Search Results for author: Kathleen McKeown

Found 61 papers, 16 papers with code

Towards Augmenting Lexical Resources for Slang and African American English

no code implementations VarDial (COLING) 2020 Alyssa Hwang, William R. Frey, Kathleen McKeown

Researchers in natural language processing have developed large, robust resources for understanding formal Standard American English (SAE), but we lack similar resources for variations of English, such as slang and African American English (AAE).

Word Embeddings

Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport

1 code implementation EMNLP 2021 Manling Li, Tengfei Ma, Mo Yu, Lingfei Wu, Tian Gao, Heng Ji, Kathleen McKeown

Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged.

Timeline Summarization

Controllable Meaning Representation to Text Generation: Linearization and Data Augmentation Strategies

no code implementations EMNLP 2020 Chris Kedzie, Kathleen McKeown

We study the degree to which neural sequence-to-sequence models exhibit fine-grained controllability when performing natural language generation from a meaning representation.

Data Augmentation Dialogue Generation +1

An analysis of document graph construction methods for AMR summarization

no code implementations27 Nov 2021 Fei-Tzin Lee, Chris Kedzie, Nakul Verma, Kathleen McKeown

Prior work in AMR-based summarization has automatically merged the individual sentence graphs into a document graph, but the method of merging and its effects on summary content selection have not been independently evaluated.

Document-level graph construction

A Bag of Tricks for Dialogue Summarization

no code implementations EMNLP 2021 Muhammad Khalifa, Miguel Ballesteros, Kathleen McKeown

Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization.

Language Modelling Language understanding +1

Semantic Categorization of Social Knowledge for Commonsense Question Answering

1 code implementation EMNLP (sustainlp) 2021 Gengyu Wang, Xiaochen Hou, Diyi Yang, Kathleen McKeown, Jing Huang

Large pre-trained language models (PLMs) have led to great success on various commonsense question answering (QA) tasks in an end-to-end fashion.

Question Answering

Event-Centric Natural Language Processing

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.

Emotion-Infused Models for Explainable Psychological Stress Detection

1 code implementation NAACL 2021 Elsbeth Turcan, Smaranda Muresan, Kathleen McKeown

The problem of detecting psychological stress in online posts, and more broadly, of detecting people in distress or in need of help, is a sensitive application for which the ability to interpret models is vital.

Fine-tuning Language Modelling +1

Adversarial Learning for Zero-Shot Stance Detection on Social Media

1 code implementation NAACL 2021 Emily Allaway, Malavika Srikanth, Kathleen McKeown

Stance detection on social media can help to identify and understand slanted news or commentary in everyday life.

Stance Detection

Segmenting Subtitles for Correcting ASR Segmentation Errors

no code implementations EACL 2021 David Wan, Chris Kedzie, Faisal Ladhak, Elsbeth Turcan, Petra Galuščáková, Elena Zotkina, Zhengping Jiang, Peter Bell, Kathleen McKeown

Typical ASR systems segment the input audio into utterances using purely acoustic information, which may not resemble the sentence-like units that are expected by conventional machine translation (MT) systems for Spoken Language Translation.

Information Retrieval Machine Translation +1

Event Guided Denoising for Multilingual Relation Learning

no code implementations4 Dec 2020 Amith Ananthram, Emily Allaway, Kathleen McKeown

General purpose relation extraction has recently seen considerable gains in part due to a massively data-intensive distant supervision technique from Soares et al. (2019) that produces state-of-the-art results across many benchmarks.

Denoising Fine-tuning +1

Event-Guided Denoising for Multilingual Relation Learning

no code implementations COLING 2020 Amith Ananthram, Emily Allaway, Kathleen McKeown

General purpose relation extraction has recently seen considerable gains in part due to a massively data-intensive distant supervision technique from Soares et al. (2019) that produces state-of-the-art results across many benchmarks.

Denoising Fine-tuning +1

Detecting Urgency Status of Crisis Tweets: A Transfer Learning Approach for Low Resource Languages

1 code implementation COLING 2020 Efsun Sarioglu Kayi, Linyong Nan, Bohan Qu, Mona Diab, Kathleen McKeown

We adopt cross-lingual embeddings constructed using different methods to extract features of the tweets, including a few state-of-the-art contextual embeddings such as BERT, RoBERTa and XLM-R. We train classifiers of different architectures on the extracted features.

Transfer Learning

Incorporating Terminology Constraints in Automatic Post-Editing

1 code implementation WMT (EMNLP) 2020 David Wan, Chris Kedzie, Faisal Ladhak, Marine Carpuat, Kathleen McKeown

In this paper, we present both autoregressive and non-autoregressive models for lexically constrained APE, demonstrating that our approach enables preservation of 95% of the terminologies and also improves translation quality on English-German benchmarks.

Automatic Post-Editing Data Augmentation +1

Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines

no code implementations19 Oct 2020 David Wan, Zhengping Jiang, Chris Kedzie, Elsbeth Turcan, Peter Bell, Kathleen McKeown

In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation.

Information Retrieval POS +2

A Unified Feature Representation for Lexical Connotations

no code implementations EACL 2021 Emily Allaway, Kathleen McKeown

Ideological attitudes and stance are often expressed through subtle meanings of words and phrases.

Stance Detection

Exploring Content Selection in Summarization of Novel Chapters

1 code implementation ACL 2020 Faisal Ladhak, Bryan Li, Yaser Al-Onaizan, Kathleen McKeown

We present a new summarization task, generating summaries of novel chapters using summary/chapter pairs from online study guides.

Extractive Summarization

A Good Sample is Hard to Find: Noise Injection Sampling and Self-Training for Neural Language Generation Models

1 code implementation WS 2019 Chris Kedzie, Kathleen McKeown

Deep neural networks (DNN) are quickly becoming the de facto standard modeling method for many natural language generation (NLG) tasks.

Text Generation

Automatically Inferring Gender Associations from Language

no code implementations IJCNLP 2019 Serina Chang, Kathleen McKeown

In this paper, we pose the question: do people talk about women and men in different ways?

Fine-grained Sentiment Analysis with Faithful Attention

no code implementations19 Aug 2019 Ruiqi Zhong, Steven Shao, Kathleen McKeown

While the general task of textual sentiment classification has been widely studied, much less research looks specifically at sentiment between a specified source and target.

Relation Extraction Sentiment Analysis

The ARIEL-CMU Systems for LoReHLT18

no code implementations24 Feb 2019 Aditi Chaudhary, Siddharth Dalmia, Junjie Hu, Xinjian Li, Austin Matthews, Aldrian Obaja Muis, Naoki Otani, Shruti Rijhwani, Zaid Sheikh, Nidhi Vyas, Xinyi Wang, Jiateng Xie, Ruochen Xu, Chunting Zhou, Peter J. Jansen, Yiming Yang, Lori Levin, Florian Metze, Teruko Mitamura, David R. Mortensen, Graham Neubig, Eduard Hovy, Alan W. black, Jaime Carbonell, Graham V. Horwood, Shabnam Tafreshi, Mona Diab, Efsun S. Kayi, Noura Farra, Kathleen McKeown

This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).

Machine Translation Translation

Content Selection in Deep Learning Models of Summarization

2 code implementations EMNLP 2018 Chris Kedzie, Kathleen McKeown, Hal Daume III

We carry out experiments with deep learning models of summarization across the domains of news, personal stories, meetings, and medical articles in order to understand how content selection is performed.

Predictive Embeddings for Hate Speech Detection on Twitter

no code implementations WS 2018 Rohan Kshirsagar, Tyus Cukuvac, Kathleen McKeown, Susan McGregor

We present a neural-network based approach to classifying online hate speech in general, as well as racist and sexist speech in particular.

Hate Speech Detection Word Embeddings

Detecting Gang-Involved Escalation on Social Media Using Context

1 code implementation EMNLP 2018 Serina Chang, Ruiqi Zhong, Ethan Adams, Fei-Tzin Lee, Siddharth Varia, Desmond Patton, William Frey, Chris Kedzie, Kathleen McKeown

Gang-involved youth in cities such as Chicago have increasingly turned to social media to post about their experiences and intents online.

Multimodal Social Media Analysis for Gang Violence Prevention

no code implementations23 Jul 2018 Philipp Blandfort, Desmond Patton, William R. Frey, Svebor Karaman, Surabhi Bhargava, Fei-Tzin Lee, Siddharth Varia, Chris Kedzie, Michael B. Gaskell, Rossano Schifanella, Kathleen McKeown, Shih-Fu Chang

In this paper we partnered computer scientists with social work researchers, who have domain expertise in gang violence, to analyze how public tweets with images posted by youth who mention gang associations on Twitter can be leveraged to automatically detect psychosocial factors and conditions that could potentially assist social workers and violence outreach workers in prevention and early intervention programs.

General Classification

Domain-Adaptable Hybrid Generation of RDF Entity Descriptions

no code implementations IJCNLP 2017 Or Biran, Kathleen McKeown

RDF ontologies provide structured data on entities in many domains and continue to grow in size and diversity.

Domain Adaptation

Leveraging Sparse and Dense Feature Combinations for Sentiment Classification

no code implementations13 Aug 2017 Tao Yu, Christopher Hidey, Owen Rambow, Kathleen McKeown

This model outperforms many deep learning models and achieves comparable results to other deep learning models with complex architectures on sentiment analysis datasets.

Classification General Classification +1

SMARTies: Sentiment Models for Arabic Target Entities

no code implementations EACL 2017 Noura Farra, Kathleen McKeown

We consider entity-level sentiment analysis in Arabic, a morphologically rich language with increasing resources.

Sentiment Analysis

Automatically Processing Tweets from Gang-Involved Youth: Towards Detecting Loss and Aggression

no code implementations COLING 2016 Terra Blevins, Robert Kwiatkowski, Jamie MacBeth, Kathleen McKeown, Desmond Patton, Owen Rambow

Violence is a serious problems for cities like Chicago and has been exacerbated by the use of social media by gang-involved youths for taunting rival gangs.

Real-Time Web Scale Event Summarization Using Sequential Decision Making

no code implementations12 May 2016 Chris Kedzie, Fernando Diaz, Kathleen McKeown

We present a system based on sequential decision making for the online summarization of massive document streams, such as those found on the web.

Decision Making

Annotating Agreement and Disagreement in Threaded Discussion

no code implementations LREC 2012 Jacob Andreas, Sara Rosenthal, Kathleen McKeown

We introduce a new corpus of sentence-level agreement and disagreement annotations over LiveJournal and Wikipedia threads.

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