inadequate training data.
no code implementations • IJCNLP 2019 • Ananya Subburathinam, Di Lu, Heng Ji, Jonathan May, Shih-Fu Chang, Avirup Sil, Clare Voss
The identification of complex semantic structures such as events and entity relations, already a challenging Information Extraction task, is doubly difficult from sources written in under-resourced and under-annotated languages.
no code implementations • WS 2019 • Xiaoman Pan, Thamme Gowda, Heng Ji, Jonathan May, Scott Miller
Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking.
no code implementations • WS 2019 • Kevin Blissett, Heng Ji
In this paper we address a challenging cross-lingual name retrieval task.
no code implementations • IJCNLP 2019 • Ying Lin, Heng Ji
In addition, we propose a two-step mention-aware attention mechanism to enable the model to focus on important words in mentions and contexts.
no code implementations • WS 2019 • Diya Li, Heng Ji
In this paper we tackle two unique challenges in biomedical relation extraction.
1 code implementation • ECCV 2020 • Dídac Surís, Dave Epstein, Heng Ji, Shih-Fu Chang, Carl Vondrick
Language acquisition is the process of learning words from the surrounding scene.
no code implementations • 11 Feb 2020 • Tongtao Zhang, Heng Ji, Shih-Fu Chang, Marjorie Freedman
In this paper, we address a practical scenario where training data is released in a sequence of small-scale batches and annotation in earlier phases has lower quality than the later counterparts.
no code implementations • LREC 2020 • Di Lu, Ananya Subburathinam, Heng Ji, Jonathan May, Shih-Fu Chang, Avi Sil, Clare Voss
Most of the current cross-lingual transfer learning methods for Information Extraction (IE) have been only applied to name tagging.
no code implementations • ACL 2020 • Manling Li, Alireza Zareian, Qi Zeng, Spencer Whitehead, Di Lu, Heng Ji, Shih-Fu Chang
We introduce a new task, MultiMedia Event Extraction (M2E2), which aims to extract events and their arguments from multimedia documents.
no code implementations • ACL 2020 • Manling Li, Alireza Zareian, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen, Bo Wu, Heng Ji, Shih-Fu Chang, Clare Voss, Daniel Napierski, Marjorie Freedman
We present the first comprehensive, open source multimedia knowledge extraction system that takes a massive stream of unstructured, heterogeneous multimedia data from various sources and languages as input, and creates a coherent, structured knowledge base, indexing entities, relations, and events, following a rich, fine-grained ontology.
no code implementations • ACL 2020 • Ying Lin, Heng Ji, Fei Huang, Lingfei Wu
OneIE performs end-to-end IE in four stages: (1) Encoding a given sentence as contextualized word representations; (2) Identifying entity mentions and event triggers as nodes; (3) Computing label scores for all nodes and their pairwise links using local classifiers; (4) Searching for the globally optimal graph with a beam decoder.
no code implementations • NAACL 2021 • Qingyun Wang, Manling Li, Xuan Wang, Nikolaus Parulian, Guangxing Han, Jiawei Ma, Jingxuan Tu, Ying Lin, Haoran Zhang, Weili Liu, Aabhas Chauhan, Yingjun Guan, Bangzheng Li, Ruisong Li, Xiangchen Song, Yi R. Fung, Heng Ji, Jiawei Han, Shih-Fu Chang, James Pustejovsky, Jasmine Rah, David Liem, Ahmed Elsayed, Martha Palmer, Clare Voss, Cynthia Schneider, Boyan Onyshkevych
To combat COVID-19, both clinicians and scientists need to digest vast amounts of relevant biomedical knowledge in scientific literature to understand the disease mechanism and related biological functions.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan, Heng Ji, Daojian Zeng, Fei Cheng, Daisuke Kawahara, Sadao Kurohashi
We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets.
1 code implementation • EMNLP 2020 • Jiaming Shen, Heng Ji, Jiawei Han
Linguistic steganography studies how to hide secret messages in natural language cover texts.
3 code implementations • 9 Oct 2020 • Wenhao Yu, Chenguang Zhu, Zaitang Li, Zhiting Hu, Qingyun Wang, Heng Ji, Meng Jiang
To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models.
1 code implementation • INLG (ACL) 2020 • Qingyun Wang, Qi Zeng, Lifu Huang, Kevin Knight, Heng Ji, Nazneen Fatema Rajani
To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison.
1 code implementation • EMNLP 2020 • Jiaxin Huang, Yu Meng, Fang Guo, Heng Ji, Jiawei Han
Aspect-based sentiment analysis of review texts is of great value for understanding user feedback in a fine-grained manner.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
2 code implementations • EMNLP 2020 • Yu Meng, Yunyi Zhang, Jiaxin Huang, Chenyan Xiong, Heng Ji, Chao Zhang, Jiawei Han
In this paper, we explore the potential of only using the label name of each class to train classification models on unlabeled data, without using any labeled documents.
no code implementations • CONLL 2018 • Boliang Zhang, Spencer Whitehead, Lifu Huang, Heng Ji
Many name tagging approaches use local contextual information with much success, but fail when the local context is ambiguous or limited.
2 code implementations • 24 Oct 2020 • Yuning Mao, Xiang Ren, Heng Ji, Jiawei Han
Despite significant progress, state-of-the-art abstractive summarization methods are still prone to hallucinate content inconsistent with the source document.
no code implementations • 6 Nov 2020 • Lihui Liu, Boxin Du, Heng Ji, Hanghang Tong
In detail, we develop KompaRe, the first of its kind prototype system that provides comparative reasoning capability over large knowledge graphs.
1 code implementation • 9 Nov 2020 • Xiaodan Hu, Pengfei Yu, Kevin Knight, Heng Ji, Bo Li, Honghui Shi
Experiments show that our approach can accurately illustrate 78% textual attributes, which also help MUSE capture the subject in a more creative and expressive way.
1 code implementation • 26 Nov 2020 • Spencer Whitehead, Hui Wu, Yi Ren Fung, Heng Ji, Rogerio Feris, Kate Saenko
Existing Visual Question Answering (VQA) models are often fragile and sensitive to input variations.
1 code implementation • ACL 2021 • Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie zhou
Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks.
no code implementations • 25 Jan 2021 • Thamar Solorio, Mahsa Shafaei, Christos Smailis, Mona Diab, Theodore Giannakopoulos, Heng Ji, Yang Liu, Rada Mihalcea, Smaranda Muresan, Ioannis Kakadiaris
This white paper presents a summary of the discussions regarding critical considerations to develop an extensive repository of online videos annotated with labels indicating questionable content.
no code implementations • 23 Feb 2021 • Huajie Shao, Jun Wang, Haohong Lin, Xuezhou Zhang, Aston Zhang, Heng Ji, Tarek Abdelzaher
The algorithm is injected into a Conditional Variational Autoencoder (CVAE), allowing \textit{Apex} to control both (i) the order of keywords in the generated sentences (conditioned on the input keywords and their order), and (ii) the trade-off between diversity and accuracy.
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.
1 code implementation • NAACL 2021 • Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, Lu Wang
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization.
no code implementations • 6 Apr 2021 • Ying Lin, Han Wang, Jiangning Chen, Tong Wang, Yue Liu, Heng Ji, Yang Liu, Premkumar Natarajan
For example, with "add milk to my cart", a customer may refer to a certain organic product, while some customers may want to re-order products they regularly purchase.
1 code implementation • EMNLP 2021 • Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han, Clare Voss
We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations.
1 code implementation • NAACL 2021 • Sha Li, Heng Ji, Jiawei Han
On the task of argument extraction, we achieve an absolute gain of 7. 6% F1 and 5. 7% F1 over the next best model on the RAMS and WikiEvents datasets respectively.
Document-level Event Extraction Event Argument Extraction +2
no code implementations • 15 Apr 2021 • Revanth Gangi Reddy, Vikas Yadav, Md Arafat Sultan, Martin Franz, Vittorio Castelli, Heng Ji, Avirup Sil
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems.
no code implementations • ACL 2021 • Haoyang Wen, Anthony Ferritto, Heng Ji, Radu Florian, Avirup Sil
Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, thereby making inference computationally inefficient for production use.
2 code implementations • Findings (ACL) 2021 • Chi Han, Mingxuan Wang, Heng Ji, Lei LI
By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art.
1 code implementation • ACL 2021 • Qingyun Wang, Semih Yavuz, Victoria Lin, Heng Ji, Nazneen Rajani
Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders.
Ranked #3 on Data-to-Text Generation on WebNLG (using extra training data)
1 code implementation • NeurIPS 2021 • Yifan Chen, Qi Zeng, Heng Ji, Yun Yang
Transformers are expensive to train due to the quadratic time and space complexity in the self-attention mechanism.
1 code implementation • ACL 2021 • Tuan Lai, Heng Ji, ChengXiang Zhai, Quan Hung Tran
It then uses an entity linker to form a knowledge graph containing relevant background knowledge for the the entity mentions in the text.
1 code implementation • NAACL 2021 • Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, D{\'\i}dac Sur{\'\i}s, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji
We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities (speech, text, image and video).
no code implementations • NAACL 2021 • Lingfei Wu, Yu Chen, Heng Ji, Yunyao Li
Due to its great power in modeling non-Euclidean data like graphs or manifolds, deep learning on graph techniques (i. e., Graph Neural Networks (GNNs)) have opened a new door to solving challenging graph-related NLP problems.
1 code implementation • NAACL 2021 • Zixuan Zhang, Heng Ji
The tasks of Rich Semantic Parsing, such as Abstract Meaning Representation (AMR), share similar goals with Information Extraction (IE) to convert natural language texts into structured semantic representations.
1 code implementation • NAACL 2021 • Haoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han, Avi Sil, Hanghang Tong, Dan Roth
Grounding events into a precise timeline is important for natural language understanding but has received limited attention in recent work.
1 code implementation • Findings (ACL) 2021 • Liliang Ren, Chenkai Sun, Heng Ji, Julia Hockenmaier
Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts.
Ranked #1 on Relation Extraction on ACE 2005 (Sentence Encoder metric)
1 code implementation • CVPR 2021 • Spencer Whitehead, Hui Wu, Heng Ji, Rogerio Feris, Kate Saenko
Generalization to out-of-distribution data has been a problem for Visual Question Answering (VQA) models.
no code implementations • ACL 2021 • Zixuan Zhang, Nikolaus Parulian, Heng Ji, Ahmed Elsayed, Skatje Myers, Martha Palmer
In this paper, we propose a novel biomedical Information Extraction (IE) model to tackle these two challenges and extract scientific entities and events from English research papers.
no code implementations • ACL 2021 • Muhao Chen, Hongming Zhang, Qiang Ning, Manling Li, Heng Ji, Kathleen McKeown, Dan Roth
This tutorial targets researchers and practitioners who are interested in AI technologies that help machines understand natural language text, particularly real-world events described in the text.
no code implementations • ACL 2021 • Yi Fung, Christopher Thomas, Revanth Gangi Reddy, Sandeep Polisetty, Heng Ji, Shih-Fu Chang, Kathleen McKeown, Mohit Bansal, Avi Sil
To defend against machine-generated fake news, an effective mechanism is urgently needed.
no code implementations • ACL 2021 • Samuel Kriman, Heng Ji
The tasks performed by this system are entity and event identification, typing, and coreference resolution.
no code implementations • 23 Aug 2021 • Tuan Manh Lai, Yang Zhang, Evelina Bakhturina, Boris Ginsburg, Heng Ji
In addition, we also create a cleaned dataset from the Spoken Wikipedia Corpora for German and report the performance of our systems on the dataset.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
no code implementations • 29 Aug 2021 • Chenkai Sun, Weijiang Li, Jinfeng Xiao, Nikolaus Nova Parulian, ChengXiang Zhai, Heng Ji
Automated knowledge discovery from trending chemical literature is essential for more efficient biomedical research.
no code implementations • 3 Sep 2021 • Daniel Campos, Heng Ji
A large portion of chemistry literature focuses on new molecules and reactions between molecules.
1 code implementation • Findings (EMNLP) 2021 • Tuan Lai, Heng Ji, ChengXiang Zhai
Biomedical entity linking is the task of linking entity mentions in a biomedical document to referent entities in a knowledge base.
1 code implementation • EMNLP 2021 • Jiaming Shen, Yunyi Zhang, Heng Ji, Jiawei Han
As events of the same type could be expressed in multiple ways, we propose to represent each event type as a cluster of <predicate sense, object head> pairs.
1 code implementation • EMNLP 2021 • Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji, Jiawei Han
We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base.
1 code implementation • ICLR 2022 • Hongwei Wang, Weijiang Li, Xiaomeng Jin, Kyunghyun Cho, Heng Ji, Jiawei Han, Martin D. Burke
Molecule representation learning (MRL) methods aim to embed molecules into a real vector space.
no code implementations • Findings (EMNLP) 2021 • Brian Chen, Xudong Lin, Christopher Thomas, Manling Li, Shoya Yoshida, Lovish Chum, Heng Ji, Shih-Fu Chang
We introduce the new task of Video MultiMedia Event Extraction (Video M2E2) and propose two novel components to build the first system towards this task.
no code implementations • ICLR 2022 • Ruicheng Xian, Heng Ji, Han Zhao
Recent advances in neural modeling have produced deep multilingual language models capable of extracting cross-lingual knowledge from unparallel texts, as evidenced by their decent zero-shot transfer performance.
1 code implementation • NeurIPS 2021 • Yifan Chen, Qi Zeng, Heng Ji, Yun Yang
Transformers are expensive to train due to the quadratic time and space complexity in the self-attention mechanism.
1 code implementation • 5 Dec 2021 • Zhenhailong Wang, Heng Ji
State-of-the-art brain-to-text systems have achieved great success in decoding language directly from brain signals using neural networks.
1 code implementation • NAACL 2022 • Yifan Chen, Qi Zeng, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang
Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules.
2 code implementations • 16 Dec 2021 • Revanth Gangi Reddy, Sai Chetan, Zhenhailong Wang, Yi R. Fung, Kathryn Conger, Ahmed Elsayed, Martha Palmer, Preslav Nakov, Eduard Hovy, Kevin Small, Heng Ji
In this work, we present NewsClaims, a new benchmark for attribute-aware claim detection in the news domain.
2 code implementations • 20 Dec 2021 • Revanth Gangi Reddy, Xilin Rui, Manling Li, Xudong Lin, Haoyang Wen, Jaemin Cho, Lifu Huang, Mohit Bansal, Avirup Sil, Shih-Fu Chang, Alexander Schwing, Heng Ji
Specifically, the task involves multi-hop questions that require reasoning over image-caption pairs to identify the grounded visual object being referred to and then predicting a span from the news body text to answer the question.
1 code implementation • CVPR 2022 • Manling Li, Ruochen Xu, Shuohang Wang, Luowei Zhou, Xudong Lin, Chenguang Zhu, Michael Zeng, Heng Ji, Shih-Fu Chang
Vision-language (V+L) pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text.
no code implementations • 12 Feb 2022 • Carl Edwards, Heng Ji
In contrast, we present a novel approach to semi-supervised new event type induction using a masked contrastive loss, which learns similarities between event mentions by enforcing an attention mechanism over the data minibatch.
no code implementations • 15 Feb 2022 • Sha Li, Liyuan Liu, Yiqing Xie, Heng Ji, Jiawei Han
Our framework decomposes event detection into an identification task and a localization task.
1 code implementation • Findings (ACL) 2022 • Tuan Manh Lai, Heng Ji, ChengXiang Zhai
We use the profile to query the indexed search engine to retrieve candidate entities.
1 code implementation • 9 Mar 2022 • Yi R. Fung, Heng Ji
Online social networks such as Twitter and Weibo play an important role in how people stay informed and exchange reactions.
1 code implementation • MMMPIE (COLING) 2022 • Zhenhailong Wang, Hang Yu, Manling Li, Han Zhao, Heng Ji
While much literature has been devoted to exploring alternative optimization strategies, we identify another essential aspect towards effective few-shot transfer learning, task sampling, which is previously only be viewed as part of data pre-processing in MAML.
1 code implementation • 10 Mar 2022 • Kung-Hsiang Huang, Kathleen McKeown, Preslav Nakov, Yejin Choi, Heng Ji
Despite recent advances in detecting fake news generated by neural models, their results are not readily applicable to effective detection of human-written disinformation.
1 code implementation • 24 Apr 2022 • Revanth Gangi Reddy, Md Arafat Sultan, Martin Franz, Avirup Sil, Heng Ji
On two public IR benchmarks, we empirically show that the proposed method helps improve both the model's attention patterns and retrieval performance, including in zero-shot settings.
1 code implementation • 25 Apr 2022 • Carl Edwards, Tuan Lai, Kevin Ros, Garrett Honke, Kyunghyun Cho, Heng Ji
We present $\textbf{MolT5}$ $-$ a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings.
Ranked #4 on Text-based de novo Molecule Generation on ChEBI-20
1 code implementation • 22 May 2022 • Zhenhailong Wang, Manling Li, Ruochen Xu, Luowei Zhou, Jie Lei, Xudong Lin, Shuohang Wang, ZiYi Yang, Chenguang Zhu, Derek Hoiem, Shih-Fu Chang, Mohit Bansal, Heng Ji
The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction.
no code implementations • 23 May 2022 • Anish Saha, Amith Ananthram, Emily Allaway, Heng Ji, Kathleen McKeown
Practitioners from many disciplines (e. g., political science) use expert-crafted taxonomies to make sense of large, unlabeled corpora.
no code implementations • 23 May 2022 • Yubin Ge, Ziang Xiao, Jana Diesner, Heng Ji, Karrie Karahalios, Hari Sundaram
We constructed a new human-annotated dataset of human-written follow-up questions with dialogue history and labeled knowledge in the context of conversational surveys.
1 code implementation • 30 May 2022 • Qi Zeng, Qiusi Zhan, Heng Ji
Events are inter-related in documents.
1 code implementation • CVPR 2023 • Xudong Lin, Simran Tiwari, Shiyuan Huang, Manling Li, Mike Zheng Shou, Heng Ji, Shih-Fu Chang
We surprisingly find that discrete text tokens coupled with a pretrained contrastive text model yields the best performance, which can even outperform state-of-the-art on the iVQA and How2QA datasets without additional training on millions of video-text data.
Ranked #1 on Video Question Answering on iVQA
no code implementations • 6 Jun 2022 • Hongwei Wang, Zixuan Zhang, Sha Li, Jiawei Han, Yizhou Sun, Hanghang Tong, Joseph P. Olive, Heng Ji
Existing link prediction or graph completion methods have difficulty dealing with event graphs because they are usually designed for a single large graph such as a social network or a knowledge graph, rather than multiple small dynamic event graphs.
no code implementations • 15 Jun 2022 • Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging.
1 code implementation • 25 Aug 2022 • Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary, Heng Ji
Goal-oriented generative script learning aims to generate subsequent steps to reach a particular goal, which is an essential task to assist robots or humans in performing stereotypical activities.
1 code implementation • 31 Aug 2022 • Chenkai Sun, Tie XU, ChengXiang Zhai, Heng Ji
In this paper, we present Tetris, a new task of Goal-Oriented Script Completion.
1 code implementation • COLING 2022 • Kung-Hsiang Huang, ChengXiang Zhai, Heng Ji
Given the absence of cross-lingual information retrieval datasets with claim-like queries, we train the retriever with our proposed Cross-lingual Inverse Cloze Task (X-ICT), a self-supervised algorithm that creates training instances by translating the title of a passage.
Ranked #1 on Zero-shot Cross-lingual Fact-checking on X-Fact
Cross-lingual Fact-checking Cross-Lingual Information Retrieval +4
1 code implementation • ACL 2022 • Xinya Du, Sha Li, Heng Ji
Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document.
1 code implementation • 1 Oct 2022 • Zhenhailong Wang, Xiaoman Pan, Dian Yu, Dong Yu, Jianshu Chen, Heng Ji
Notably, our proposed $\text{Zemi}_\text{LARGE}$ outperforms T0-3B by 16% on all seven evaluation tasks while being 3. 9x smaller in model size.
no code implementations • 9 Oct 2022 • Feng Wang, Manling Li, Xudong Lin, Hairong Lv, Alexander G. Schwing, Heng Ji
Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations.
2 code implementations • 13 Oct 2022 • Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, PengFei Liu, Chenguang Zhu, Heng Ji, Jiawei Han
We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.
1 code implementation • 16 Oct 2022 • Yi R. Fung, Tuhin Chakraborty, Hao Guo, Owen Rambow, Smaranda Muresan, Heng Ji
Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions.
1 code implementation • 21 Oct 2022 • Ziqi Wang, Yuexin Wu, Frederick Liu, Daogao Liu, Le Hou, Hongkun Yu, Jing Li, Heng Ji
However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models).
1 code implementation • 22 Oct 2022 • Long Chen, Yulei Niu, Brian Chen, Xudong Lin, Guangxing Han, Christopher Thomas, Hammad Ayyubi, Heng Ji, Shih-Fu Chang
Specifically, given an article and a relevant video, WSAG aims to localize all ``groundable'' sentences to the video, and these sentences are possibly at different semantic scales.
1 code implementation • 23 Oct 2022 • Liliang Ren, Zixuan Zhang, Han Wang, Clare R. Voss, ChengXiang Zhai, Heng Ji
Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks.
Ranked #6 on Few-shot NER on Few-NERD (INTRA) (using extra training data)
1 code implementation • 23 Oct 2022 • Xingyao Wang, Sha Li, Heng Ji
As a case study, we formulate Event Argument Extraction (EAE) as converting text into event-argument structures that can be represented as a class object using code.
1 code implementation • 25 Oct 2022 • Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, Dawn Song
For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.
Ranked #5 on Link Prediction on UMLS
2 code implementations • 31 Oct 2022 • Yangyi Chen, Lifan Yuan, Ganqu Cui, Zhiyuan Liu, Heng Ji
We observe a consistent change in calibration performance across six factors.
no code implementations • 3 Nov 2022 • Guang Yang, Manling Li, Jiajie Zhang, Xudong Lin, Shih-Fu Chang, Heng Ji
Video event extraction aims to detect salient events from a video and identify the arguments for each event as well as their semantic roles.
1 code implementation • 3 Nov 2022 • Yizhu Jiao, Sha Li, Yiqing Xie, Ming Zhong, Heng Ji, Jiawei Han
Specifically, we formulate the role prediction problem as an in-filling task and construct prompts for a pre-trained language model to generate candidate roles.
1 code implementation • 7 Nov 2022 • Chi Han, Hengzhi Pei, Xinya Du, Heng Ji
To this end, we propose the framework CLORE (Classification by LOgical Reasoning on Explanations).
1 code implementation • 10 Nov 2022 • Ke Yang, Charles Yu, Yi Fung, Manling Li, Heng Ji
Despite this, relatively few efforts have been made to debias PLMs by prompt tuning with continuous prompts compared to its discrete counterpart.
1 code implementation • 14 Nov 2022 • Xinya Du, Heng Ji
We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction.
1 code implementation • 30 Nov 2022 • Sha Li, Heng Ji, Jiawei Han
To tackle this problem, we introduce the idea of type abstraction, where the model is prompted to generalize and name the type.
1 code implementation • 2 Dec 2022 • Revanth Gangi Reddy, Heba Elfardy, Hou Pong Chan, Kevin Small, Heng Ji
A primary objective of news articles is to establish the factual record for an event, frequently achieved by conveying both the details of the specified event (i. e., the 5 Ws; Who, What, Where, When and Why regarding the event) and how people reacted to it (i. e., reported statements).
no code implementations • 22 Jan 2023 • Tuan Manh Lai, Heng Ji
Leveraging the idea that the coreferential links naturally exist between anchor texts pointing to the same article, our method builds a sizeable distantly-supervised dataset for the target language that consists of tens of thousands of documents.
no code implementations • 25 Feb 2023 • Tianyi Zhang, Isaac Tham, Zhaoyi Hou, Jiaxuan Ren, Liyang Zhou, Hainiu Xu, Li Zhang, Lara J. Martin, Rotem Dror, Sha Li, Heng Ji, Martha Palmer, Susan Brown, Reece Suchocki, Chris Callison-Burch
Schema induction builds a graph representation explaining how events unfold in a scenario.
1 code implementation • 16 Mar 2023 • Qiusi Zhan, Sha Li, Kathryn Conger, Martha Palmer, Heng Ji, Jiawei Han
Finally, we perform error analysis and show that label noise is still the largest challenge for improving performance for this new dataset.
1 code implementation • 25 Mar 2023 • Revanth Gangi Reddy, Yi R. Fung, Qi Zeng, Manling Li, Ziqi Wang, Paul Sullivan, Heng Ji
Further, experiments show that expert analysts tend to add more information into the SmartBook reports, with only 2. 3% of the existing tokens being deleted, meaning SmartBook can serve as a useful foundation for analysts to build upon when creating intelligence reports.
3 code implementations • 17 Apr 2023 • Yujia Qin, Shengding Hu, Yankai Lin, Weize Chen, Ning Ding, Ganqu Cui, Zheni Zeng, Yufei Huang, Chaojun Xiao, Chi Han, Yi Ren Fung, Yusheng Su, Huadong Wang, Cheng Qian, Runchu Tian, Kunlun Zhu, Shihao Liang, Xingyu Shen, Bokai Xu, Zhen Zhang, Yining Ye, Bowen Li, Ziwei Tang, Jing Yi, Yuzhang Zhu, Zhenning Dai, Lan Yan, Xin Cong, Yaxi Lu, Weilin Zhao, Yuxiang Huang, Junxi Yan, Xu Han, Xian Sun, Dahai Li, Jason Phang, Cheng Yang, Tongshuang Wu, Heng Ji, Zhiyuan Liu, Maosong Sun
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.