Search Results for author:
Found 98 papers, 43 papers with code
IGA: An Intent-Guided Authoring Assistant
While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored.
Learning Prototype Representations Across Few-Shot Tasks for Event Detection
We address the sampling bias and outlier issues in few-shot learning for event detection, a subtask of information extraction.
Document-Level Event Argument Extraction via Optimal Transport
Event Argument Extraction (EAE) is one of the sub-tasks of event extraction, aiming to recognize the role of each entity mention toward a specific event trigger.
Transfer Learning and Prediction Consistency for Detecting Offensive Spans of Text
Toxic span detection is the task of recognizing offensive spans in a text snippet.
Joint Summarization-Entailment Optimization for Consumer Health Question Understanding
Understanding the intent of medical questions asked by patients, or Consumer Health Questions, is an essential skill for medical Conversational AI systems.
UCSD-Adobe at MEDIQA 2021: Transfer Learning and Answer Sentence Selection for Medical Summarization
We show that both transfer learning methods combined achieve the highest ROUGE scores.
ViLBERTScore: Evaluating Image Caption Using Vision-and-Language BERT
In this paper, we propose an evaluation metric for image captioning systems using both image and text information.
Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations
We propose a margin-based loss for vision-language model pretraining that encourages gradient-based explanations that are consistent with region-level annotations.
Fine-grained Image Captioning with CLIP Reward
Toward more descriptive and distinctive caption generation, we propose using CLIP, a multimodal encoder trained on huge image-text pairs from web, to calculate multimodal similarity and use it as a reward function.
Symlink: A New Dataset for Scientific Symbol-Description Linking
Mathematical symbols and descriptions appear in various forms across document section boundaries without explicit markup.
Factual Error Correction for Abstractive Summaries Using Entity Retrieval
In this paper, we propose an efficient factual error correction system RFEC based on entities retrieval post-editing process.
Survey of Aspect-based Sentiment Analysis Datasets
Aspect-based sentiment analysis (ABSA) is a natural language processing problem that requires analyzing user-generated reviews in order to determine: a) The target entity being reviewed, b) The high-level aspect to which it belongs, and c) The sentiment expressed toward the targets and the aspects.
MHMS: Multimodal Hierarchical Multimedia Summarization
Multimedia summarization with multimodal output can play an essential role in real-world applications, i. e., automatically generating cover images and titles for news articles or providing introductions to online videos.
Enriching Unsupervised User Embedding via Medical Concepts
Clinical notes in Electronic Health Records (EHR) present rich documented information of patients to inference phenotype for disease diagnosis and study patient characteristics for cohort selection.
CAISE: Conversational Agent for Image Search and Editing
To our knowledge, this is the first dataset that provides conversational image search and editing annotations, where the agent holds a grounded conversation with users and helps them to search and edit images according to their requests.
SemEval 2022 Task 12: Symlink- Linking Mathematical Symbols to their Descriptions
Given the increasing number of livestreaming videos, automatic speech recognition and post-processing for livestreaming video transcripts are crucial for efficient data management as well as knowledge mining.
MACRONYM: A Large-Scale Dataset for Multilingual and Multi-Domain Acronym Extraction
Acronym extraction is the task of identifying acronyms and their expanded forms in texts that is necessary for various NLP applications.
Exploring Conditional Text Generation for Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) is an NLP task that entails processing user-generated reviews to determine (i) the target being evaluated, (ii) the aspect category to which it belongs, and (iii) the sentiment expressed towards the target and aspect pair.
TLDR9+: A Large Scale Resource for Extreme Summarization of Social Media Posts
Recent models in developing summarization systems consist of millions of parameters and the model performance is highly dependent on the abundance of training data.
Ranked #1 on
Extreme Summarization
on TLDR9+
User-Entity Differential Privacy in Learning Natural Language Models
In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models.
Bit-aware Randomized Response for Local Differential Privacy in Federated Learning
In this paper, we develop BitRand, a bit-aware randomized response algorithm, to preserve local differential privacy (LDP) in federated learning (FL).
StreamHover: Livestream Transcript Summarization and Annotation
With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into this wealth of knowledge.
A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding
Users of medical question answering systems often submit long and detailed questions, making it hard to achieve high recall in answer retrieval.
TIMERS: Document-level Temporal Relation Extraction
We present TIMERS - a TIME, Rhetorical and Syntactic-aware model for document-level temporal relation classification in the English language.
DPR at SemEval-2021 Task 8: Dynamic Path Reasoning for Measurement Relation Extraction
To this end, in this paper, we propose a novel model for the task of measurement relation extraction (MRE) whose goal is to recognize the relation between measured entities, quantities, and conditions mentioned in a document.
Unleash GPT-2 Power for Event Detection
To prevent the noises inevitable in automatically generated data from hampering training process, we propose to exploit a teacher-student architecture in which the teacher is supposed to learn anchor knowledge from the original data.
Syntopical Graphs for Computational Argumentation Tasks
Approaches to computational argumentation tasks such as stance detection and aspect detection have largely focused on the text of independent claims, losing out on potentially valuable context provided by the rest of the collection.
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
Also, we observe critical problems of the previous benchmark dataset (i. e., human annotations) on image captioning metric, and introduce a new collection of human annotations on the generated captions.
Learning by Planning: Language-Guided Global Image Editing
Recently, language-guided global image editing draws increasing attention with growing application potentials.
X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering
We extensively evaluate our framework on two challenging cross-lingual NLU tasks: multilingual task-oriented dialog and typologically diverse question answering.
IGA : An Intent-Guided Authoring Assistant
While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored.
A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution
Event coreference resolution is an important research problem with many applications.
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models
These two observations are further employed to formulate a measurement which can quantify the shortcut degree of each training sample.
User Factor Adaptation for User Embedding via Multitask Learning
In this study, we treat the user interest as domains and empirically examine how the user language can vary across the user factor in three English social media datasets.
MadDog: A Web-based System for Acronym Identification and Disambiguation
However, none of the existing works provide a unified solution capable of processing acronyms in various domains and to be publicly available.
Learning to Emphasize: Dataset and Shared Task Models for Selecting Emphasis in Presentation Slides
We evaluate a range of state-of-the-art models on this novel dataset by organizing a shared task and inviting multiple researchers to model emphasis in this new domain.
Acronym Identification and Disambiguation Shared Tasks for Scientific Document Understanding
To push forward research in this direction, we have organized two shared task for acronym identification and acronym disambiguation in scientific documents, named AI@SDU and AD@SDU, respectively.
Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering
Interpretability and explainability of deep neural networks are challenging due to their scale, complexity, and the agreeable notions on which the explaining process rests.
Using Visual Feature Space as a Pivot Across Languages
Our work aims to leverage visual feature space to pass information across languages.
What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation
The proposed model outperforms the state-of-the-art models on the new AD dataset, providing a strong baseline for future research on this dataset.
Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning
In this work, we propose to incorporate the syntactic structures of the sentences into the deep learning models for TOWE, leveraging the syntax-based opinion possibility scores and the syntactic connections between the words.
Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation
In addition, we propose a mechanism to obtain the importance scores for each word in the sentences based on the dependency trees that are then injected into the model to improve the representation vectors for ABSA.
A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion
We present an empirical study in favor of a cascade architecture to neural text summarization.
Learning to Fuse Sentences with Transformers for Summarization
The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts.
Scene Graph Modification Based on Natural Language Commands
In this paper, we explore the novel problem of graph modification, where the systems need to learn how to update an existing scene graph given a new user's command.
A Benchmark and Baseline for Language-Driven Image Editing
To solve this new task, we first present a new language-driven image editing dataset that supports both local and global editing with editing operation and mask annotations.
SemEval-2020 Task 6: Definition extraction from free text with the DEFT corpus
Research on definition extraction has been conducted for well over a decade, largely with significant constraints on the type of definitions considered.
SemEval-2020 Task 10: Emphasis Selection for Written Text in Visual Media
In this paper, we present the main findings and compare the results of SemEval-2020 Task 10, Emphasis Selection for Written Text in Visual Media.
Bayesian Optimization for Selecting Efficient Machine Learning Models
The performance of many machine learning models depends on their hyper-parameter settings.
Exploiting the Syntax-Model Consistency for Neural Relation Extraction
In order to overcome these issues, we propose a novel deep learning model for RE that uses the dependency trees to extract the syntax-based importance scores for the words, serving as a tree representation to introduce syntactic information into the models with greater generalization.
Extensively Matching for Few-shot Learning Event Detection
In this work, weformulate event detection as a few-shot learn-ing problem to enable to extend event detec-tion to new event types.
Understanding Points of Correspondence between Sentences for Abstractive Summarization
We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences.
Open-Domain Question Answering with Pre-Constructed Question Spaces
Our reader-retriever first uses an offline reader to read the corpus and generate collections of all answerable questions associated with their answers, and then uses an online retriever to respond to user queries by searching the pre-constructed question spaces for answers that are most likely to be asked in the given way.
Efficient Deployment of Conversational Natural Language Interfaces over Databases
Many users communicate with chatbots and AI assistants in order to help them with various tasks.
Interaction Matching for Long-Tail Multi-Label Classification
We present an elegant and effective approach for addressing limitations in existing multi-label classification models by incorporating interaction matching, a concept shown to be useful for ad-hoc search result ranking.
Let Me Choose: From Verbal Context to Font Selection
In this paper, we aim to learn associations between visual attributes of fonts and the verbal context of the texts they are typically applied to.
KPQA: A Metric for Generative Question Answering Using Keyphrase Weights
To evaluate our metric, we create high-quality human judgments of correctness on two GenQA datasets.
DSTC8-AVSD: Multimodal Semantic Transformer Network with Retrieval Style Word Generator
Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog.
A Corpus for Detecting High-Context Medical Conditions in Intensive Care Patient Notes Focusing on Frequently Readmitted Patients
In this paper, we introduce a dataset for patient phenotyping, a task that is defined as the identification of whether a patient has a given medical condition (also referred to as clinical indication or phenotype) based on their patient note.
Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition
Existing research on fairness evaluation of document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes.
Exploiting the Matching Information in the Support Set for Few Shot Event Classification
The existing event classification (EC) work primarily focuseson the traditional supervised learning setting in which models are unableto extract event mentions of new/unseen event types.
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation
Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks.
TutorialVQA: Question Answering Dataset for Tutorial Videos
The results indicate that the task is challenging and call for the investigation of new algorithms.
Rethinking Self-Attention: Towards Interpretability in Neural Parsing
Finally, we find that the Label Attention heads learn relations between syntactic categories and show pathways to analyze errors.
Ranked #1 on
Constituency Parsing
on Penn Treebank
A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency
In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies.
Improving Slot Filling by Utilizing Contextual Information
To address this issue, in this paper, we propose a novel method to incorporate the contextual information in two different levels, i. e., representation level and task-specific (i. e., label) level.
Ranked #3 on
Intent Detection
on SNIPS
On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning
Deep learning models have achieved state-of-the-art performances on many relation extraction datasets.
Analyzing Sentence Fusion in Abstractive Summarization
While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences.
Margin Call: an Accessible Web-based Text Viewer with Generated Paragraph Summaries in the Margin
We present Margin Call, a web-based text viewer that automatically generates short summaries for each paragraph of the text and displays the summaries in the margin of the text next to the corresponding paragraph.
Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks
In this study, we propose a novel graph neural network called propagate-selector (PS), which propagates information over sentences to understand information that cannot be inferred when considering sentences in isolation.
Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition
In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework.
DEFT: A corpus for definition extraction in free- and semi-structured text
Definition extraction has been a popular topic in NLP research for well more than a decade, but has been historically limited to well-defined, structured, and narrow conditions.
Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions
In visual communication, text emphasis is used to increase the comprehension of written text to convey the author{'}s intent.
Expressing Visual Relationships via Language
To push forward the research in this direction, we first introduce a new language-guided image editing dataset that contains a large number of real image pairs with corresponding editing instructions.
Scoring Sentence Singletons and Pairs for Abstractive Summarization
There is thus a crucial gap between sentence selection and fusion to support summarizing by both compressing single sentences and fusing pairs.
A Compare-Aggregate Model with Latent Clustering for Answer Selection
In this paper, we propose a novel method for a sentence-level answer-selection task that is a fundamental problem in natural language processing.
Ranked #2 on
Question Answering
on TrecQA
Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation
Titles of short sections within long documents support readers by guiding their focus towards relevant passages and by providing anchor-points that help to understand the progression of the document.
A Web-based Framework for Collecting and Assessing Highlighted Sentences in a Document
Automatically highlighting a text aims at identifying key portions that are the most important to a reader.
MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network
SemEval 2018 Task 7 tasked participants to build a system to classify two entities within a sentence into one of the 6 possible relation types.
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
Neural abstractive summarization models have led to promising results in summarizing relatively short documents.
Ranked #4 on
Unsupervised Extractive Summarization
on Pubmed
Abstractive Text Summarization
Unsupervised Extractive Summarization
PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts
First, the majority of datasets for sequential short-text classification (i. e., classification of short texts that appear in sequences) are small: we hope that releasing a new large dataset will help develop more accurate algorithms for this task.
Transfer Learning for Named-Entity Recognition with Neural Networks
In particular, we demonstrate that transferring an ANN model trained on a large labeled dataset to another dataset with a limited number of labels improves upon the state-of-the-art results on two different datasets for patient note de-identification.
NeuroNER: an easy-to-use program for named-entity recognition based on neural networks
Named-entity recognition (NER) aims at identifying entities of interest in a text.
MIT at SemEval-2017 Task 10: Relation Extraction with Convolutional Neural Networks
Over 50 million scholarly articles have been published: they constitute a unique repository of knowledge.
Comparing Rule-Based and Deep Learning Models for Patient Phenotyping
We assess the performance of deep learning algorithms and compare them with classical NLP approaches.
Neural Networks for Joint Sentence Classification in Medical Paper Abstracts
Existing models based on artificial neural networks (ANNs) for sentence classification often do not incorporate the context in which sentences appear, and classify sentences individually.
Feature-Augmented Neural Networks for Patient Note De-identification
In this work, we explore a method to incorporate human-engineered features as well as features derived from EHRs to a neural-network-based de-identification system.
Optimizing Neural Network Hyperparameters with Gaussian Processes for Dialog Act Classification
Therefore it is a useful technique for tuning ANN models to yield the best performances for natural language processing tasks.
Mapping distributional to model-theoretic semantic spaces: a baseline
Word embeddings have been shown to be useful across state-of-the-art systems in many natural language processing tasks, ranging from question answering systems to dependency parsing.
De-identification of Patient Notes with Recurrent Neural Networks
It yields an F1-score of 97. 85 on the i2b2 2014 dataset, with a recall 97. 38 and a precision of 97. 32, and an F1-score of 99. 23 on the MIMIC de-identification dataset, with a recall 99. 25 and a precision of 99. 06.
Adobe-MIT submission to the DSTC 4 Spoken Language Understanding pilot task
The Dialog State Tracking Challenge 4 (DSTC 4) proposes several pilot tasks.
Robust Dialog State Tracking for Large Ontologies
The Dialog State Tracking Challenge 4 (DSTC 4) differentiates itself from the previous three editions as follows: the number of slot-value pairs present in the ontology is much larger, no spoken language understanding output is given, and utterances are labeled at the subdialog level.
Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks
Recent approaches based on artificial neural networks (ANNs) have shown promising results for short-text classification.
Ranked #10 on
Dialogue Act Classification
on Switchboard corpus
