Search Results for author: Giuseppe Carenini

Found 70 papers, 21 papers with code

Coreference for Discourse Parsing: A Neural Approach

no code implementations EMNLP (CODI) 2020 Grigorii Guz, Giuseppe Carenini

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.

coreference-resolution Discourse Parsing

T3-Vis: visual analytic for Training and fine-Tuning Transformers in NLP

1 code implementation EMNLP (ACL) 2021 Raymond Li, Wen Xiao, Lanjun Wang, Hyeju Jang, Giuseppe Carenini

Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging.

Neural Multimodal Topic Modeling: A Comprehensive Evaluation

1 code implementation26 Mar 2024 Felipe González-Pizarro, Giuseppe Carenini

This paper presents the first systematic and comprehensive evaluation of multimodal topic modeling of documents containing both text and images.

Topic Models

Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation

no code implementations30 Nov 2023 Linzi Xing, Quan Tran, Fabian Caba, Franck Dernoncourt, Seunghyun Yoon, Zhaowen Wang, Trung Bui, Giuseppe Carenini

Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks.

Contrastive Learning Segmentation +2

Tracing Influence at Scale: A Contrastive Learning Approach to Linking Public Comments and Regulator Responses

no code implementations24 Nov 2023 Linzi Xing, Brad Hackinen, Giuseppe Carenini

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.

Contrastive Learning Language Modelling +1

Visual Analytics for Generative Transformer Models

no code implementations21 Nov 2023 Raymond Li, Ruixin Yang, Wen Xiao, Ahmed Aburaed, Gabriel Murray, Giuseppe Carenini

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

no code implementations24 Oct 2023 Raymond Li, Gabriel Murray, Giuseppe Carenini

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

1 code implementation25 May 2023 Raymond Li, Felipe González-Pizarro, Linzi Xing, Gabriel Murray, Giuseppe Carenini

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.

Topic Models

Personalized Abstractive Summarization by Tri-agent Generation Pipeline

1 code implementation4 May 2023 Wen Xiao, Yujia Xie, Giuseppe Carenini, Pengcheng He

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.

Abstractive Text Summarization Language Modelling +1

NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions

1 code implementation14 Mar 2023 Rindranirina Ramamonjison, Timothy T. Yu, Raymond Li, Haley Li, Giuseppe Carenini, Bissan Ghaddar, Shiqi He, Mahdi Mostajabdaveh, Amin Banitalebi-Dehkordi, Zirui Zhou, Yong Zhang

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.

Language Modelling Large Language Model

Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues

no code implementations12 Feb 2023 Chuyuan Li, Patrick Huber, Wen Xiao, Maxime Amblard, Chloé Braud, Giuseppe Carenini

As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs).

Sentence Sentence Ordering

Attend to the Right Context: A Plug-and-Play Module for Content-Controllable Summarization

1 code implementation21 Dec 2022 Wen Xiao, Lesly Miculicich, Yang Liu, Pengcheng He, Giuseppe Carenini

Content-Controllable Summarization generates summaries focused on the given controlling signals.

Large Discourse Treebanks from Scalable Distant Supervision

no code implementations18 Oct 2022 Patrick Huber, Giuseppe Carenini

Discourse parsing is an essential upstream task in Natural Language Processing with strong implications for many real-world applications.

Discourse Parsing Sentiment Analysis

Towards Domain-Independent Supervised Discourse Parsing Through Gradient Boosting

no code implementations18 Oct 2022 Patrick Huber, Giuseppe Carenini

Discourse analysis and discourse parsing have shown great impact on many important problems in the field of Natural Language Processing (NLP).

Discourse Parsing Domain Adaptation

Unsupervised Inference of Data-Driven Discourse Structures using a Tree Auto-Encoder

no code implementations18 Oct 2022 Patrick Huber, Giuseppe Carenini

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.

Discourse Parsing

Transition to Adulthood for Young People with Intellectual or Developmental Disabilities: Emotion Detection and Topic Modeling

1 code implementation21 Sep 2022 Yan Liu, Maria Laricheva, Chiyu Zhang, Patrick Boutet, GuanYu Chen, Terence Tracey, Giuseppe Carenini, Richard Young

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

no code implementations COLING (CODI, CRAC) 2022 Linzi Xing, Patrick Huber, Giuseppe Carenini

Recent neural supervised topic segmentation models achieve distinguished superior effectiveness over unsupervised methods, with the availability of large-scale training corpora sampled from Wikipedia.

Segmentation Sentence

Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency

1 code implementation7 Sep 2022 Wen Xiao, Giuseppe Carenini

Despite the success of recent abstractive summarizers on automatic evaluation metrics, the generated summaries still present factual inconsistencies with the source document.

Abstractive Text Summarization

Automated Utterance Labeling of Conversations Using Natural Language Processing

1 code implementation12 Aug 2022 Maria Laricheva, Chiyu Zhang, Yan Liu, GuanYu Chen, Terence Tracey, Richard Young, Giuseppe Carenini

Conversational data is essential in psychology because it can help researchers understand individuals cognitive processes, emotions, and behaviors.

Domain Adaptation

Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models

no code implementations NAACL 2022 Patrick Huber, Giuseppe Carenini

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

no code implementations12 Dec 2021 Patrick Huber, Linzi Xing, Giuseppe Carenini

RST-style discourse parsing plays a vital role in many NLP tasks, revealing the underlying semantic/pragmatic structure of potentially complex and diverse documents.

Discourse Parsing Sentence +1

PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization

2 code implementations ACL 2022 Wen Xiao, Iz Beltagy, Giuseppe Carenini, Arman Cohan

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.

Abstractive Text Summarization Document Summarization +2

T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP

1 code implementation31 Aug 2021 Raymond Li, Wen Xiao, Lanjun Wang, Hyeju Jang, Giuseppe Carenini

Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging.

ConVIScope: Visual Analytics for Exploring Patient Conversations

no code implementations30 Aug 2021 Raymond Li, Enamul Hoque, Giuseppe Carenini, Richard Lester, Raymond Chau

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.

W-RST: Towards a Weighted RST-style Discourse Framework

no code implementations ACL 2021 Patrick Huber, Wen Xiao, Giuseppe Carenini

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

no code implementations ACL 2021 Linzi Xing, Wen Xiao, Giuseppe Carenini

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.

News Summarization

Unsupervised Learning of Discourse Structures using a Tree Autoencoder

no code implementations17 Dec 2020 Patrick Huber, Giuseppe Carenini

In this paper we are inferring general tree structures of natural text in multiple domains, showing promising results on a diverse set of tasks.

Discourse Parsing

Do We Really Need That Many Parameters In Transformer For Extractive Summarization? Discourse Can Help !

no code implementations EMNLP (CODI) 2020 Wen Xiao, Patrick Huber, Giuseppe Carenini

The multi-head self-attention of popular transformer models is widely used within Natural Language Processing (NLP), including for the task of extractive summarization.

Extractive Summarization Sentence

Unleashing the Power of Neural Discourse Parsers - A Context and Structure Aware Approach Using Large Scale Pretraining

no code implementations COLING 2020 Grigorii Guz, Patrick Huber, Giuseppe Carenini

RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining.

Ranked #10 on Discourse Parsing on RST-DT (Standard Parseval (Span) metric)

Discourse Parsing Machine Translation +2

Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining

no code implementations6 Nov 2020 Grigorii Guz, Patrick Huber, Giuseppe Carenini

RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining.

Ranked #8 on Discourse Parsing on RST-DT (Standard Parseval (Span) metric)

Discourse Parsing Machine Translation +2

MEGA RST Discourse Treebanks with Structure and Nuclearity from Scalable Distant Sentiment Supervision

1 code implementation EMNLP 2020 Patrick Huber, Giuseppe Carenini

The lack of large and diverse discourse treebanks hinders the application of data-driven approaches, such as deep-learning, to RST-style discourse parsing.

Discourse Parsing

From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation

no code implementations COLING 2020 Patrick Huber, Giuseppe Carenini

Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistics structures.

Sentiment Analysis

Towards Domain-Independent Text Structuring Trainable on Large Discourse Treebanks

no code implementations DT4TP 2020 Grigorii Guz, Giuseppe Carenini

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.

Neural RST-based Evaluation of Discourse Coherence

1 code implementation Asian Chapter of the Association for Computational Linguistics 2020 Grigorii Guz, Peyman Bateni, Darius Muglich, Giuseppe Carenini

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.

Coherence Evaluation Discourse Parsing +2

Predicting Discourse Structure using Distant Supervision from Sentiment

no code implementations IJCNLP 2019 Patrick Huber, Giuseppe Carenini

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.

Discourse Parsing Multiple Instance Learning +2

Extractive Summarization of Long Documents by Combining Global and Local Context

1 code implementation IJCNLP 2019 Wen Xiao, Giuseppe Carenini

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.

Extractive Summarization Text Summarization

Evaluating Topic Quality with Posterior Variability

1 code implementation IJCNLP 2019 Linzi Xing, Michael J. Paul, Giuseppe Carenini

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.

Bayesian Inference Topic Models

Discourse Analysis and Its Applications

no code implementations ACL 2019 Shafiq Joty, Giuseppe Carenini, Raymond Ng, Gabriel Murray

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.

Machine Translation Question Answering +3

Multimedia Summary Generation from Online Conversations: Current Approaches and Future Directions

no code implementations WS 2017 Enamul Hoque, Giuseppe Carenini

With the proliferation of Web-based social media, asynchronous conversations have become very common for supporting online communication and collaboration.

Community Question Answering

Detecting Dementia through Retrospective Analysis of Routine Blog Posts by Bloggers with Dementia

1 code implementation WS 2017 Vaden Masrani, Gabriel Murray, Thalia Field, Giuseppe Carenini

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.

BIG-bench Machine Learning

Training Data Enrichment for Infrequent Discourse Relations

no code implementations COLING 2016 Kailang Jiang, Giuseppe Carenini, Raymond Ng

We propose a training data enrichment framework that relies on co-training of two different discourse parsers on unlabeled documents.

Discourse Parsing Relation +1

Topic Segmentation and Labeling in Asynchronous Conversations

no code implementations4 Feb 2014 Shafiq Rayhan Joty, Giuseppe Carenini, Raymond T. Ng

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.

Segmentation

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