Related papers: Unsupervised, Efficient and Semantic Expertise Ret…

Language segmentation consists in finding the boundaries where one language ends and another language begins in a text written in more than one language. This is important for all natural language processing tasks. The problem can be solved…

Search queries with superlatives (e.g., best, most popular) require comparing candidates across multiple dimensions, demanding linguistic understanding and domain knowledge. We show that LLMs can uncover latent intent behind these…

Translated texts are distinctively different from original ones, to the extent that supervised text classification methods can distinguish between them with high accuracy. These differences were proven useful for statistical machine…

Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and…

We propose a method to learn unsupervised sentence representations in a non-compositional manner based on Generative Latent Optimization. Our approach does not impose any assumptions on how words are to be combined into a sentence…

Relation extraction is an important but challenging task that aims to extract all hidden relational facts from the text. With the development of deep language models, relation extraction methods have achieved good performance on various…

Semantic similarity based retrieval is playing an increasingly important role in many IR systems such as modern web search, question-answering, similar document retrieval etc. Improvements in retrieval of semantically similar content are…

Generative retrieval shed light on a new paradigm of document retrieval, aiming to directly generate the identifier of a relevant document for a query. While it takes advantage of bypassing the construction of auxiliary index structures,…

In this paper, an Eliteness Hypothesis for information retrieval is proposed, where we define two generative processes to create information items and queries. By assuming the deterministic relationships between the eliteness of terms and…

Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are…

The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the…

BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning…

Automatic sentence summarization produces a shorter version of a sentence, while preserving its most important information. A good summary is characterized by language fluency and high information overlap with the source sentence. We model…

Large language models (LLMs) are currently applied to scientific paper evaluation by assigning an absolute score to each paper independently. However, since score scales vary across conferences, time periods, and evaluation criteria, models…

The paper presents a first attempt towards unsupervised neural text simplification that relies only on unlabeled text corpora. The core framework is composed of a shared encoder and a pair of attentional-decoders and gains knowledge of…

Knowledge discovery is hindered by the increasing volume of publications and the scarcity of extensive annotated data. To tackle the challenge of information overload, it is essential to employ automated methods for knowledge extraction and…

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We…

Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks. To extend the benefits of disentangled representations to more complex…

Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle…

Unsupervised approaches to extractive summarization usually rely on a notion of sentence importance defined by the semantic similarity between a sentence and the document. We propose new metrics of relevance and redundancy using pointwise…