Related papers: Towards Unification of Discourse Annotation Framew…
Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation…
In this paper, we study the problem of data augmentation for language understanding in task-oriented dialogue system. In contrast to previous work which augments an utterance without considering its relation with other utterances, we…
Despite efforts to increase the representation of disabled people in AI datasets, accessibility datasets are often annotated by crowdworkers without disability-specific expertise, leading to inconsistent or inaccurate labels. This paper…
Unified multimodal models (UMMs) were designed to combine the reasoning ability of large language models (LLMs) with the generation capability of vision models. In practice, however, this synergy remains elusive: UMMs fail to transfer…
Obtaining syntactic parses is a crucial part of many NLP pipelines. However, most of the world's languages do not have large amounts of syntactically annotated corpora available for building parsers. Syntactic projection techniques attempt…
Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…
Implicit discourse relation classification is a challenging task due to the absence of discourse connectives. To overcome this issue, we design an end-to-end neural model to explicitly generate discourse connectives for the task, inspired…
Thanks to information extraction and semantic Web efforts, search on unstructured text is increasingly refined using semantic annotations and structured knowledge bases. However, most users cannot become familiar with the schema of…
Named entity recognition (NER) identifies typed entity mentions in raw text. While the task is well-established, there is no universally used tagset: often, datasets are annotated for use in downstream applications and accordingly only…
Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper we try to overcome this difficulty by presenting a…
The goal of the present chapter is to explore the possibility of providing the research (but also the industrial) community that commonly uses spoken corpora with a stable portfolio of well-documented standardised formats that allow a high…
In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…
Post-training has demonstrated its importance in enhancing the reasoning capabilities of large language models (LLMs). The primary post-training methods can be categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning…
We propose a unified Implicit Dialog framework for goal-oriented, information seeking tasks of Conversational Search applications. It aims to enable dialog interactions with domain data without replying on explicitly encoded the rules but…
This paper investigates how unitizing affects external observers' annotation of group cohesion. We compared unitizing techniques belonging to these categories: interval coding, continuous coding, and a technique inspired by a cognitive…
Instruction tuning has emerged as a promising approach to enhancing large language models in following human instructions. It is shown that increasing the diversity and number of instructions in the training data can consistently enhance…
Supervised classification algorithms are used to solve a growing number of real-life problems around the globe. Their performance is strictly connected with the quality of labels used in training. Unfortunately, acquiring good-quality…
In this article, we are interested in the annotation of transcriptions of human-human dialogue taken from meeting records. We first propose a meeting content model where conversational acts are interpreted with respect to their…
In this work, we propose to use linguistic annotations as a basis for a \textit{Discourse-Aware Semantic Self-Attention} encoder that we employ for reading comprehension on long narrative texts. We extract relations between discourse units,…
Recommendation systems focus on helping users find items of interest in the situations of information overload, where users' preferences are typically estimated by the past observed behaviors. In contrast, conversational recommendation…