Search Results for author:
Found 108 papers, 33 papers with code
GenerativeRE: Incorporating a Novel Copy Mechanism and Pretrained Model for Joint Entity and Relation Extraction
During the training stage, GenerativeRE fine-tunes the pre-trained generative model and learns the special entity labels simultaneously.
Text Classification and Prediction in the Legal Domain
We present a case study on the application of text classification and legal judgment prediction for flight compensation.
GenCompareSum: a hybrid unsupervised summarization method using salience
To this end, we propose a hybrid, unsupervised, abstractive-extractive approach, in which we walk through a document, generating salient textual fragments representing its key points.
Ranked #1 on
Text Summarization
on S2ORC
RELATE: Generating a linguistically inspired Knowledge Graph for fine-grained emotion classification
These resources are either large, common-sense knowledge graphs (KG) that cover a limited amount of polarities/emotions or they are smaller in size (e. g.: lexicons), which require costly human annotation and cover fine-grained emotions.
Named Entity Recognition for Cancer Immunology Research Using Distant Supervision
Cancer immunology research involves several important cell and protein factors.
Incorporating Zoning Information into Argument Mining from Biomedical Literature
Argumentative zoning, a specific text zoning scheme for the scientific domain, is considered as the antecedent for argument mining by many researchers.
Simple is not Enough: Document-level Text Simplification using Readability and Coherence
In the past decade, the progress of the Text Simplification (TS) field has been mostly shown at a sentence level, rather than considering paragraphs or documents, a setting from which most TS audiences would benefit.
Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
Understanding the mechanisms behind Large Language Models (LLMs) is crucial for designing improved models and strategies.
FMDLlama: Financial Misinformation Detection based on Large Language Models
The emergence of social media has made the spread of misinformation easier.
Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
We find arithmetic ability resides within a limited number of attention heads, with each head specializing in distinct operations.
Selective Preference Optimization via Token-Level Reward Function Estimation
This method applies to any existing alignment datasets with response-level annotations and enables cost-efficient token selection with small-scale oracle models and training data.
Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
We begin with FinLLaMA, pre-trained on a 52 billion token financial corpus, incorporating text, tables, and time-series data to embed comprehensive financial knowledge.
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
In this paper, we take a step forward to explore LLMs for tabular data synthesis and privacy protection, by introducing a new framework HARMONIC for tabular data generation and evaluation.
Are Large Language Models True Healthcare Jacks-of-All-Trades? Benchmarking Across Health Professions Beyond Physician Exams
To fill this research gap, we introduce the Examinations for Medical Personnel in Chinese (EMPEC), a pioneering large-scale healthcare knowledge benchmark in traditional Chinese.
RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning based on Emotional Information
Misinformation is prevalent in various fields such as education, politics, health, etc., causing significant harm to society.
MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
MetaAligner models multi-objective alignment into three stages: (1) dynamic objectives reformulation algorithm reorganizes traditional alignment datasets to supervise the model on performing flexible alignment across different objectives; (2) conditional weak-to-strong correction paradigm aligns the weak outputs of fixed policy models to approach strong outputs with higher preferences in the corresponding alignment objectives, enabling plug-and-play inferences on any policy models, which significantly reduces training costs and facilitates alignment on close-source policy models; (3) generalizable inference method flexibly adjusts target objectives by updating their text descriptions in the prompts, facilitating generalizable alignment to unseen objectives.
ConspEmoLLM: Conspiracy Theory Detection Using an Emotion-Based Large Language Model
Driven by a comprehensive analysis of conspiracy text that reveals its distinctive affective features, we propose ConspEmoLLM, the first open-source LLM that integrates affective information and is able to perform diverse tasks relating to conspiracy theories.
No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks
While the progression of Large Language Models (LLMs) has notably propelled financial analysis, their application has largely been confined to singular language realms, leaving untapped the potential of bilingual Chinese-English capacity.
Factual Consistency Evaluation of Summarisation in the Era of Large Language Models
Experiments on TreatFact suggest that both previous methods and LLM-based evaluators are unable to capture factual inconsistencies in clinical summaries, posing a new challenge for FC evaluation.
The Lay Person's Guide to Biomedicine: Orchestrating Large Language Models
Moreover, automated methods that can effectively assess the `layness' of generated summaries are lacking.
FinBen: A Holistic Financial Benchmark for Large Language Models
Our evaluation of 15 representative LLMs, including GPT-4, ChatGPT, and the latest Gemini, reveals several key findings: While LLMs excel in IE and textual analysis, they struggle with advanced reasoning and complex tasks like text generation and forecasting.
Dólares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and English
We evaluate our model and existing LLMs using FLARE-ES, the first comprehensive bilingual evaluation benchmark with 21 datasets covering 9 tasks.
How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning
We investigate the mechanism of in-context learning (ICL) on sentence classification tasks with semantically-unrelated labels ("foo"/"bar").
EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis
In this paper, we propose EmoLLMs, the first series of open-sourced instruction-following LLMs for comprehensive affective analysis based on fine-tuning various LLMs with instruction data, the first multi-task affective analysis instruction dataset (AAID) with 234K data samples based on various classification and regression tasks to support LLM instruction tuning, and a comprehensive affective evaluation benchmark (AEB) with 14 tasks from various sources and domains to test the generalization ability of LLMs.
Large Language Models in Mental Health Care: a Scoping Review
There is a need to systematically review the application outcomes and delineate the advantages and limitations in clinical settings.
Neuron-Level Knowledge Attribution in Large Language Models
Additionally, since most static methods typically only identify "value neurons" directly contributing to the final prediction, we propose a method for identifying "query neurons" which activate these "value neurons".
Rethinking Large Language Models in Mental Health Applications
Large Language Models (LLMs) have become valuable assets in mental health, showing promise in both classification tasks and counseling applications.
Emotion Detection for Misinformation: A Review
The emotions and sentiments of netizens, as expressed in social media posts and news, constitute important factors that can help to distinguish fake news from genuine news and to understand the spread of rumors.
Back to the Future: Towards Explainable Temporal Reasoning with Large Language Models
In this paper, we introduce the first task of explainable temporal reasoning, to predict an event's occurrence at a future timestamp based on context which requires multiple reasoning over multiple events, and subsequently provide a clear explanation for their prediction.
Overview of the BioLaySumm 2023 Shared Task on Lay Summarization of Biomedical Research Articles
This paper presents the results of the shared task on Lay Summarisation of Biomedical Research Articles (BioLaySumm), hosted at the BioNLP Workshop at ACL 2023.
MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models
The raw social media data are collected from 10 existing sources covering 8 mental health analysis tasks.
LongDocFACTScore: Evaluating the Factuality of Long Document Abstractive Summarisation
We create a human-annotated data set for evaluating automatic factuality metrics, LongSciVerify, which contains fine-grained factual consistency annotations for long document summaries from the scientific domain.
A Bipartite Graph is All We Need for Enhancing Emotional Reasoning with Commonsense Knowledge
However, most previous knowledge infusion methods perform empirical knowledge filtering and design highly customized architectures for knowledge interaction with the utterances, which can discard useful knowledge aspects and limit their generalizability to different knowledge sources.
Graph Contrastive Topic Model
Based on it, we propose the graph contrastive topic model (GCTM), which conducts graph contrastive learning (GCL) using informative positive and negative samples that are generated by the graph-based sampling strategy leveraging in-depth correlation and irrelevance among documents and words.
Disentangled Variational Autoencoder for Emotion Recognition in Conversations
We also enhance the disentangled representations by introducing VAD supervision signals from a sentiment lexicon and minimising the mutual information between VAD distributions.
Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health
In the mental health domain, domain-specific language models are pretrained and released, which facilitates the early detection of mental health conditions.
Emotion fusion for mental illness detection from social media: A survey
In this article, we provide a comprehensive survey of approaches to mental illness detection in social media that incorporate emotion fusion.
A Survey for Biomedical Text Summarization: From Pre-trained to Large Language Models
In this paper, we present a systematic review of recent advancements in BTS, leveraging cutting-edge NLP techniques from PLMs to LLMs, to help understand the latest progress, challenges, and future directions.
Zero-shot Temporal Relation Extraction with ChatGPT
The current shortcomings of ChatGPT on temporal relation extraction are also discussed in this paper.
Towards Interpretable Mental Health Analysis with Large Language Models
The latest large language models (LLMs) such as ChatGPT, exhibit strong capabilities in automated mental health analysis.
ChatGPT as a Factual Inconsistency Evaluator for Text Summarization
In this paper, we particularly explore ChatGPT's ability to evaluate factual inconsistency under a zero-shot setting by examining it on both coarse-grained and fine-grained evaluation tasks including binary entailment inference, summary ranking, and consistency rating.
Abstractive Text Summarization
Natural Language Inference
+3
Span-based Named Entity Recognition by Generating and Compressing Information
For one type of IB model, we incorporate two unsupervised generative components, span reconstruction and synonym generation, into a span-based NER system.
Cluster-Level Contrastive Learning for Emotion Recognition in Conversations
To address these issues, we propose a novel low-dimensional Supervised Cluster-level Contrastive Learning (SCCL) method, which first reduces the high-dimensional SCL space to a three-dimensional affect representation space Valence-Arousal-Dominance (VAD), then performs cluster-level contrastive learning to incorporate measurable emotion prototypes.
CitationSum: Citation-aware Graph Contrastive Learning for Scientific Paper Summarization
To fill that gap, we propose a novel citation-aware scientific paper summarization framework based on citation graphs, able to accurately locate and incorporate the salient contents from references, as well as capture varying relevance between source papers and their references.
Readability Controllable Biomedical Document Summarization
Different from general documents, it is recognised that the ease with which people can understand a biomedical text is eminently varied, owing to the highly technical nature of biomedical documents and the variance of readers' domain knowledge.
GRETEL: Graph Contrastive Topic Enhanced Language Model for Long Document Extractive Summarization
Recently, neural topic models (NTMs) have been incorporated into pre-trained language models (PLMs), to capture the global semantic information for text summarization.
Ranked #10 on
Text Summarization
on Pubmed
Learning Disentangled Representations of Negation and Uncertainty
Negation and uncertainty modeling are long-standing tasks in natural language processing.
Transformer for Graphs: An Overview from Architecture Perspective
In this survey, we provide a comprehensive review of various Graph Transformer models from the architectural design perspective.
Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer
Although these methods have made great progress, they are often limited by the recommender system's direct exposure and inactive interactions, and thus fail to mine all potential user interests.
Investigating Text Simplification Evaluation
Modern text simplification (TS) heavily relies on the availability of gold standard data to build machine learning models.
One-shot to Weakly-Supervised Relation Classification using Language Models
Unfortunately, both annotation methodologies are costly and time-consuming since they depend on intensive human labour for annotation or for knowledge base creation.
EPICURE Ensemble Pretrained Models for Extracting Cancer Mutations from Literature
To interpret the genetic profile present in a patient sample, it is necessary to know which mutations have important roles in the development of the corresponding cancer type.
Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors
We propose a multi-task, probabilistic approach to facilitate distantly supervised relation extraction by bringing closer the representations of sentences that contain the same Knowledge Base pairs.
Ranked #4 on
Relation Extraction
on NYT Corpus
Paladin: an annotation tool based on active and proactive learning
In this paper, we present Paladin, an open-source web-based annotation tool for creating high-quality multi-label document-level datasets.
HSEarch: semantic search system for workplace accident reports
Semantic search engines, which integrate the output of text mining (TM) methods, can significantly increase the ease and efficiency of finding relevant documents and locating important information within them.
SpanEmo: Casting Multi-label Emotion Classification as Span-prediction
We propose a new model "SpanEmo" casting multi-label emotion classification as span-prediction, which can aid ER models to learn associations between labels and words in a sentence.
Ranked #1 on
Emotion Classification
on SemEval 2018 Task 1E-c
A Neural Model for Aggregating Coreference Annotation in Crowdsourcing
To ensure high-quality data, it is crucial to infer the correct labels by aggregating the noisy labels.
DeepEventMine: end-to-end neural nested event extraction from biomedical texts
Motivation Recent neural approaches on event extraction from text mainly focus on flat events in general domain, while there are less attempts to detect nested and overlapping events.
Ranked #1 on
Event Extraction
on GENIA 2013
Semantic Annotation for Improved Safety in Construction Work
In response, we have designed a novel named entity annotation scheme and associated guidelines for this domain, which covers hazards, consequences, mitigation strategies and project attributes.
Revisiting Unsupervised Relation Extraction
Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs).
Coreference Resolution in Full Text Articles with BERT and Syntax-based Mention Filtering
Additionally, the proposed model is able to detect coreferent pairs in long distances, even with a distance of more than 200 sentences.
A Search-based Neural Model for Biomedical Nested and Overlapping Event Detection
We tackle the nested and overlapping event detection task and propose a novel search-based neural network (SBNN) structured prediction model that treats the task as a search problem on a relation graph of trigger-argument structures.
Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs
We thus propose an edge-oriented graph neural model for document-level relation extraction.
Improving classification of Adverse Drug Reactions through Using Sentiment Analysis and Transfer Learning
The availability of large-scale and real-time data on social media has motivated research into adverse drug reactions (ADRs).
Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network
Inter-sentence relation extraction deals with a number of complex semantic relationships in documents, which require local, non-local, syntactic and semantic dependencies.
Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks
It can automatically estimate the per-instance reliability of each annotator and the correct label for each instance.
A Walk-based Model on Entity Graphs for Relation Extraction
We present a novel graph-based neural network model for relation extraction.
Ranked #1 on
Relation Extraction
on ACE 2005
(Cross Sentence metric)
APLenty: annotation tool for creating high-quality datasets using active and proactive learning
In this paper, we present APLenty, an annotation tool for creating high-quality sequence labeling datasets using active and proactive learning.
Investigating Domain-Specific Information for Neural Coreference Resolution on Biomedical Texts
Existing biomedical coreference resolution systems depend on features and/or rules based on syntactic parsers.
Paths for uncertainty: Exploring the intricacies of uncertainty identification for news
We compare the differences in the definition and expression of uncertainty between a scientific domain, i. e., biomedicine, and newswire.
A Neural Layered Model for Nested Named Entity Recognition
Each flat NER layer is based on the state-of-the-art flat NER model that captures sequential context representation with bidirectional Long Short-Term Memory (LSTM) layer and feeds it to the cascaded CRF layer.
Ranked #10 on
Nested Mention Recognition
on ACE 2005
Proactive Learning for Named Entity Recognition
The goal of active learning is to minimise the cost of producing an annotated dataset, in which annotators are assumed to be perfect, i. e., they always choose the correct labels.
Distributed Document and Phrase Co-embeddings for Descriptive Clustering
Descriptive document clustering aims to automatically discover groups of semantically related documents and to assign a meaningful label to characterise the content of each cluster.
Learning to recognise named entities in tweets by exploiting weakly labelled data
Named entity recognition (NER) in social media (e. g., Twitter) is a challenging task due to the noisy nature of text.
Identifying Content Types of Messages Related to Open Source Software Projects
Assessing the suitability of an Open Source Software project for adoption requires not only an analysis of aspects related to the code, such as code quality, frequency of updates and new version releases, but also an evaluation of the quality of support offered in related online forums and issue trackers.
Ensemble Classification of Grants using LDA-based Features
Classifying research grants into useful categories is a vital task for a funding body to give structure to the portfolio for analysis, informing strategic planning and decision-making.
Interoperability and Customisation of Annotation Schemata in Argo
Argo aids the development of custom annotation schemata and supports their interoperability by featuring a schema editor and specialised analytics for schemata alignment.
The Meta-knowledge of Causality in Biomedical Scientific Discourse
Causality lies at the heart of biomedical knowledge, being involved in diagnosis, pathology or systems biology.
Locating Requests among Open Source Software Communication Messages
As a first step towards assessing the quality of support offered online for Open Source Software (OSS), we address the task of locating requests, i. e., messages that raise an issue to be addressed by the OSS community, as opposed to any other message.
The Strategic Impact of META-NET on the Regional, National and International Level
This article provides an overview of the dissemination work carried out in META-NET from 2010 until early 2014; we describe its impact on the regional, national and international level, mainly with regard to politics and the situation of funding for LT topics.
Identification of Manner in Bio-Events
Until recently, these corpora, and hence the event extraction systems trained on them, focussed almost exclusively on the identification and classification of event arguments, without taking into account how the textual context of the events could affect their interpretation.
A data and analysis resource for an experiment in text mining a collection of micro-blogs on a political topic.
The analysis of a corpus of micro-blogs on the topic of the 2011 UK referendum about the Alternative Vote has been undertaken as a joint activity by text miners and social scientists.
Biomedical Chinese-English CLIR Using an Extended CMeSH Resource to Expand Queries
All experiments compare the use of two different retrieval models, i. e. Okapi BM25 and a query likelihood language model.
Collaborative Development and Evaluation of Text-processing Workflows in a UIMA-supported Web-based Workbench
Challenges in creating comprehensive text-processing worklows include a lack of the interoperability of individual components coming from different providers and/or a requirement imposed on the end users to know programming techniques to compose such workflows.
