2 |
On the Use of Linguistic Features for the Evaluation of Generative Dialogue Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Quantifying the Task-Specific Information in Text-Based Classifications ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
An {E}valuation of {D}isentangled {R}epresentation {L}earning for {T}exts ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
How is BERT surprised? Layerwise detection of linguistic anomalies ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Comparing Pre-trained and Feature-Based Models for Prediction of Alzheimer's Disease Based on Speech
|
|
|
|
In: Front Aging Neurosci (2021)
|
|
BASE
|
|
Show details
|
|
8 |
Identification of primary and collateral tracks in stuttered speech
|
|
|
|
In: LREC 2020 - 12th Conference on Language Resources and Evaluation ; https://hal.archives-ouvertes.fr/hal-02959454 ; LREC 2020 - 12th Conference on Language Resources and Evaluation, May 2020, Marseille, France (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Semantic coordinates analysis reveals language changes in the AI field ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
An information theoretic view on selecting linguistic probes ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Examining the rhetorical capacities of neural language models ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
A textual analysis of US corporate social responsibility reports
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power ...
|
|
|
|
Abstract:
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. In this paper, we investigate how generic language characteristics, such as syntax or the lexicon, are impacted by artificial text alterations. The vulnerability of features is analysed from two perspectives: (1) the level of feature value change, and (2) the level of change of feature predictive power as a result of text modifications. We show that lexical features are more sensitive to text modifications than syntactic ones. However, we also demonstrate that these smaller changes of syntactic features have a stronger influence on classification performance downstream, compared to the impact of changes to lexical features. Results are validated across three datasets representing different text-classification tasks, with different levels of lexical and syntactic complexity of both ... : EMNLP Workshop on Noisy User-generated Text (W-NUT 2019) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1910.00065 https://dx.doi.org/10.48550/arxiv.1910.00065
|
|
BASE
|
|
Hide details
|
|
16 |
Representation Learning for Discovering Phonemic Tone Contours ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
The Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Detecting cognitive impairments by agreeing on interpretations of linguistic features ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Deconfounding age effects with fair representation learning when assessing dementia ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|