相关论文: Neural Label Search for Zero-Shot Multi-Lingual Ex…

Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far richer search modalities such as images, speaker, content,…

Large pre-trained language models have brought remarkable progress in NLP. Pre-training and Fine-tuning have given state-of-art performance across tasks in text processing. Data Augmentation techniques have also helped build state-of-art…

An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an…

An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or…

While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing…

Large Language Models (LLMs) have become a key topic in AI and NLP, transforming sectors like healthcare, finance, education, and marketing by improving customer service, automating tasks, providing insights, improving diagnostics, and…

Vision-Language Models (VLMs) often struggle to balance visual and textual information when summarizing complex multimodal inputs, such as entire TV show episodes. In this paper, we propose a zero-shot video-to-text summarization approach…

Error detection (ED) in tabular data is crucial yet challenging due to diverse error types and the need for contextual understanding. Traditional ED methods often rely heavily on manual criteria and labels, making them labor-intensive.…

Most rumour detection models for social media are designed for one specific language (mostly English). There are over 40 languages on Twitter and most languages lack annotated resources to build rumour detection models. In this paper we…

We propose a rubric-guided, pseudo-labeled, and prompt-driven zero-shot video summarization framework that bridges large language models with structured semantic reasoning. A small subset of human annotations is converted into…

Recognizing emotions in spoken communication is crucial for advanced human-machine interaction. Current emotion detection methodologies often display biases when applied cross-corpus. To address this, our study amalgamates 16 diverse…

Extracting summaries from long documents can be regarded as sentence classification using the structural information of the documents. How to use such structural information to summarize a document is challenging. In this paper, we propose…

In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of…

In recent years, biomedical event extraction has been dominated by complicated pipeline and joint methods, which need to be simplified. In addition, existing work has not effectively utilized trigger word information explicitly. Hence, we…

Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn commonsense knowledge…

It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog…

Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts…

Multilingual speech emotion recognition aims to estimate a speaker's emotional state using a contactless method across different languages. However, variability in voice characteristics and linguistic diversity poses significant challenges…

We present a study on the integration of Large Language Models (LLMs) in tabular data classification, emphasizing an efficient framework. Building upon existing work done in TabLLM (arXiv:2210.10723), we introduce three novel serialization…

This work investigates the use of natural language to enable zero-shot model adaptation to new tasks. We use text and metadata from social commenting platforms as a source for a simple pretraining task. We then provide the language model…