Related papers: IndoBERT-Relevancy: A Context-Conditioned Relevanc…
The spread of cyber hatred has led to communal violence, fueling aggression and conflicts between various religious, ethnic, and social groups, posing a significant threat to social harmony. Despite its critical importance, the…
Deaf and hard of hearing individuals regularly rely on captioning while watching live TV. Live TV captioning is evaluated by regulatory agencies using various caption evaluation metrics. However, caption evaluation metrics are often not…
Current neural re-rankers often struggle with complex information needs and long, content-rich documents. The fundamental issue is not computational--it is intelligent content selection: identifying what matters in lengthy, multi-faceted…
Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…
Pre-trained contextual language models such as BERT, GPT, and XLnet work quite well for document retrieval tasks. Such models are fine-tuned based on the query-document/query-passage level relevance labels to capture the ranking signals.…
In the context of investigative journalism, we address the problem of automatically identifying which claims in a given document are most worthy and should be prioritized for fact-checking. Despite its importance, this is a relatively…
It is hard to detect important articles in a specific context. Information retrieval techniques based on full text search can be inaccurate to identify main topics and they are not able to provide an indication about the importance of the…
Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations. Neural IR models have achieved promising results in learning query-document relevance patterns, but few explorations…
Audio-text relevance learning refers to learning the shared semantic properties of audio samples and textual descriptions. The standard approach uses binary relevances derived from pairs of audio samples and their human-provided captions,…
Machine learning methods have recently achieved high-performance in biomedical text analysis. However, a major bottleneck in the widespread application of these methods is obtaining the required large amounts of annotated training data,…
Weak supervision has emerged as a promising approach for rapid and large-scale dataset creation in response to the increasing demand for accelerated NLP development. By leveraging labeling functions, weak supervision allows practitioners to…
We propose InDEX, an Indonesian Idiom and Expression dataset for cloze test. The dataset contains 10438 unique sentences for 289 idioms and expressions for which we generate 15 different types of distractors, resulting in a large…
Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…
In light of the tremendous amount of data produced by social media, a large body of research have revisited the relevance estimation of the users' generated content. Most of the studies have stressed the multidimensional nature of relevance…
Currently, the quality of a search engine is often determined using so-called topical relevance, i.e., the match between the user intent (expressed as a query) and the content of the document. In this work we want to draw attention to two…
Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate this skill in fragmented settings, failing to ensure context consistency or cover the full…
Making use of off-the-shelf resources of resource-rich languages to transfer knowledge for low-resource languages raises much attention recently. The requirements of enabling the model to reach the reliable performance lack well guided,…
Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking…
Despite rapid progress in vision-language and large language models (VLMs and LLMs), their effectiveness for AI-driven educational assessment in real-world, underrepresented classrooms remains largely unexplored. We evaluate…
Natural language processing (NLP) has a significant impact on society via technologies such as machine translation and search engines. Despite its success, NLP technology is only widely available for high-resource languages such as English…