A5079066886- Natural Language Processing Techniques
- Topic Modeling
- Text Readability and Simplification
- Semantic Web and Ontologies
- Speech and dialogue systems
- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Translation Studies and Practices
- Biomedical Text Mining and Ontologies
- Hate Speech and Cyberbullying Detection
- Spam and Phishing Detection
- Multimodal Machine Learning Applications
- Mental Health via Writing
- Misinformation and Its Impacts
- Rough Sets and Fuzzy Logic
- Web Data Mining and Analysis
- Service-Oriented Architecture and Web Services
- Interpreting and Communication in Healthcare
- Software Engineering Research
- Data Mining Algorithms and Applications
- Algorithms and Data Compression
- Handwritten Text Recognition Techniques
- Authorship Attribution and Profiling
- Text and Document Classification Technologies
- Emotion and Mood Recognition
University of Surrey
2020-2024
University of Tehran
2023
University of Wolverhampton
2011-2021
Universitat Politècnica de Catalunya
2019
Tokyo Metropolitan University
2019
University of Michigan
2019
Stanford University
2019
Saarland University
2016
German Research Centre for Artificial Intelligence
2016
University of Alicante
2002
Frederic Blain, Chrysoula Zerva, Ricardo Ribeiro, Nuno M. Guerreiro, Diptesh Kanojia, José G. C. de Souza, Beatriz Silva, Tânia Vaz, Yan Jingxuan, Fatemeh Azadi, Constantin Orasan, André Martins. Proceedings of the Eighth Conference on Machine Translation. 2023.
Recent years have seen big advances in the field of sentence-level quality estimation (QE), largely as a result using neural-based architectures. However, majority these methods work only on language pair they are trained and need retraining for new pairs. This process can prove difficult from technical point view is usually computationally expensive. In this paper we propose simple QE framework based cross-lingual transformers, use it to implement evaluate two different neural Our...
Syntactically complex sentences constitute an obstacle for some people with Autistic Spectrum Disorders.This paper evaluates a set of simplification rules specifically designed tackling and compound sentences.In total, 127 different were developed the rewriting 56 sentences.The evaluation assessed accuracy these individually revealed that fully automatic conversion into more accessible form is not very reliable.
Calculating the Semantic Textual Similarity (STS) is an important research area in natural language processing which plays a significant role many applications such as question answering, document summarisation, information retrieval and extraction.This paper evaluates Siamese recurrent architectures, special type of neural networks, are used here to measure STS.Several variants architecture compared with existing methods.
Many state-of-the-art Machine Translation (MT) evaluation metrics are complex, involve extensive external resources (e.g. for paraphrasing) and require tuning to achieve best results.We present a simple alternative approach based on dense vector spaces recurrent neural networks (RNNs), in particular Long Short Term Memory (LSTM) networks.For WMT-14, our new metric scores two out of five language pairs, overall second all using Spearman Pearson correlation, respectively.We also show how...
This paper investigates the reference-less evaluation of machine translation for low-resource language pairs, known as quality estimation (QE). Segment-level QE is a challenging cross-lingual understanding task that provides score (0-100) to translated output. We comprehensively evaluate large models (LLMs) in zero/few-shot scenarios and perform instruction fine-tuning using novel prompt based on annotation guidelines. Our results indicate prompt-based approaches are outperformed by...
This paper reports on the results from a pilot study investigating impact of automatic speech recognition (ASR) technology interpreting quality in remote healthcare settings. Employing within-subjects experiment design with four randomised conditions, this utilises scripted medical consultations to simulate dialogue tasks. It involves trainee interpreters language combination Chinese and English. also gathers participants' experience perceptions ASR support through cued retrospective...
The ability to automatically detect human stress and relaxation is crucial for timely diagnosing stress-related diseases, ensuring customer satisfaction in services managing human-centric applications such as traffic management. Traditional methods employ stress-measuring scales or physiological monitoring which may be intrusive inconvenient. Instead, the ubiquitous nature of social media can leveraged identify relaxation, since many people habitually share their recent life experiences...
This paper presents the team TransQuest's participation in Sentence-Level Direct Assessment shared task WMT 2020. We introduce a simple QE framework based on cross-lingual transformers, and we use it to implement evaluate two different neural architectures. The proposed methods achieve state-of-the-art results surpassing obtained by OpenKiwi, baseline used task. further fine tune performing ensemble data augmentation. Our approach is winning solution all of language pairs according 2020...
In anaphora resolution for English, animacy identification can play an integral role in the application of agreement restrictions between pronouns and candidates, as a result, improve accuracy systems. this paper, two methods are proposed evaluated using intrinsic extrinsic measures. The first method is rule-based one which uses information about unique beginners WordNet to classify NPs on basis their animacy. second relies machine learning algorithm exploits enriched with each sense. effect...
Hanna Béchara, Hernani Costa, Shiva Taslimipoor, Rohit Gupta, Constantin Orasan, Gloria Corpas Pastor, Ruslan Mitkov. Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015). 2015.