Search Results for author:
Found 39 papers, 9 papers with code
The Tutorbot Corpus --- A Corpus for Studying Tutoring Behaviour in Multiparty Face-to-Face Spoken Dialogue
The corpus is targeted and designed towards the development of a dialogue system platform to explore verbal and nonverbal tutoring strategies in multiparty spoken interactions.
Crowd-sourcing NLG Data: Pictures Elicit Better Data
Recent advances in corpus-based Natural Language Generation (NLG) hold the promise of being easily portable across domains, but require costly training data, consisting of meaning representations (MRs) paired with Natural Language (NL) utterances.
Sympathy Begins with a Smile, Intelligence Begins with a Word: Use of Multimodal Features in Spoken Human-Robot Interaction
We find that happiness in the user's recognised facial expression strongly correlates with likeability of a robot, while dialogue-related features (such as number of human turns or number of sentences per robot utterance) correlate with perceiving a robot as intelligent.
The E2E Dataset: New Challenges For End-to-End Generation
This paper describes the E2E data, a new dataset for training end-to-end, data-driven natural language generation systems in the restaurant domain, which is ten times bigger than existing, frequently used datasets in this area.
Data-driven Natural Language Generation: Paving the Road to Success
We argue that there are currently two major bottlenecks to the commercial use of statistical machine learning approaches for natural language generation (NLG): (a) The lack of reliable automatic evaluation metrics for NLG, and (b) The scarcity of high quality in-domain corpora.
Why We Need New Evaluation Metrics for NLG
The majority of NLG evaluation relies on automatic metrics, such as BLEU .
Referenceless Quality Estimation for Natural Language Generation
Traditional automatic evaluation measures for natural language generation (NLG) use costly human-authored references to estimate the quality of a system output.
RankME: Reliable Human Ratings for Natural Language Generation
Human evaluation for natural language generation (NLG) often suffers from inconsistent user ratings.
Semi-supervised classification by reaching consensus among modalities
Deep learning has demonstrated abilities to learn complex structures, but they can be restricted by available data.
Deconfounding age effects with fair representation learning when assessing dementia
One of the most prevalent symptoms among the elderly population, dementia, can be detected by classifiers trained on linguistic features extracted from narrative transcripts.
Detecting cognitive impairments by agreeing on interpretations of linguistic features
In this paper, we also present two methods that improve the performance of CNs.
Findings of the E2E NLG Challenge
This paper summarises the experimental setup and results of the first shared task on end-to-end (E2E) natural language generation (NLG) in spoken dialogue systems.
Ranked #5 on
Data-to-Text Generation
on E2E NLG Challenge
The Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech
We analyze the impact of age of the added samples and if they affect fairness in classification.
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
Introducing novel automatic and human metrics, we compare 62 systems submitted by 17 institutions, covering a wide range of approaches, including machine learning architectures -- with the majority implementing sequence-to-sequence models (seq2seq) -- as well as systems based on grammatical rules and templates.
Impact of ASR on Alzheimer's Disease Detection: All Errors are Equal, but Deletions are More Equal than Others
We find that deletion errors affect detection performance the most, due to their impact on the features of syntactic complexity and discourse representation in speech.
Alzheimer's Disease Detection
Automatic Speech Recognition
+2
Variations on the Chebyshev-Lagrange Activation Function
We seek to improve the data efficiency of neural networks and present novel implementations of parameterized piece-wise polynomial activation functions.
Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power
Understanding the vulnerability of linguistic features extracted from noisy text is important for both developing better health text classification models and for interpreting vulnerabilities of natural language models.
Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation
We learn mappings from other languages to English and detect aphasia from linguistic characteristics of speech, and show that OT domain adaptation improves aphasia detection over unilingual baselines for French (6% increased F1) and Mandarin (5% increased F1).
To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection
Research related to automatically detecting Alzheimer's disease (AD) is important, given the high prevalence of AD and the high cost of traditional methods.
Fantastic Features and Where to Find Them: Detecting Cognitive Impairment with a Subsequence Classification Guided Approach
Despite the widely reported success of embedding-based machine learning methods on natural language processing tasks, the use of more easily interpreted engineered features remains common in fields such as cognitive impairment (CI) detection.
Augmenting BERT Carefully with Underrepresented Linguistic Features
Fine-tuned Bidirectional Encoder Representations from Transformers (BERT)-based sequence classification models have proven to be effective for detecting Alzheimer's Disease (AD) from transcripts of human speech.
Comparing Acoustic-based Approaches for Alzheimer's Disease Detection
Robust strategies for Alzheimer's disease (AD) detection are important, given the high prevalence of AD.
Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text
Understanding robustness and sensitivity of BERT models predicting Alzheimer's disease from text is important for both developing better classification models and for understanding their capabilities and limitations.
Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?
However, speech audio may be affected by different types of background noise and it is important to understand how the noise influences the accuracy of ML models detecting AD from speech.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text
Models that accurately detect depression from text are important tools for addressing the post-pandemic mental health crisis.
Data-driven Approach to Differentiating between Depression and Dementia from Noisy Speech and Language Data
In this work, we investigate the ability of clustering approaches in distinguishing between depression and dementia from human speech.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
Multi-modal deep learning system for depression and anxiety detection
We find that augmenting hand-crafted features with deep-learned features improves our overall classification F1 score comparing to a baseline of hand-crafted features alone from 0. 58 to 0. 63 for depression and from 0. 54 to 0. 57 for anxiety.
Cost-effective Models for Detecting Depression from Speech
Our findings suggest that models trained on conventional acoustic features perform equally well or better than the ones trained on deep representation features at significantly lower computational cost, irrespective of other factors, e. g. content and length of speech, gender of the speaker and severity of the disorder.
Factors Affecting the Performance of Automated Speaker Verification in Alzheimer's Disease Clinical Trials
Detecting duplicate patient participation in clinical trials is a major challenge because repeated patients can undermine the credibility and accuracy of the trial's findings and result in significant health and financial risks.
DEPAC: a Corpus for Depression and Anxiety Detection from Speech
Automated diagnosis systems of such disorders, empowered by recent innovations in Artificial Intelligence, can pave the way to reduce the sufferings of the affected individuals.
Zero-Shot Multi-Lingual Speaker Verification in Clinical Trials
This represents a significant step in developing more versatile and efficient speaker verification systems for cognitive and mental health clinical trials that can be used across a wide range of languages and dialects, substantially reducing the effort required to develop speaker verification systems for multiple languages.
Impact of Environmental Noise on Alzheimer’s Disease Detection from Speech: Should You Let a Baby Cry?
However, speech audio may be affected by different types of background noise and it is important to understand how the noise influences the accuracy of ML models detecting AD from speech.
Impact of ASR on Alzheimer’s Disease Detection: All Errors are Equal, but Deletions are More Equal than Others
We find that deletion errors affect detection performance the most, due to their impact on the features of syntactic complexity and discourse representation in speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Robustness and Sensitivity of BERT Models Predicting Alzheimer’s Disease from Text
Understanding robustness and sensitivity of BERT models predicting Alzheimer’s disease from text is important for both developing better classification models and for understanding their capabilities and limitations.
