Search Results for author:
Found 52 papers, 11 papers with code
Rare-Class Dialogue Act Tagging for Alzheimer’s Disease Diagnosis
Alzheimer’s Disease (AD) is associated with many characteristic changes, not only in an individual’s language but also in the interactive patterns observed in dialogue.
Zero-shot Cross-lingual Content Filtering: Offensive Language and Hate Speech Detection
We present a system for zero-shot cross-lingual offensive language and hate speech classification.
Communicative Grounding of Analogical Explanations in Dialogue: A Corpus Study of Conversational Management Acts and Statistical Sequence Models for Tutoring through Analogy
We annotate a corpus of analogical episodes with the schema and develop statistical sequence models from the corpus which predict tutor content related decisions, in terms of the selection of the analogical component (AC) and tutor conversational management act (TCMA) to deploy at the current utterance, given the student’s behaviour.
Mitigating Topic Bias when Detecting Decisions in Dialogue
This work revisits the task of detecting decision-related utterances in multi-party dialogue.
EMBEDDIA Tools, Datasets and Challenges: Resources and Hackathon Contributions
This paper presents tools and data sources collected and released by the EMBEDDIA project, supported by the European Union’s Horizon 2020 research and innovation program.
JSI at SemEval-2022 Task 1: CODWOE - Reverse Dictionary: Monolingual and cross-lingual approaches
The reverse dictionary task is a sequence-to-vector task in which a gloss is provided as input, and the output must be a semantically matching word vector.
Tracking Changes in ESG Representation: Initial Investigations in UK Annual Reports
We describe initial work into analysing the language used around environmental, social and governance (ESG) issues in UK company annual reports.
Scaling for Fairness? Analyzing Model Size, Data Composition, and Multilinguality in Vision-Language Bias
As large-scale vision-language models (VLMs) become increasingly central to modern AI applications, understanding and mitigating social biases in these systems has never been more critical. We investigate how dataset composition, model size, and multilingual training affect gender and racial bias in a popular VLM, CLIP, and its open-source variants.
Recent Trends in Linear Text Segmentation: a Survey
In this survey, we provide an extensive overview of current advances in linear text segmentation, describing the state of the art in terms of resources and approaches for the task.
Evaluating and explaining training strategies for zero-shot cross-lingual news sentiment analysis
We investigate zero-shot cross-lingual news sentiment detection, aiming to develop robust sentiment classifiers that can be deployed across multiple languages without target-language training data.
ClarQ-LLM: A Benchmark for Models Clarifying and Requesting Information in Task-Oriented Dialog
The benchmark includes 31 different task types, each with 10 unique dialogue scenarios between information seeker and provider agents.
Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly
Large Language Models (LLMs) have demonstrated remarkable capabilities in comprehending and analyzing lengthy sequential inputs, owing to their extensive context windows that allow processing millions of tokens in a single forward pass.
Multimodal Machine Learning in Mental Health: A Survey of Data, Algorithms, and Challenges
The application of machine learning (ML) in detecting, diagnosing, and treating mental health disorders is garnering increasing attention.
FairCoT: Enhancing Fairness in Diffusion Models via Chain of Thought Reasoning of Multimodal Language Models
In the domain of text-to-image generative models, biases inherent in training datasets often propagate into generated content, posing significant ethical challenges, particularly in socially sensitive contexts.
A Computational Analysis of the Dehumanisation of Migrants from Syria and Ukraine in Slovene News Media
Dehumanisation involves the perception and or treatment of a social group's members as less than human.
Reformulating NLP tasks to Capture Longitudinal Manifestation of Language Disorders in People with Dementia
Here, we automatically learn linguistic disorder patterns by making use of a moderately-sized pre-trained language model and forcing it to focus on reformulated natural language processing (NLP) tasks and associated linguistic patterns.
Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
We study the influence of different activation functions in the output layer of deep neural network models for soft and hard label prediction in the learning with disagreement task.
CoRAL: a Context-aware Croatian Abusive Language Dataset
In light of unprecedented increases in the popularity of the internet and social media, comment moderation has never been a more relevant task.
Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment
To deal with this problem, we modify a number of state-of-the-art models to train on the segmented data of Spider-SS, and we show that this method improves the generalization performance.
Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model
Moderation of reader comments is a significant problem for online news platforms.
Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization
Recently, there has been significant progress in studying neural networks for translating text descriptions into SQL queries under the zero-shot cross-domain setting.
Natural SQL: Making SQL Easier to Infer from Natural Language Specifications
Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation.
A Longitudinal Multi-modal Dataset for Dementia Monitoring and Diagnosis
The corpus consists of spoken conversations, a subset of which are transcribed, as well as typed and written thoughts and associated extra-linguistic information such as pen strokes and keystrokes.
Evaluation of contextual embeddings on less-resourced languages
The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives.
Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputs
We present two multimodal fusion-based deep learning models that consume ASR transcribed speech and acoustic data simultaneously to classify whether a speaker in a structured diagnostic task has Alzheimer's Disease and to what degree, evaluating the ADReSSo challenge 2021 data.
Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's Dementia recognition from spontaneous speech
This paper is a submission to the Alzheimer's Dementia Recognition through Spontaneous Speech (ADReSS) challenge, which aims to develop methods that can assist in the automated prediction of severity of Alzheimer's Disease from speech data.
Towards Robustness of Text-to-SQL Models against Synonym Substitution
We observe that the accuracy dramatically drops by eliminating such explicit correspondence between NL questions and table schemas, even if the synonyms are not adversarially selected to conduct worst-case adversarial attacks.
SemEval-2020 Task 3: Graded Word Similarity in Context
This paper presents the Graded Word Similarity in Context (GWSC) task which asked participants to predict the effects of context on human perception of similarity in English, Croatian, Slovene and Finnish.
A Review of Cross-Domain Text-to-SQL Models
WikiSQL and Spider, the large-scale cross-domain text-to-SQL datasets, have attracted much attention from the research community.
Temporal Mental Health Dynamics on Social Media
We describe a set of experiments for building a temporal mental health dynamics system.
How Furiously Can Colourless Green Ideas Sleep? Sentence Acceptability in Context
We study the influence of context on sentence acceptability.
How Furiously Can Colorless Green Ideas Sleep? Sentence Acceptability in Context
We study the influence of context on sentence acceptability.
CoSimLex: A Resource for Evaluating Graded Word Similarity in Context
State of the art natural language processing tools are built on context-dependent word embeddings, but no direct method for evaluating these representations currently exists.
Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics
One of the fundamental requirements for models of semantic processing in dialogue is incrementality: a model must reflect how people interpret and generate language at least on a word-by-word basis, and handle phenomena such as fragments, incomplete and jointly-produced utterances.
Incongruent Headlines: Yet Another Way to Mislead Your Readers
This paper discusses the problem of incongruent headlines: those which do not accurately represent the information contained in the article with which they occur.
Words, Concepts, and the Geometry of Analogy
This paper presents a geometric approach to the problem of modelling the relationship between words and concepts, focusing in particular on analogical phenomena in language and cognition.
Strongly Incremental Repair Detection
We present STIR (STrongly Incremental Repair detection), a system that detects speech repairs and edit terms on transcripts incrementally with minimal latency.
Evaluating Neural Word Representations in Tensor-Based Compositional Settings
We provide a comparative study between neural word representations and traditional vector spaces based on co-occurrence counts, in a number of compositional tasks.
