Related papers: SLAM-Inspired Simultaneous Contextualization and I…

The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language…

Automatic Term Recognition is used to extract domain-specific terms that belong to a given domain. In order to be accurate, these corpus and language-dependent methods require large volumes of textual data that need to be processed to…

We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…

Sarcasm, a common feature of human communication, poses challenges in interpersonal interactions and human-machine interactions. Linguistic research has highlighted the importance of prosodic cues, such as variations in pitch, speaking…

Several recent works have suggested to represent semantic relations with questions and answers, decomposing textual information into separate interrogative natural language statements. In this paper, we consider three QA-based semantic…

Speech separation with several speakers is a challenging task because of the non-stationarity of the speech and the strong signal similarity between interferent sources. Current state-of-the-art solutions can separate well the different…

In this paper, we propose a novel approach for the transcription of speech conversations with natural speaker overlap, from single channel speech recordings. The proposed model is a combination of a speaker diarization system and a hybrid…

For human beings, the processing of text streams of unknown size leads generally to problems because e.g. noise must be selected out, information be tested for its relevance or redundancy, and linguistic phenomenon like ambiguity or the…

Spatial audio understanding is essential for accurately perceiving and interpreting acoustic environments. However, existing audio-language models exhibit limitations in processing spatial audio and perceiving spatial acoustic scenes. To…

To avoid the "meaning conflation deficiency" of word embeddings, a number of models have aimed to embed individual word senses. These methods at one time performed well on tasks such as word sense induction (WSI), but they have since been…

Multilingual Large Language Models (LLMs) exhibit remarkable cross-lingual abilities, yet often exhibit a systematic bias toward the representations from other languages, resulting in semantic interference when generating content in…

Distributed representation plays an important role in deep learning based natural language processing. However, the representation of a sentence often varies in different tasks, which is usually learned from scratch and suffers from the…

Simultaneous localization and mapping (SLAM) is a critical technology that enables autonomous robots to be aware of their surrounding environment. With the development of deep learning, SLAM systems can achieve a higher level of perception…

Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance…

Spoken Language Understanding (SLU) systems consist of several machine learning components operating together (e.g. intent classification, named entity recognition and resolution). Deep learning models have obtained state of the art results…

Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for…

Despite large language models (LLMs) have demonstrated impressive performance in various tasks, they are still suffering from the factual inconsistency problem called hallucinations. For instance, LLMs occasionally generate content that…

There have been some works that learn a lexicon together with the corpus to improve the word embeddings. However, they either model the lexicon separately but update the neural networks for both the corpus and the lexicon by the same…

Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these…

We consider the problem of aligning two sets of continuous word representations, corresponding to languages, to a common space in order to infer a bilingual lexicon. It was recently shown that it is possible to infer such lexicon, without…