no code implementations • Findings (EMNLP) 2021 • Prafulla Kumar Choubey, Ruihong Huang
We present an actor-critic framework to induce subtopical structures in a news article for news discourse profiling.
Ranked #4 on Text Classification on NewsDiscourse
no code implementations • ACL 2022 • Bohan Zhang, Prafulla Kumar Choubey, Ruihong Huang
Document-level text simplification often deletes some sentences besides performing lexical, grammatical or structural simplification to reduce text complexity.
1 code implementation • NAACL 2022 • Pei Chen, Haotian Xu, Cheng Zhang, Ruihong Huang
General domain Named Entity Recognition (NER) datasets like CoNLL-2003 mostly annotate coarse-grained location entities such as a country or a city.
no code implementations • EMNLP 2020 • Wenlin Yao, Zeyu Dai, Maitreyi Ramaswamy, Bonan Min, Ruihong Huang
We first obtain the initial set of event pairs that are likely to have the subevent relation, by exploiting two observations that 1) subevents are temporally contained by the parent event, and 2) the definitions of the parent event can be used to further guide the identification of subevents.
no code implementations • 8 Apr 2024 • Ajit Jain, Andruid Kerne, Nic Lupfer, Gabriel Britain, Aaron Perrine, Yoonsuck Choe, John Keyser, Ruihong Huang, Jinsil Seo, Annie Sungkajun, Robert Lightfoot, Timothy McGuire
With the goal of making the analytics intelligible to instructors, we developed a research artifact integrating a design analytics dashboard with design instances, and the design environment that students use to create them.
1 code implementation • 2 Apr 2024 • Yuanyuan Lei, Ruihong Huang
Then, we incorporate event relation graph for bias sentences identification in two steps: an event-aware language model is built to inject the events and event relations knowledge into the basic language model via soft labels; further, a relation-aware graph attention network is designed to update sentence embedding with events and event relations information based on hard labels.
1 code implementation • 2 Apr 2024 • Yuanyuan Lei, Md Messal Monem Miah, Ayesha Qamar, Sai Ramana Reddy, Jonathan Tong, Haotian Xu, Ruihong Huang
This paper initiates a new task to understand moral opinions towards events in news articles.
1 code implementation • 2 Apr 2024 • Yuanyuan Lei, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Ruihong Huang, Dong Yu
To address this issue and make the summarizer express both sides of opinions, we introduce the concept of polarity calibration, which aims to align the polarity of output summary with that of input text.
1 code implementation • EMNLP 2023 • Md Messal Monem Miah, Adarsh Pyarelal, Ruihong Huang
We propose a framework for online multimodal dialog act (DA) classification based on raw audio and ASR-generated transcriptions of current and past utterances.
Ranked #1 on Dialogue Act Classification on EMOTyDA
1 code implementation • 28 Oct 2023 • Yuanyuan Lei, Ruihong Huang
Conspiracy theories, as a type of misinformation, are narratives that explains an event or situation in an irrational or malicious manner.
1 code implementation • 28 Oct 2023 • Yuanyuan Lei, Ruihong Huang
Hence, we propose to incorporate both local and global discourse structures for propaganda discovery and construct two teacher models for identifying PDTB-style discourse relations between nearby sentences and common discourse roles of sentences in a news article respectively.
no code implementations • 28 Oct 2023 • Yujian Liu, Xinliang Frederick Zhang, Kaijian Zou, Ruihong Huang, Nick Beauchamp, Lu Wang
Public opinion is shaped by the information news media provide, and that information in turn may be shaped by the ideological preferences of media outlets.
no code implementations • 20 Sep 2023 • Ming Li, Ruihong Huang
News Discourse Profiling seeks to scrutinize the event-related role of each sentence in a news article and has been proven useful across various downstream applications.
no code implementations • 8 Sep 2023 • Ming Li, Ruihong Huang
Rhetorical Structure Theory based Discourse Parsing (RST-DP) explores how clauses, sentences, and large text spans compose a whole discourse and presents the rhetorical structure as a hierarchical tree.
1 code implementation • NeurIPS 2023 • Pei Chen, Soumajyoti Sarkar, Leonard Lausen, Balasubramaniam Srinivasan, Sheng Zha, Ruihong Huang, George Karypis
Language models pretrained on large collections of tabular data have demonstrated their effectiveness in several downstream tasks.
1 code implementation • 14 Jul 2023 • Sachin J. Chanchani, Ruihong Huang
Vector representations of natural language are ubiquitous in search applications.
1 code implementation • 21 Oct 2022 • Prafulla Kumar Choubey, Ruihong Huang
We propose to leverage news discourse profiling to model document-level temporal structures for building temporal dependency graphs.
no code implementations • 18 Oct 2022 • Ming Li, Ruihong Huang
Complex feature extractors are widely employed for text representation building.
1 code implementation • ACL 2021 • Pei Chen, Haibo Ding, Jun Araki, Ruihong Huang
Named entity recognition (NER) is well studied for the general domain, and recent systems have achieved human-level performance for identifying common entity types.
1 code implementation • EACL 2021 • Prafulla Kumar Choubey, Ruihong Huang
We propose to leverage lexical paraphrases and high precision rules informed by news discourse structure to automatically collect coreferential and non-coreferential event pairs from unlabeled English news articles.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Pei Chen, Hang Yang, Kang Liu, Ruihong Huang, Yubo Chen, Taifeng Wang, Jun Zhao
Event information is usually scattered across multiple sentences within a document.
1 code implementation • EMNLP 2020 • Yun He, Zhuoer Wang, Yin Zhang, Ruihong Huang, James Caverlee
We present a new benchmark dataset called PARADE for paraphrase identification that requires specialized domain knowledge.
1 code implementation • 4 Oct 2020 • Wenlin Yao, Cheng Zhang, Shiva Saravanan, Ruihong Huang, Ali Mostafavi
People increasingly use social media to report emergencies, seek help or share information during disasters, which makes social networks an important tool for disaster management.
no code implementations • ACL 2020 • Prafulla Kumar Choubey, Aaron Lee, Ruihong Huang, Lu Wang
Understanding discourse structures of news articles is vital to effectively contextualize the occurrence of a news event.
Ranked #5 on Text Classification on NewsDiscourse
no code implementations • LREC 2020 • Prafulla Kumar Choubey, Ruihong Huang
Most supervised word sense disambiguation (WSD) systems build word-specific classifiers by leveraging labeled data.
no code implementations • IJCNLP 2019 • Zeyu Dai, Ruihong Huang
We argue that external commonsense knowledge and linguistic constraints need to be incorporated into neural network models for mitigating data sparsity issues and further improving the performance of discourse parsing.
1 code implementation • IJCNLP 2019 • Lisa Fan, Marshall White, Eva Sharma, Ruisi Su, Prafulla Kumar Choubey, Ruihong Huang, Lu Wang
The increasing prevalence of political bias in news media calls for greater public awareness of it, as well as robust methods for its detection.
no code implementations • NAACL 2019 • Lei Gao, Prafulla Kumar Choubey, Ruihong Huang
We aim to comprehensively identify all the event causal relations in a document, both within a sentence and across sentences, which is important for reconstructing pivotal event structures.
no code implementations • NAACL 2019 • Sanuj Sharma, Prafulla Kumar Choubey, Ruihong Huang
Specifically, we use the current user utterance and the most recent system utterance to determine the relevance of a system utterance.
1 code implementation • EMNLP 2018 • Zeyu Dai, Ruihong Huang
Capabilities to categorize a clause based on the type of situation entity (e. g., events, states and generic statements) the clause introduces to the discourse can benefit many NLP applications.
no code implementations • COLING 2018 • Zeyu Dai, Himanshu Taneja, Ruihong Huang
Journalists usually organize and present the contents of a news article following a well-defined structure.
no code implementations • ACL 2018 • Prafulla Kumar Choubey, Ruihong Huang
This paper proposes a novel approach for event coreference resolution that models correlations between event coreference chains and document topical structures through an Integer Linear Programming formulation.
no code implementations • NAACL 2018 • Prafulla Kumar Choubey, Kaushik Raju, Ruihong Huang
Identifying the most dominant and central event of a document, which governs and connects other foreground and background events in the document, is useful for many applications, such as text summarization, storyline generation and text segmentation.
no code implementations • ACL 2018 • Wenlin Yao, Ruihong Huang
Inspired by the double temporality characteristic of narrative texts, we propose a novel approach for acquiring rich temporal "before/after" event knowledge across sentences in narrative stories.
no code implementations • NAACL 2018 • Zeyu Dai, Ruihong Huang
We argue that semantic meanings of a sentence or clause can not be interpreted independently from the rest of a paragraph, or independently from all discourse relations and the overall paragraph-level discourse structure.
General Classification Implicit Discourse Relation Classification +2
1 code implementation • 6 Nov 2017 • Prafulla Kumar Choubey, Ruihong Huang
Our simple system designed using minimal features achieved the micro-average F1 scores of 57. 72, 44. 27 and 42. 47 for event span detection, type identification and realis status classification tasks respectively.
no code implementations • IJCNLP 2017 • Lei Gao, Alexis Kuppersmith, Ruihong Huang
In the wake of a polarizing election, social media is laden with hateful content.
2 code implementations • RANLP 2017 • Lei Gao, Ruihong Huang
In the wake of a polarizing election, the cyber world is laden with hate speech.
no code implementations • IJCNLP 2017 • Zeyu Dai, Wenlin Yao, Ruihong Huang
Focusing on the task of identifying event temporal status, we find that events directly or indirectly governing the target event in a dependency tree are most important contexts.
no code implementations • RANLP 2017 • Wenlin Yao, Saipravallika Nettyam, Ruihong Huang
Capabilities of detecting temporal relations between two events can benefit many applications.
no code implementations • RANLP 2017 • Wenlin Yao, Zeyu Dai, Ruihong Huang, James Caverlee
The lack of large realistic datasets presents a bottleneck in online deception detection studies.
no code implementations • EMNLP 2017 • Prafulla Kumar Choubey, Ruihong Huang
We present a sequential model for temporal relation classification between intra-sentence events.
no code implementations • EMNLP 2017 • Prafulla Kumar Choubey, Ruihong Huang
We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as across event chains.
no code implementations • WS 2016 • Ajit Jain, Girish Kasiviswanathan, Ruihong Huang
Accurate event detection in social media is very challenging because user generated contents are extremely noisy and sparse in content.
no code implementations • COLING 2016 • Fangyuan Li, Ruihong Huang, Deyi Xiong, Min Zhang
Aiming to resolve high complexities of event descriptions, previous work (Huang and Riloff, 2013) proposes multi-faceted event recognition and a bootstrapping method to automatically acquire both event facet phrases and event expressions from unannotated texts.
no code implementations • COLING 2016 • Seth Polsley, Pooja Jhunjhunwala, Ruihong Huang
Attorneys, judges, and others in the justice system are constantly surrounded by large amounts of legal text, which can be difficult to manage across many cases.