Related papers: Extracting Parallel Paragraphs from Common Crawl
The proliferation of the web presents an unsolved problem of automatically analyzing billions of pages of natural language. We introduce a scalable algorithm that clusters hundreds of millions of web pages into hundreds of thousands of…
Large-scale news corpora support a wide range of research in Computational Social Science and NLP, yet access remains constrained: commercial archives impose prohibitive costs and licensing restrictions, while open alternatives like Common…
Job descriptions are posted on many online channels, including company websites, job boards or social media platforms. These descriptions are usually published with varying text for the same job, due to the requirements of each platform or…
Although more and more language pairs are covered by machine translation services, there are still many pairs that lack translation resources. Cross-language information retrieval (CLIR) is an application which needs translation…
Common algorithms for sentence and word-alignment allow the automatic identification of word translations from parallel texts. This study suggests that the identification of word translations should also be possible with non-parallel and…
In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given document, the same…
The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification for an…
In this paper, we present a kernel-based learning approach for the 2018 Complex Word Identification (CWI) Shared Task. Our approach is based on combining multiple low-level features, such as character n-grams, with high-level semantic…
The amount of graph-structured data has recently experienced an enormous growth in many applications. To transform such data into useful information, fast analytics algorithms and software tools are necessary. One common graph analytics…
There are several ideas being used today for Web information retrieval, and specifically in Web search engines. The PageRank algorithm is one of those that introduce a content-neutral ranking function over Web pages. This ranking is applied…
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…
We propose a method for efficiently finding all parallel passages in a large corpus, even if the passages are not quite identical due to rephrasing and orthographic variation. The key ideas are the representation of each word in the corpus…
Commercial web search engines employ near-duplicate detection to ensure that users see each relevant result only once, albeit the underlying web crawls typically include (near-)duplicates of many web pages. We revisit the risks and…
We propose a methodology that adapts graph embedding techniques (DeepWalk (Perozzi et al., 2014) and node2vec (Grover and Leskovec, 2016)) as well as cross-lingual vector space mapping approaches (Least Squares and Canonical Correlation…
Biclustering is a two way clustering approach involving simultaneous clustering along two dimensions of the data matrix. Finding biclusters of web objects (i.e. web users and web pages) is an emerging topic in the context of web usage…
Continuous space word embeddings have received a great deal of attention in the natural language processing and machine learning communities for their ability to model term similarity and other relationships. We study the use of term…
Bipartite graphs are widely used to model relationships between entities of different types, where nodes are divided into two disjoint sets. Similarity search, a fundamental operation that retrieves nodes similar to a given query node,…
We propose graph kernels based on subgraph matchings, i.e. structure-preserving bijections between subgraphs. While recently proposed kernels based on common subgraphs (Wale et al., 2008; Shervashidze et al., 2009) in general can not be…
The increasing amount of data on the Web, in particular of Linked Data, has led to a diverse landscape of datasets, which make entity retrieval a challenging task. Explicit cross-dataset links, for instance to indicate co-references or…
The ability to match pieces of code to their corresponding natural language descriptions and vice versa is fundamental for natural language search interfaces to software repositories. In this paper, we propose a novel multi-perspective…