2.4k citations · 2.7k across the 35 of their papers we have counts for
19 papers · 1 filter
Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
Shahin Atakishiyev, Housam K. B. Babiker, Jiayi Dai +8
Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next…
Deep Temporal Modelling of Clinical Depression through Social Media Text
Nawshad Farruque, Randy Goebel, Sudhakar Sivapalan +1
We describe the development of a model to detect user-level clinical depression based on a user's temporal social media posts. Our model uses a Depression Symptoms Detection (DSD)…
Depression Symptoms Modelling from Social Media Text: A Semi-supervised Learning Approach
Nawshad Farruque, Randy Goebel, Sudhakar Sivapalan +1
A fundamental component of user-level social media language based clinical depression modelling is depression symptoms detection (DSD). Unfortunately, there does not exist any DSD…
Named Entity Recognition for Partially Annotated Datasets
Michael Strobl, Amine Trabelsi, Osmar Zaiane
The most common Named Entity Recognizers are usually sequence taggers trained on fully annotated corpora, i.e. the class of all words for all entities is known. Partially annotated…
On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?
Nouha Dziri, Sivan Milton, Mo Yu +2
Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallucination. In this work, we investigate t…
FREDA: Flexible Relation Extraction Data Annotation
Michael Strobl, Amine Trabelsi, Osmar Zaiane
To effectively train accurate Relation Extraction models, sufficient and properly labeled data is required. Adequately labeled data is difficult to obtain and annotating such data…
Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
Chenyang Huang, Hao Zhou, Osmar R. Zaïane +2
How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they…
Simulated Annealing for Emotional Dialogue Systems
Chengzhang Dong, Chenyang Huang, Osmar Zaïane +1
Explicitly modeling emotions in dialogue generation has important applications, such as building empathetic personal companions. In this study, we consider the task of expressing a…
A comprehensive empirical analysis on cross-domain semantic enrichment for detection of depressive language
Nawshad Farruque, Randy Goebel, Osmar Zaiane
We analyze the process of creating word embedding feature representations designed for a learning task when annotated data is scarce, for example, in depressive language detection…
STEP-EZ: Syntax Tree guided semantic ExPlanation for Explainable Zero-shot modeling of clinical depression symptoms from text
Nawshad Farruque, Randy Goebel, Osmar Zaiane +1
We focus on exploring various approaches of Zero-Shot Learning (ZSL) and their explainability for a challenging yet important supervised learning task notorious for training data s…
ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)
Anandh Perumal, Chenyang Huang, Amine Trabelsi +1
In this paper, we describe our mUlti-task learNIng for cOmmonsense reasoNing (UNION) system submitted for Task C of the SemEval2020 Task 4, which is to generate a reason explaining…
Seq2Emo for Multi-label Emotion Classification Based on Latent Variable Chains Transformation
Chenyang Huang, Amine Trabelsi, Xuebin Qin +2
Emotion detection in text is an important task in NLP and is essential in many applications. Most of the existing methods treat this task as a problem of single-label multi-class t…
Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems
Mansour Saffar Mehrjardi, Amine Trabelsi, Osmar R. Zaiane
Self-attentional models are a new paradigm for sequence modelling tasks which differ from common sequence modelling methods, such as recurrence-based and convolution-based sequence…
Contrastive Reasons Detection and Clustering from Online Polarized Debate
Amine Trabelsi, Osmar R. Zaiane
This work tackles the problem of unsupervised modeling and extraction of the main contrastive sentential reasons conveyed by divergent viewpoints on polarized issues. It proposes a…
ANA at SemEval-2019 Task 3: Contextual Emotion detection in Conversations through hierarchical LSTMs and BERT
Chenyang Huang, Amine Trabelsi, Osmar R. Zaïane
This paper describes the system submitted by ANA Team for the SemEval-2019 Task 3: EmoContext. We propose a novel Hierarchical LSTMs for Contextual Emotion Detection (HRLCE) model.…
Evaluating Coherence in Dialogue Systems using Entailment
Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson +1
Evaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers. Automatic metrics such as BLEU correlate weakly with human annotations, resul…
Generating Responses Expressing Emotion in an Open-domain Dialogue System
Chenyang Huang, Osmar R. Zaïane
Neural network-based Open-ended conversational agents automatically generate responses based on predictive models learned from a large number of pairs of utterances. The generated…
On Generality and Knowledge Transferability in Cross-Domain Duplicate Question Detection for Heterogeneous Community Question Answering
Mohomed Shazan Mohomed Jabbar, Luke Kumar, Hamman Samuel +4
Duplicate question detection is an ongoing challenge in community question answering because semantically equivalent questions can have significantly different words and structures…
Augmenting Neural Response Generation with Context-Aware Topical Attention
Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson +1
Sequence-to-Sequence (Seq2Seq) models have witnessed a notable success in generating natural conversational exchanges. Notwithstanding the syntactically well-formed responses gener…