Search Results for author:
Found 76 papers, 24 papers with code
T3-Vis: visual analytic for Training and fine-Tuning Transformers in NLP
Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging.
KW-ATTN: Knowledge Infused Attention for Accurate and Interpretable Text Classification
Text classification has wide-ranging applications in various domains.
Coreference for Discourse Parsing: A Neural Approach
We present preliminary results on investigating the benefits of coreference resolution features for neural RST discourse parsing by considering different levels of coupling of the discourse parser with the coreference resolver.
Evaluating LLM Reasoning in the Operations Research Domain with ORQA
In this paper, we introduce and apply Operations Research Question Answering (ORQA), a new benchmark designed to assess the generalization capabilities of Large Language Models (LLMs) in the specialized technical domain of Operations Research (OR).
FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering
Multimodal multihop question answering is a complex task that requires reasoning over multiple sources of information, such as images and text, to answer questions.
Captioning Visualizations with Large Language Models (CVLLM): A Tutorial
Automatically captioning visualizations is not new, but recent advances in large language models(LLMs) open exciting new possibilities.
DeTriever: Decoder-representation-based Retriever for Improving NL2SQL In-Context Learning
While in-context Learning (ICL) has proven to be an effective technique to improve the performance of Large Language Models (LLMs) in a variety of complex tasks, notably in translating natural language questions into Structured Query Language (NL2SQL), the question of how to select the most beneficial demonstration examples remains an open research problem.
BCAmirs at SemEval-2024 Task 4: Beyond Words: A Multimodal and Multilingual Exploration of Persuasion in Memes
Memes, combining text and images, frequently use metaphors to convey persuasive messages, shaping public opinion.
Caption Generation
Hierarchical Multi-label Classification
+1
Neural Multimodal Topic Modeling: A Comprehensive Evaluation
This paper presents the first systematic and comprehensive evaluation of multimodal topic modeling of documents containing both text and images.
Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation
Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks.
Tracing Influence at Scale: A Contrastive Learning Approach to Linking Public Comments and Regulator Responses
U. S. Federal Regulators receive over one million comment letters each year from businesses, interest groups, and members of the public, all advocating for changes to proposed regulations.
Visual Analytics for Generative Transformer Models
While transformer-based models have achieved state-of-the-art results in a variety of classification and generation tasks, their black-box nature makes them challenging for interpretability.
Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models
In this work, we propose a method that combines two popular research areas by injecting linguistic structures into pre-trained language models in the parameter-efficient fine-tuning (PEFT) setting.
Diversity-Aware Coherence Loss for Improving Neural Topic Models
The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss.
Personalized Abstractive Summarization by Tri-agent Generation Pipeline
The inference-only large language model (ChatGPT) serves as both the generator and editor, with a smaller model acting as the instructor to guide output generation.
NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions
The Natural Language for Optimization (NL4Opt) Competition was created to investigate methods of extracting the meaning and formulation of an optimization problem based on its text description.
Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues
As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs).
Attend to the Right Context: A Plug-and-Play Module for Content-Controllable Summarization
Content-Controllable Summarization generates summaries focused on the given controlling signals.
Unsupervised Inference of Data-Driven Discourse Structures using a Tree Auto-Encoder
With a growing need for robust and general discourse structures in many downstream tasks and real-world applications, the current lack of high-quality, high-quantity discourse trees poses a severe shortcoming.
Towards Domain-Independent Supervised Discourse Parsing Through Gradient Boosting
Discourse analysis and discourse parsing have shown great impact on many important problems in the field of Natural Language Processing (NLP).
Large Discourse Treebanks from Scalable Distant Supervision
Discourse parsing is an essential upstream task in Natural Language Processing with strong implications for many real-world applications.
Transition to Adulthood for Young People with Intellectual or Developmental Disabilities: Emotion Detection and Topic Modeling
This study is to explore how to use natural language processing (NLP) methods, especially unsupervised machine learning, to assist psychologists to analyze emotions and sentiments and to use topic modeling to identify common issues and challenges that young people with IDD and their families have.
Improving Topic Segmentation by Injecting Discourse Dependencies
Recent neural supervised topic segmentation models achieve distinguished superior effectiveness over unsupervised methods, with the availability of large-scale training corpora sampled from Wikipedia.
Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency
Despite the success of recent abstractive summarizers on automatic evaluation metrics, the generated summaries still present factual inconsistencies with the source document.
Automated Utterance Labeling of Conversations Using Natural Language Processing
Conversational data is essential in psychology because it can help researchers understand individuals cognitive processes, emotions, and behaviors.
Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models
With a growing number of BERTology work analyzing different components of pre-trained language models, we extend this line of research through an in-depth analysis of discourse information in pre-trained and fine-tuned language models.
Predicting Above-Sentence Discourse Structure using Distant Supervision from Topic Segmentation
RST-style discourse parsing plays a vital role in many NLP tasks, revealing the underlying semantic/pragmatic structure of potentially complex and diverse documents.
Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation
The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently.
PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization
We introduce PRIMERA, a pre-trained model for multi-document representation with a focus on summarization that reduces the need for dataset-specific architectures and large amounts of fine-tuning labeled data.
Ranked #1 on
Multi-Document Summarization
on Multi-News
T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP
Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging.
ConVIScope: Visual Analytics for Exploring Patient Conversations
The proliferation of text messaging for mobile health is generating a large amount of patient-doctor conversations that can be extremely valuable to health care professionals.
Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring
Dialogue topic segmentation is critical in several dialogue modeling problems.
W-RST: Towards a Weighted RST-style Discourse Framework
Aiming for a better integration of data-driven and linguistically-inspired approaches, we explore whether RST Nuclearity, assigning a binary assessment of importance between text segments, can be replaced by automatically generated, real-valued scores, in what we call a Weighted-RST framework.
Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning
In news articles the lead bias is a common phenomenon that usually dominates the learning signals for neural extractive summarizers, severely limiting their performance on data with different or even no bias.
Predicting Discourse Trees from Transformer-based Neural Summarizers
Previous work indicates that discourse information benefits summarization.
Unsupervised Learning of Discourse Structures using a Tree Autoencoder
In this paper we are inferring general tree structures of natural text in multiple domains, showing promising results on a diverse set of tasks.
Do We Really Need That Many Parameters In Transformer For Extractive Summarization? Discourse Can Help !
The multi-head self-attention of popular transformer models is widely used within Natural Language Processing (NLP), including for the task of extractive summarization.
Unleashing the Power of Neural Discourse Parsers - A Context and Structure Aware Approach Using Large Scale Pretraining
RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining.
Ranked #18 on
Discourse Parsing
on RST-DT
(Standard Parseval (Span) metric)
Systematically Exploring Redundancy Reduction in Summarizing Long Documents
Our analysis of large summarization datasets indicates that redundancy is a very serious problem when summarizing long documents.
Ranked #16 on
Text Summarization
on Pubmed
Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining
RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining.
Ranked #9 on
Discourse Parsing
on Instructional-DT (Instr-DT)
MEGA RST Discourse Treebanks with Structure and Nuclearity from Scalable Distant Sentiment Supervision
The lack of large and diverse discourse treebanks hinders the application of data-driven approaches, such as deep-learning, to RST-style discourse parsing.
From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation
Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistics structures.
An Improved Attention for Visual Question Answering
We also propose multimodal fusion module to combine both visual and textual information.
Towards Domain-Independent Text Structuring Trainable on Large Discourse Treebanks
With the goal of fostering more general and data-driven approaches to text structuring, we propose the new and domain-independent NLG task of structuring and ordering a (possibly large) set of EDUs.
Improving Context Modeling in Neural Topic Segmentation
Topic segmentation is critical in key NLP tasks and recent works favor highly effective neural supervised approaches.
Neural RST-based Evaluation of Discourse Coherence
We evaluate our approach on the Grammarly Corpus for Discourse Coherence (GCDC) and show that when ensembled with the current state of the art, we can achieve the new state of the art accuracy on this benchmark.
Ranked #1 on
Coherence Evaluation
on GCDC + RST - F1
Exploratory Analysis of COVID-19 Related Tweets in North America to Inform Public Health Institutes
We also examine people's sentiment about COVID-19 related issues.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Comparing the Intrinsic Performance of Clinical Concept Embeddings by Their Field of Medicine
Pre-trained word embeddings are becoming increasingly popular for natural language processing tasks.
Predicting Discourse Structure using Distant Supervision from Sentiment
Results indicate that while our parser does not yet match the performance of a parser trained and tested on the same dataset (intra-domain), it does perform remarkably well on the much more difficult and arguably more useful task of inter-domain discourse structure prediction, where the parser is trained on one domain and tested/applied on another one.
Extractive Summarization of Long Documents by Combining Global and Local Context
In this paper, we propose a novel neural single document extractive summarization model for long documents, incorporating both the global context of the whole document and the local context within the current topic.
Ranked #20 on
Text Summarization
on Arxiv HEP-TH citation graph
Evaluating Topic Quality with Posterior Variability
Probabilistic topic models such as latent Dirichlet allocation (LDA) are popularly used with Bayesian inference methods such as Gibbs sampling to learn posterior distributions over topic model parameters.
Discourse Analysis and Its Applications
Discourse processing is a suite of Natural Language Processing (NLP) tasks to uncover linguistic structures from texts at several levels, which can support many downstream applications.
Chat Disentanglement: Identifying Semantic Reply Relationships with Random Forests and Recurrent Neural Networks
Thread disentanglement is a precursor to any high-level analysis of multiparticipant chats.
Automatic Community Creation for Abstractive Spoken Conversations Summarization
Summarization of spoken conversations is a challenging task, since it requires deep understanding of dialogs.
Multimedia Summary Generation from Online Conversations: Current Approaches and Future Directions
With the proliferation of Web-based social media, asynchronous conversations have become very common for supporting online communication and collaboration.
Exploring Joint Neural Model for Sentence Level Discourse Parsing and Sentiment Analysis
Discourse Parsing and Sentiment Analysis are two fundamental tasks in Natural Language Processing that have been shown to be mutually beneficial.
Ranked #26 on
Sentiment Analysis
on SST-5 Fine-grained classification
Detecting Dementia through Retrospective Analysis of Routine Blog Posts by Bloggers with Dementia
We investigate if writers with dementia can be automatically distinguished from those without by analyzing linguistic markers in written text, in the form of blog posts.
Generating and Evaluating Summaries for Partial Email Threads: Conversational Bayesian Surprise and Silver Standards
We define and motivate the problem of summarizing partial email threads.
Training Data Enrichment for Infrequent Discourse Relations
We propose a training data enrichment framework that relies on co-training of two different discourse parsers on unlabeled documents.
An Interactive System for Exploring Community Question Answering Forums
We present an interactive system to provide effective and efficient search capabilities in Community Question Answering (cQA) forums.
CODRA: A Novel Discriminative Framework for Rhetorical Analysis
Ranked #8 on
Discourse Parsing
on RST-DT
(RST-Parseval (Span) metric)
Topic Segmentation and Labeling in Asynchronous Conversations
Topic segmentation and labeling is often considered a prerequisite for higher-level conversation analysis and has been shown to be useful in many Natural Language Processing (NLP) applications.
A Publicly Available Annotated Corpus for Supervised Email Summarization
Annotated email corpora are necessary for evaluation and training of machine learning summarization techniques.
