Related papers: Improving Natural Language Processing Tasks with H…

Vision-language models (VLMs) have rapidly evolved into general-purpose multimodal reasoners with strong zero-shot generalization. In this context, VLMs could greatly benefit the analysis of human gaze and attention, a central task in human…

This review presents a comprehensive exploration of hybrid and ensemble deep learning models within Natural Language Processing (NLP), shedding light on their transformative potential across diverse tasks such as Sentiment Analysis, Named…

We propose a multi-task learning (MTL) model for jointly performing three tasks that are commonly solved in a text-to-speech (TTS) front-end: text normalization (TN), part-of-speech (POS) tagging, and homograph disambiguation (HD). Our…

Text segmentation plays an important role in various Natural Language Processing (NLP) tasks like summarization, context understanding, document indexing and document noise removal. Previous methods for this task require manual feature…

We present PaLM, a hybrid parser and neural language model. Building on an RNN language model, PaLM adds an attention layer over text spans in the left context. An unsupervised constituency parser can be derived from its attention weights,…

Ensuring that Text-to-Speech (TTS) systems deliver human-perceived quality at scale is a central challenge for modern speech technologies. Human subjective evaluation protocols such as Mean Opinion Score (MOS) and Side-by-Side (SBS)…

We consider the problem of learning general-purpose, paraphrastic sentence embeddings based on supervision from the Paraphrase Database (Ganitkevitch et al., 2013). We compare six compositional architectures, evaluating them on annotated…

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…

In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, we collect a new…

Soft prompt learning has recently emerged as one of the methods of choice for adapting V&L models to a downstream task using a few training examples. However, current methods significantly overfit the training data, suffering from large…

State-of-the-art text-to-speech (TTS) systems have utilized pretrained language models (PLMs) to enhance prosody and create more natural-sounding speech. However, while PLMs have been extensively researched for natural language…

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to…

Charts are a crucial visual medium for communicating and representing information. While Large Vision-Language Models (LVLMs) have made progress on chart question answering (CQA), the task remains challenging, particularly when models…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

This paper presents the results of the SHROOM, a shared task focused on detecting hallucinations: outputs from natural language generation (NLG) systems that are fluent, yet inaccurate. Such cases of overgeneration put in jeopardy many NLG…

In order to successfully perform tasks specified by natural language instructions, an artificial agent operating in a visual world needs to map words, concepts, and actions from the instruction to visual elements in its environment. This…

Automatically describing video content with natural language has been attracting much attention in CV and NLP communities. Most existing methods predict one word at a time, and by feeding the last generated word back as input at the next…

Large Language Models (LLMs) often generate incorrect or unsupported content, known as hallucinations. Existing detection methods rely on heuristics or simple models over isolated computational traces such as activations, or attention maps.…

The allure of superhuman-level capabilities has led to considerable interest in language models like GPT-3 and T5, wherein the research has, by and large, revolved around new model architectures, training tasks, and loss objectives, along…

Recent years have witnessed a surge of research on leveraging large language models (LLMs) for sequential recommendation. LLMs have demonstrated remarkable potential in inferring users' nuanced preferences through fine-grained semantic…