Related papers: Learning to Exploit Different Translation Resource…
Cross-lingual transfer (XLT) is an emergent ability of multilingual language models that preserves their performance on a task to a significant extent when evaluated in languages that were not included in the fine-tuning process. While…
Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the…
This study finds that existing information retrieval (IR) models show significant biases based on the linguistic complexity of input queries, performing well on linguistically simpler (or more complex) queries while underperforming on…
In-context machine translation (MT) with large language models (LLMs) is a promising approach for low-resource MT, as it can readily take advantage of linguistic resources such as grammar books and dictionaries. Such resources are usually…
Retrieval-Augmented Large Language Models (LLMs), which incorporate the non-parametric knowledge from external knowledge bases into LLMs, have emerged as a promising approach to enhancing response accuracy in several tasks, such as…
In this chapter, we consider generative information retrieval evaluation from two distinct but interrelated perspectives. First, large language models (LLMs) themselves are rapidly becoming tools for evaluation, with current research…
Image-Text Retrieval (ITR) is essentially a ranking problem. Given a query caption, the goal is to rank candidate images by relevance, from large to small. The current ITR datasets are constructed in a pairwise manner. Image-text pairs are…
Typically, every part in most coherent text has some plausible reason for its presence, some function that it performs to the overall semantics of the text. Rhetorical relations, e.g. contrast, cause, explanation, describe how the parts of…
Cross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts. The first step of (X)EL is candidate generation, which retrieves a list of…
Query rewriting refers to an established family of approaches that are applied to underspecified and ambiguous queries to overcome the vocabulary mismatch problem in document ranking. Queries are typically rewritten during query processing…
This work describes our two approaches for the background linking task of TREC 2020 News Track. The main objective of this task is to recommend a list of relevant articles that the reader should refer to in order to understand the context…
BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently. In the mean time, the importance and usefulness to…
This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…
Cross-lingual retrieval-augmented generation (RAG) is a critical capability for retrieving and generating answers across languages. Prior work in this context has mostly focused on generation and relied on benchmarks derived from…
Several widely used software applications involve some form of processing of natural language, with tasks ranging from digitising hardcopies and text processing to speech generation. Varied language resources are used to develop software…
Selecting high-quality pre-training data is important for creating capable language models, but existing methods rely on simple heuristics. We introduce QuRating, a method for selecting pre-training data that can capture human intuitions…
Considering query variance in information retrieval (IR) experiments is beneficial for retrieval effectiveness. Especially ranking ensembles based on different topically related queries retrieve better results than rankings based on a…
Search engines are the most commonly used type of tool for finding relevant information on the Internet. However, today's search engines are far from perfect. Typical search queries are short, often one or two words, and can be ambiguous…
Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…
The rise of large language models (LLMs) has significantly transformed both the construction and application of information retrieval (IR) systems. However, current interactions between IR systems and LLMs remain limited, with LLMs merely…