Search Results for author: Claire Cardie

Found 97 papers, 31 papers with code

Question Generation using a Scratchpad Encoder

no code implementations ICLR 2019 Ryan Y. Benmalek, Madian Khabsa, Suma Desu, Claire Cardie, Michele Banko

In this paper we introduce the Scratchpad Encoder, a novel addition to the sequence to sequence (seq2seq) framework and explore its effectiveness in generating natural language questions from a given logical form.

Question Generation Question-Generation

Intrinsic Evaluation of Summarization Datasets

no code implementations EMNLP 2020 Rishi Bommasani, Claire Cardie

High quality data forms the bedrock for building meaningful statistical models in NLP.

SUMSUM@FNS-2020 Shared Task

no code implementations FNP (COLING) 2020 Siyan Zheng, Anneliese Lu, Claire Cardie

This paper describes the SUMSUM systems submitted to the Financial Narrative Summarization Shared Task (FNS-2020).

Extractive Summarization

Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations

no code implementations24 May 2023 Wenting Zhao, Justin T. Chiu, Claire Cardie, Alexander M. Rush

Instead of using direct supervision, this work proposes an approach for abductive commonsense reasoning that exploits the fact that only a subset of explanations is correct for a given context.

HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision

no code implementations23 May 2023 Wenting Zhao, Justin T. Chiu, Claire Cardie, Alexander M. Rush

Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers.

Multi-hop Question Answering Question Answering

Fashionpedia-Taste: A Dataset towards Explaining Human Fashion Taste

no code implementations3 May 2023 Mengyun Shi, Serge Belongie, Claire Cardie

Existing fashion datasets do not consider the multi-facts that cause a consumer to like or dislike a fashion image.

Automatic Error Analysis for Document-level Information Extraction

1 code implementation ACL 2022 Aliva Das, Xinya Du, Barry Wang, Kejian Shi, Jiayuan Gu, Thomas Porter, Claire Cardie

Document-level information extraction (IE) tasks have recently begun to be revisited in earnest using the end-to-end neural network techniques that have been successful on their sentence-level IE counterparts.

Relation Extraction

Compositional Task-Oriented Parsing as Abstractive Question Answering

1 code implementation NAACL 2022 Wenting Zhao, Konstantine Arkoudas, Weiqi Sun, Claire Cardie

Task-oriented parsing (TOP) aims to convert natural language into machine-readable representations of specific tasks, such as setting an alarm.

abstractive question answering Question Answering +1

Visual Prompt Tuning

2 code implementations23 Mar 2022 Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge Belongie, Bharath Hariharan, Ser-Nam Lim

The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning.

Image Classification Long-tail Learning +1

Rethinking Nearest Neighbors for Visual Classification

1 code implementation15 Dec 2021 Menglin Jia, Bor-Chun Chen, Zuxuan Wu, Claire Cardie, Serge Belongie, Ser-Nam Lim

In this paper, we investigate $k$-Nearest-Neighbor (k-NN) classifiers, a classical model-free learning method from the pre-deep learning era, as an augmentation to modern neural network based approaches.


Learning to Adapt to Semantic Shift

no code implementations29 Sep 2021 Ryan Y Benmalek, Sabhya Chhabria, Pedro O. Pinheiro, Claire Cardie, Serge Belongie

These models outperform both previous work and static models under both \emph{static} and \emph{continual} semantic shifts, suggesting that ``learning to adapt'' is a useful capability for models and agents in a changing world.


Template Filling with Generative Transformers

1 code implementation NAACL 2021 Xinya Du, Alexander Rush, Claire Cardie

Template filling is generally tackled by a pipeline of two separate supervised systems {--} one for role-filler extraction and another for template/event recognition.

Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data

no code implementations Findings (EMNLP) 2021 Dian Yu, Kai Sun, Dong Yu, Claire Cardie

In spite of much recent research in the area, it is still unclear whether subject-area question-answering data is useful for machine reading comprehension (MRC) tasks.

Machine Reading Comprehension Multiple-choice +1

Intentonomy: a Dataset and Study towards Human Intent Understanding

1 code implementation CVPR 2021 Menglin Jia, Zuxuan Wu, Austin Reiter, Claire Cardie, Serge Belongie, Ser-Nam Lim

Based on our findings, we conduct further study to quantify the effect of attending to object and context classes as well as textual information in the form of hashtags when training an intent classifier.

Adding Chit-Chat to Enhance Task-Oriented Dialogues

1 code implementation NAACL 2021 Kai Sun, Seungwhan Moon, Paul Crook, Stephen Roller, Becka Silvert, Bing Liu, Zhiguang Wang, Honglei Liu, Eunjoon Cho, Claire Cardie

Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e. g., booking hotels), open-domain chatbots aim at making socially engaging conversations.

Dialogue Generation Dialogue Understanding +1

Exploring the Role of Argument Structure in Online Debate Persuasion

no code implementations EMNLP 2020 Jialu Li, Esin Durmus, Claire Cardie

Online debate forums provide users a platform to express their opinions on controversial topics while being exposed to opinions from diverse set of viewpoints.

Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings

no code implementations ACL 2020 Rishi Bommasani, Kelly Davis, Claire Cardie

Contextualized representations (e. g. ELMo, BERT) have become the default pretrained representations for downstream NLP applications.

Word Embeddings

Event Extraction by Answering (Almost) Natural Questions

3 code implementations EMNLP 2020 Xinya Du, Claire Cardie

The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments.

Event Argument Extraction Event Extraction +3

Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset

5 code implementations ECCV 2020 Menglin Jia, Mengyun Shi, Mikhail Sirotenko, Yin Cui, Claire Cardie, Bharath Hariharan, Hartwig Adam, Serge Belongie

In this work we explore the task of instance segmentation with attribute localization, which unifies instance segmentation (detect and segment each object instance) and fine-grained visual attribute categorization (recognize one or multiple attributes).

Fine-Grained Visual Categorization Fine-Grained Visual Recognition +3

Dialogue-Based Relation Extraction

3 code implementations ACL 2020 Dian Yu, Kai Sun, Claire Cardie, Dong Yu

We present the first human-annotated dialogue-based relation extraction (RE) dataset DialogRE, aiming to support the prediction of relation(s) between two arguments that appear in a dialogue.

Ranked #6 on Dialog Relation Extraction on DialogRE (F1c (v1) metric)

Dialog Relation Extraction

The Role of Pragmatic and Discourse Context in Determining Argument Impact

no code implementations IJCNLP 2019 Esin Durmus, Faisal Ladhak, Claire Cardie

Research in the social sciences and psychology has shown that the persuasiveness of an argument depends not only the language employed, but also on attributes of the source/communicator, the audience, and the appropriateness and strength of the argument's claims given the pragmatic and discourse context of the argument.

Persuasion of the Undecided: Language vs. the Listener

no code implementations WS 2019 Liane Longpre, Esin Durmus, Claire Cardie

In a study of users of a popular debate platform, we find first that different combinations of linguistic features are critical for predicting persuasion outcomes for UNDECIDED versus DECIDED members of the audience.

Keeping Notes: Conditional Natural Language Generation with a Scratchpad Encoder

no code implementations ACL 2019 Ryan Benmalek, Madian Khabsa, Suma Desu, Claire Cardie, Michele Banko

We introduce the Scratchpad Mechanism, a novel addition to the sequence-to-sequence (seq2seq) neural network architecture and demonstrate its effectiveness in improving the overall fluency of seq2seq models for natural language generation tasks.

Machine Translation Question Generation +4

A Corpus for Modeling User and Language Effects in Argumentation on Online Debating

no code implementations ACL 2019 Esin Durmus, Claire Cardie

Existing argumentation datasets have succeeded in allowing researchers to develop computational methods for analyzing the content, structure and linguistic features of argumentative text.

Exploring the Role of Prior Beliefs for Argument Persuasion

no code implementations NAACL 2018 Esin Durmus, Claire Cardie

Public debate forums provide a common platform for exchanging opinions on a topic of interest.

Determining Relative Argument Specificity and Stance for Complex Argumentative Structures

no code implementations ACL 2019 Esin Durmus, Faisal Ladhak, Claire Cardie

Systems for automatic argument generation and debate require the ability to (1) determine the stance of any claims employed in the argument and (2) assess the specificity of each claim relative to the argument context.


Be Consistent! Improving Procedural Text Comprehension using Label Consistency

1 code implementation NAACL 2019 Xinya Du, Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark, Claire Cardie

Our goal is procedural text comprehension, namely tracking how the properties of entities (e. g., their location) change with time given a procedural text (e. g., a paragraph about photosynthesis, a recipe).

Reading Comprehension

Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism

1 code implementation12 Jun 2019 Ryan Y. Benmalek, Madian Khabsa, Suma Desu, Claire Cardie, Michele Banko

We introduce the Scratchpad Mechanism, a novel addition to the sequence-to-sequence (seq2seq) neural network architecture and demonstrate its effectiveness in improving the overall fluency of seq2seq models for natural language generation tasks.

Machine Translation Question Generation +4

SPARSE: Structured Prediction using Argument-Relative Structured Encoding

no code implementations WS 2019 Rishi Bommasani, Arzoo Katiyar, Claire Cardie

We apply our approach to the second-order structured prediction task studied in the 2016/2017 Belief and Sentiment analysis evaluations (BeSt): given a document and its entities, relations, and events (including metadata and mentions), determine the sentiment of each entity towards every relation and event in the document.

Sentiment Analysis Structured Prediction

Improving Question Answering with External 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.

Multiple-choice Question Answering

DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension

1 code implementation1 Feb 2019 Kai Sun, Dian Yu, Jianshu Chen, Dong Yu, Yejin Choi, Claire Cardie

DREAM is likely to present significant challenges for existing reading comprehension systems: 84% of answers are non-extractive, 85% of questions require reasoning beyond a single sentence, and 34% of questions also involve commonsense knowledge.

Dialogue Understanding Multiple-choice +1

Multi-Source Cross-Lingual Model Transfer: Learning What to Share

1 code implementation ACL 2019 Xilun Chen, Ahmed Hassan Awadallah, Hany Hassan, Wei Wang, Claire Cardie

In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance.

Cross-Lingual NER text-classification +2

Zero-Resource Multilingual Model Transfer: Learning What to Share

no code implementations27 Sep 2018 Xilun Chen, Ahmed Hassan Awadallah, Hany Hassan, Wei Wang, Claire Cardie

In this work, we propose a zero-resource multilingual transfer learning model that can utilize training data in multiple source languages, while not requiring target language training data nor cross-lingual supervision.

Cross-Lingual Transfer text-classification +2

Towards Dynamic Computation Graphs via Sparse Latent Structure

1 code implementation EMNLP 2018 Vlad Niculae, André F. T. Martins, Claire Cardie

Deep NLP models benefit from underlying structures in the data---e. g., parse trees---typically extracted using off-the-shelf parsers.

graph construction

Unsupervised Multilingual Word Embeddings

3 code implementations EMNLP 2018 Xilun Chen, Claire Cardie

Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space.

Multilingual Word Embeddings Translation +2

The Neural Painter: Multi-Turn Image Generation

no code implementations16 Jun 2018 Ryan Y. Benmalek, Claire Cardie, Serge Belongie, Xiadong He, Jianfeng Gao

In this work we combine two research threads from Vision/ Graphics and Natural Language Processing to formulate an image generation task conditioned on attributes in a multi-turn setting.

Benchmarking Conditional Image Generation

Nested Named Entity Recognition Revisited

no code implementations NAACL 2018 Arzoo Katiyar, Claire Cardie

We propose a novel recurrent neural network-based approach to simultaneously handle nested named entity recognition and nested entity mention detection.

Coreference Resolution named-entity-recognition +4

Understanding the Effect of Gender and Stance in Opinion Expression in Debates on ``Abortion''

no code implementations WS 2018 Esin Durmus, Claire Cardie

We use the gender and stance information to identify significant linguistic differences across individuals with different gender and stance.

Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia

1 code implementation ACL 2018 Xinya Du, Claire Cardie

We study the task of generating from Wikipedia articles question-answer pairs that cover content beyond a single sentence.

Question Generation Question-Generation

Identifying Where to Focus in Reading Comprehension for Neural Question Generation

no code implementations EMNLP 2017 Xinya Du, Claire Cardie

A first step in the task of automatically generating questions for testing reading comprehension is to identify \textit{question-worthy} sentences, i. e. sentences in a text passage that humans find it worthwhile to ask questions about.

Dependency Parsing Machine Translation +7

Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees

no code implementations ACL 2017 Arzoo Katiyar, Claire Cardie

We also compare our model with an end-to-end tree-based LSTM model (SPTree) by Miwa and Bansal (2016) and show that our model performs within 1{\%} on entity mentions and 2{\%} on relations.

Argument Mining with Structured SVMs and RNNs

1 code implementation ACL 2017 Vlad Niculae, Joonsuk Park, Claire Cardie

We propose a novel factor graph model for argument mining, designed for settings in which the argumentative relations in a document do not necessarily form a tree structure.

Argument Mining General Classification

Summarizing Decisions in Spoken Meetings

no code implementations25 Jun 2016 Lu Wang, Claire Cardie

This paper addresses the problem of summarizing decisions in spoken meetings: our goal is to produce a concise {\it decision abstract} for each meeting decision.

Topic Models

Focused Meeting Summarization via Unsupervised Relation Extraction

no code implementations WS 2012 Lu Wang, Claire Cardie

We present a novel unsupervised framework for focused meeting summarization that views the problem as an instance of relation extraction.

Extractive Summarization Meeting Summarization +1

Unsupervised Topic Modeling Approaches to Decision Summarization in Spoken Meetings

no code implementations WS 2012 Lu Wang, Claire Cardie

We present a token-level decision summarization framework that utilizes the latent topic structures of utterances to identify "summary-worthy" words.

Decision Making Topic Models

Socially-Informed Timeline Generation for Complex Events

no code implementations HLT 2015 Lu Wang, Claire Cardie, Galen Marchetti

Existing timeline generation systems for complex events consider only information from traditional media, ignoring the rich social context provided by user-generated content that reveals representative public interests or insightful opinions.


Improving Agreement and Disagreement Identification in Online Discussions with A Socially-Tuned Sentiment Lexicon

no code implementations WS 2014 Lu Wang, Claire Cardie

For example, the isotonic CRF model achieves F1 scores of 0. 74 and 0. 67 for agreement and disagreement detection, when a linear chain CRF obtains 0. 58 and 0. 56 for the discussions on Wikipedia Talk pages.

A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection

no code implementations ACL 2014 Lu Wang, Claire Cardie

We investigate the novel task of online dispute detection and propose a sentiment analysis solution to the problem: we aim to identify the sequence of sentence-level sentiments expressed during a discussion and to use them as features in a classifier that predicts the DISPUTE/NON-DISPUTE label for the discussion as a whole.

Sentiment Analysis

Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

2 code implementations TACL 2018 Xilun Chen, Yu Sun, Ben Athiwaratkun, Claire Cardie, Kilian Weinberger

To tackle the sentiment classification problem in low-resource languages without adequate annotated data, we propose an Adversarial Deep Averaging Network (ADAN) to transfer the knowledge learned from labeled data on a resource-rich source language to low-resource languages where only unlabeled data exists.

Classification Cross-Lingual Document Classification +5

Modeling Compositionality with Multiplicative Recurrent Neural Networks

no code implementations20 Dec 2014 Ozan İrsoy, Claire Cardie

We present the multiplicative recurrent neural network as a general model for compositional meaning in language, and evaluate it on the task of fine-grained sentiment analysis.

Sentiment Analysis

Deep Recursive Neural Networks for Compositionality in Language

no code implementations NeurIPS 2014 Ozan .Irsoy, Claire Cardie

In this work we introduce a new architecture --- a deep recursive neural network (deep RNN) --- constructed by stacking multiple recursive layers.

Sentiment Analysis Sentiment Classification

Joint Modeling of Opinion Expression Extraction and Attribute Classification

no code implementations TACL 2014 Bishan Yang, Claire Cardie

In this paper, we study the problems of opinion expression extraction and expression-level polarity and intensity classification.

Classification Fine-Grained Opinion Analysis +3

Bidirectional Recursive Neural Networks for Token-Level Labeling with Structure

no code implementations2 Dec 2013 Ozan İrsoy, Claire Cardie

Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks.

Early Stage Influenza Detection from Twitter

no code implementations27 Sep 2013 Jiwei Li, Claire Cardie

In this paper, we investigate the real-time flu detection problem on Twitter data by proposing Flu Markov Network (Flu-MN): a spatio-temporal unsupervised Bayesian algorithm based on a 4 phase Markov Network, trying to identify the flu breakout at the earliest stage.

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