Related papers: Building and curating conversational corpora for d…
Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi-speaker ASR remains a challenging task for these models due…
Developing language model-based dialogue agents requires effective data to train models that can follow specific task logic. However, most existing data simulation methods focus on increasing diversity in language, topics, or dialogue acts…
Aspect-based sentiment analysis (ABSA) is a natural language processing problem that requires analyzing user-generated reviews to determine: a) The target entity being reviewed, b) The high-level aspect to which it belongs, and c) The…
Conversational tones -- the manners and attitudes in which speakers communicate -- are essential to effective communication. Amidst the increasing popularization of Large Language Models (LLMs) over recent years, it becomes necessary to…
In machine translation field, in both academia and industry, there is a growing interest in increasingly powerful systems, using corpora of several hundred million to several billion examples. These systems represent the state-of-the-art.…
The success of large language models has driven interest in developing similar speech processing capabilities. However, a key challenge is the scarcity of high-quality spontaneous speech data, as most existing datasets contain scripted…
Recently, a large number of tuning strategies have been proposed to adapt pre-trained language models to downstream tasks. In this paper, we perform an extensive empirical evaluation of various tuning strategies for multilingual learning,…
Large language models are commonly trained on a mixture of filtered web data and curated high-quality corpora, such as social media conversations, books, or technical papers. This curation process is believed to be necessary to produce…
The conversational nature of chatbots poses challenges to designers since their development is different from other software and requires investigating new practices in the context of human-AI interaction and their impact on user…
This paper presents SaSLaW, a spontaneous dialogue speech corpus containing synchronous recordings of what speakers speak, listen to, and watch. Humans consider the diverse environmental factors and then control the features of their…
Based on the foundation of Large Language Models (LLMs), Multilingual LLMs (MLLMs) have been developed to address the challenges faced in multilingual natural language processing, hoping to achieve knowledge transfer from high-resource…
Language technology has the potential to facilitate intercultural communication through meaningful translations. However, the current state of language technology is deeply entangled with colonial knowledge due to path dependencies and…
This paper focuses on AI tutors in foreign language learning, a field of application of AI tutors with great development, especially during the last years, when great advances in natural language understanding and processing in real time,…
How can large language models (LLMs) serve users with varying preferences that may conflict across cultural, political, or other dimensions? To advance this challenge, this paper establishes four key results. First, we demonstrate, through…
Open-domain conversational systems are assumed to generate equally good responses on multiple domains. Previous work achieved good performance on the single corpus, but training and evaluating on multiple corpora from different domains are…
Disentangling conversations mixed together in a single stream of messages is a difficult task, made harder by the lack of large manually annotated datasets. We created a new dataset of 77,563 messages manually annotated with reply-structure…
When humans read a text, their eye movements are influenced by the structural complexity of the input sentences. This cognitive phenomenon holds across languages and recent studies indicate that multilingual language models utilize…
We have so many languages to communicate with others as humans. There are approximately 7000 languages in the world, and many are becoming extinct for a variety of reasons. In order to preserve and prevent the extinction of these languages,…
The outstanding performance of transformer-based language models on a great variety of NLP and NLU tasks has stimulated interest in exploring their inner workings. Recent research has focused primarily on higher-level and complex linguistic…
Despite representing nearly one-third of the world's languages, African languages remain critically underserved by modern NLP technologies, with 88\% classified as severely underrepresented or completely ignored in computational…