Related papers: Parole de pr\'esidents (1958-2022)
Entity tags in human-machine dialog are integral to natural language understanding (NLU) tasks in conversational assistants. However, current systems struggle to accurately parse spoken queries with the typical use of text input alone, and…
This study examines how interruptions during U.S. Supreme Court oral arguments shape both the semantic content and emotional tone of advocates' speech, with a focus on gendered dynamics in judicial discourse. Using the ConvoKit Supreme…
Recent significant advancements in Large Language Models (LLMs) have greatly propelled the development of Role-Playing Conversational Agents (RPCAs). These systems aim to create immersive user experiences through consistent persona…
ParlaSpeech is a collection of spoken parliamentary corpora currently spanning four Slavic languages - Croatian, Czech, Polish and Serbian - all together 6 thousand hours in size. The corpora were built in an automatic fashion from the…
This paper describes the design and development of CUCHILD, a large-scale Cantonese corpus of child speech. The corpus contains spoken words collected from 1,986 child speakers aged from 3 to 6 years old. The speech materials include 130…
This study is an attempt to build a contemporary linguistic corpus for Arabic language. The corpus produced, is a text corpus includes more than five million newspaper articles. It contains over a billion and a half words in total, out of…
This paper establishes an empirical baseline of public sentiment toward Fourth Industrial Revolution (4IR) technologies across six European countries during the period 2006--2019, prior to the widespread adoption of generative AI systems.…
Hidden structural patterns in written texts have been subject of considerable research in the last decades. In particular, mapping a text into a time series of sentence lengths is a natural way to investigate text structure. Typically,…
A recent increase in data availability has allowed the possibility to perform different statistical linguistic studies. Here we use the Google Books Ngram dataset to analyze word flow among English, French, German, Italian, and Spanish. We…
The world's digital transformation has influenced not only the way we do business, but also the way we perform daily activities. In fact, the past Presidential elections in the United States as well as those in Great Britain (Brexit) and in…
We present a novel corpus of 445 human- and computer-generated documents, comprising about 27,000 clauses, annotated for semantic clause types and coherence relations that allow for nuanced comparison of artificial and natural discourse…
Large Language Models (LLMs) demonstrate strong conversational abilities. In this Working Paper, we study them in the context of debating in two ways: their ability to perform in a structured debate along with a dataset of arguments to use…
France is one of the pioneer countries in the use of Electric Vehicles (EVs). The French government aims to complete the transition to EVs by 2040. Therefore, modeling related to the adoption of EVs is needed in order to determine the…
Political discourse datasets are important for gaining political insights, analyzing communication strategies or social science phenomena. Although numerous political discourse corpora exist, comprehensive, high-quality, annotated datasets…
We propose a new benchmark corpus to be used for measuring progress in statistical language modeling. With almost one billion words of training data, we hope this benchmark will be useful to quickly evaluate novel language modeling…
Responding to the increasing need for automated writing evaluation (AWE) systems to assess language use beyond lexis and grammar (Burstein et al., 2016), we introduce a new approach to identify rhetorical features of stance in academic…
This study presents a fascinating linguistic property related to the number of letters in words and their corresponding numerical values. By selecting any arbitrary word, counting its constituent letters, and subsequently spelling out the…
Of all components of Prosody, Rhythm has been regarded as the hardest to address, as it is utterly linked to Pitch and Intensity. Nevertheless, Rhythm is a very good indicator of a speaker's fluency in a foreign language or even of some…
Amidst the rising capabilities of generative AI to mimic specific human styles, this study investigates the ability of state-of-the-art large language models (LLMs), including GPT-4o, Gemini 1.5 Pro, and Claude Sonnet 3.5, to emulate the…
In this work, we report on the effectiveness of our efforts to tailor the personality and conversational style of a conversational agent based on GPT-3.5 and GPT-4 through prompts. We use three personality dimensions with two levels each to…