ICNLSP 2022

Keynotes

Hybrid natural language processing in the deep learning era

Prof. Eric Laporte, Gustave Eiffel University, France

Multilingual and Code-Switching Speech Recognition

Dr. Ahmed Ali, Qatar Computing Research Institute, Qatar

Plug-and-Play Abilities for Neural Machine Translation

Prof Jan Niehues, Karlsruhe Institute of Technology, Germany

Presentations

Error correction and extraction in request dialogs Stefan Constantin and Alex Waibel.
Comparison of Token- and Character-Level Approaches to Restoration of Spaces, Punctuation, and Capitalization in Various Languages Laurence Dyer, Anthony Hughes, Dhwani Shah and Burcu Can.
Improving NL-to-Query Systems through Re-ranking of Semantic Hypothesis Pius von Däniken, Jan Deriu, Eneko Agirre, Ursin Brunner, Mark Cieliebak and Kurt Stockinger.
TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System Hongru Wang, Mingyu Cui, Zimo Zhou and Kam-Fai Wong.
Contextual Embeddings Can Distinguish Homonymy from Polysemy in a Human-Like Way Kyra Wilson and Alec Marantz.
Modeling the Ordering of English Adjectives using Collaborative Filtering Sagar Indurkhya.
Arguments to Key Points Mapping with Prompt-based Learning Ahnaf Mozib Samin, Behrooz Nikandish and Jingyan Chen.
Evaluating Large-Language Models for Dimensional Music Emotion Prediction from Social Media Discourse Patrick Donnelly and Aidan Beery.
Semantic Similarity-Based Clustering of Findings From Security Testing Tools Phillip Schneider, Markus Voggenreiter, Abdullah Gulraiz and Florian Matthes.
Semi-supervised Automated Clinical Coding Using International Classification of Diseases Hlynur Hlynsson, Steindór Ellertsson, Jon Dadason, Emil Sigurdsson and Hrafn Loftsson.
Towards an Automatic Dialect Identification System using Algerian Youtube Videos Khaled Lounnas, Mohamed Lichouri and Mourad Abbas.
Semantic Similarity Based Filtering for Turkish Paraphrase Dataset Creation Besher Alkurdi, Hasan Yunus Sarioglu and Mehmet Fatih Amasyali.
Second-order Document Similarity Metrics for Transformers Jarkko Lagus, Niki Loppi and Arto Klami.
The Elementary Scenario Component Metric for Summarization Evaluation Martin Kirilov, Daan Kolkman and Bert-Jan Butijn.
“Der Frank Sinatra der Wettervorhersage”: Cross-Lingual Vossian Antonomasia Extraction Michel Schwab, Robert Jäschke and Frank Fischer.
Pre-training Language Models for Surface Realization Farhood Farahnak and Leila Kosseim.
Utilizing BERT Intermediate Layers for Unsupervised Keyphrase Extraction Mingyang Song, Yi Feng and Liping Jing.
A Dataset for Detecting Humor in Arabic Text Hend Alkhalifa, Fetoun Alzahrani, Hala Qawara, Reema Alrowais, Sawsan Alowa and Luluh Aldhubayi.
Detecting Security Patches in Java Projects Using NLP Technology Andrea Stefanoni, Šarūnas Girdzijauskas, Christina Jenkins, Zekarias T. Kefato, Licia Sbattella, Vincenzo Scotti and Emil Wåreus.
Optimizing singular value based similarity measures for document similarity comparisons Jarkko Lagus and Arto Klami.
Supervised Acoustic Embeddings And Their Transferability Across Languages Sreepratha Ram and Hanan Aldarmaki.
Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Task Radostin Cholakov and Todor Kolev.
A deep sentiment analysis of Tunisian dialect comments on multi-domain posts in different social media platforms Emna Fsih, Rahma Boujelbane and Lamia Hadrich Belguith.
Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning Zezhong Wang, Hongru Wang, Wai Chung Kwan and Kam-Fai Wong.
Hierarchical Multi-Task Transformers for Crosslingual Low Resource Phoneme Recognition Kevin Glocker and Munir Georges.
Experimenting with ensembles of pre-trained language models for classification of custom legal datasets Tamara Matthews and David Lillis.
Linguistic Knowledge in Data Augmentation for Natural Language Processing: An Example on Chinese Question Matching Zhengxiang Wang.
Customer Sentiments Toward Saudi Banks During the Covid-19 Pandemic Dhuha Alqahtani, Lama Alzahrani, Maram Bahareth, Nora Alshameri, Hend Al-Khalifa and Luluh Aldhubayi.
Recent Advances in Long Documents Classification Using Deep-Learning Muhammad Al-Qurishi.
A low latency technique for speaker detection from a large negative list Yu Zhou, B. Chandra Mouli and Vijay Gurbani.
Constructing the Corpus of Chinese Textual ‘Run-on’ Sentences (CCTRS): Discourse Corpus Benchmark with Multi-layer Annotations Kun Sun and Rong Wang.
Concatenative Phonetic Synthesis for the Proto-Indo-European Language Patrick Donnelly.
Handling Class Imbalance when Detecting Dataset Mentions with Pre-trained Language Models Yousef Younes and Brigitte Mathiak.
TuniSER: Toward a Tunisian Speech Emotion Recognition System Abir Messaoudi, Hatem Haddad, Moez Benhaj Hmida and Mohamed Graiet.
New Features for Discriminative Keyword Spotting Punnoose Kuriakose.

ICNLSP 2022

Keynotes

Hybrid natural language processing in the deep learning era

Multilingual and Code-Switching Speech Recognition

Plug-and-Play Abilities for Neural Machine Translation

Presentations

Error correction and extraction in request dialogs

Comparison of Token- and Character-Level Approaches to Restoration of Spaces, Punctuation, and Capitalization in Various Languages

Improving NL-to-Query Systems through Re-ranking of Semantic Hypothesis

TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System

Contextual Embeddings Can Distinguish Homonymy from Polysemy in a Human-Like Way

Modeling the Ordering of English Adjectives using Collaborative Filtering

Arguments to Key Points Mapping with Prompt-based Learning

Evaluating Large-Language Models for Dimensional Music Emotion Prediction from Social Media Discourse

Semantic Similarity-Based Clustering of Findings From Security Testing Tools

Semi-supervised Automated Clinical Coding Using International Classification of Diseases

Towards an Automatic Dialect Identification System using Algerian Youtube Videos

Semantic Similarity Based Filtering for Turkish Paraphrase Dataset Creation

Second-order Document Similarity Metrics for Transformers

The Elementary Scenario Component Metric for Summarization Evaluation

“Der Frank Sinatra der Wettervorhersage”: Cross-Lingual Vossian Antonomasia Extraction

Pre-training Language Models for Surface Realization

Utilizing BERT Intermediate Layers for Unsupervised Keyphrase Extraction

A Dataset for Detecting Humor in Arabic Text

Detecting Security Patches in Java Projects Using NLP Technology

Optimizing singular value based similarity measures for document similarity comparisons

Supervised Acoustic Embeddings And Their Transferability Across Languages

Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Task

A deep sentiment analysis of Tunisian dialect comments on multi-domain posts in different social media platforms

Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning

Hierarchical Multi-Task Transformers for Crosslingual Low Resource Phoneme Recognition

Experimenting with ensembles of pre-trained language models for classification of custom legal datasets

Linguistic Knowledge in Data Augmentation for Natural Language Processing: An Example on Chinese Question Matching

Customer Sentiments Toward Saudi Banks During the Covid-19 Pandemic

Recent Advances in Long Documents Classification Using Deep-Learning

A low latency technique for speaker detection from a large negative list

Constructing the Corpus of Chinese Textual ‘Run-on’ Sentences (CCTRS): Discourse Corpus Benchmark with Multi-layer Annotations

Concatenative Phonetic Synthesis for the Proto-Indo-European Language

Handling Class Imbalance when Detecting Dataset Mentions with Pre-trained Language Models

TuniSER: Toward a Tunisian Speech Emotion Recognition System

New Features for Discriminative Keyword Spotting