Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that generate toxic, inaccurate, and unhelpful content, and automatic evaluation metri... read more of Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation

Speech and Language Processing is a field at the intersection of computer science, linguistics, and artificial intelligence that focuses on understanding and developing technologies to process and analyze human language. It encompasses various tasks such ... read more of Speech and Language Processing

Representation learning techniques in NLP capture meaningful and distributed representations of textual data, known as embeddings. These embeddings enable NLP models to effectively understand semantic and syntactic relationships. Popular methods include w... read more of Representation Learning for Natural Language Processing

Proactive dialogue systems, related to a wide range of real-world conversational applications, equip the conversational agent with the capability of leading the conversation direction towards achieving predefined targets or fulfilling certain goals from t... read more of A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects

Acoustic digital signals are ubiquitous and have many applications in several disciplines, notably in: -Digital Media, Social Media (music, voice signals), -Biomedical Signal Analysis and Diagnosis, -Scientific signal acquisition of any sort, e.g., E... read more of Acoustics, Speech, Natural Language Processing and Analysis Module