Related papers: SoftMatcha: A Soft and Fast Pattern Matcher for Bi…

Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language tasks through multiple rounds of reasoning and information retrieval. Most existing systems access information using a retriever that takes…

This paper is concerned with paraphrase detection. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship…

Lecture transcript translation helps learners understand online courses, however, building a high-quality lecture machine translation system lacks publicly available parallel corpora. To address this, we examine a framework for parallel…

While large language models now handle million-token contexts, their capacity for reasoning across entire document repositories remains largely untested. Existing benchmarks are inadequate, as they are mostly limited to single long texts or…

Mining large-scale high-throughput tandem mass spectrometry data sets is a very important problem in mass spectrometry based protein identification. One of the fundamental problems in large scale mining of spectra is to design appropriate…

Corpus-based set expansion (i.e., finding the "complete" set of entities belonging to the same semantic class, based on a given corpus and a tiny set of seeds) is a critical task in knowledge discovery. It may facilitate numerous downstream…

Metaphors are ubiquitous in natural language, and their detection plays an essential role in many natural language processing tasks, such as language understanding, sentiment analysis, etc. Most existing approaches for metaphor detection…

Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent…

Synthetic long-context LLM benchmarks (e.g., "needle-in-the-haystack") test only surface-level retrieval capabilities, but how well can long-context LLMs retrieve, synthesize, and reason over information across book-length inputs? We…

This work compares concept models for cross-language retrieval: First, we adapt probabilistic Latent Semantic Analysis (pLSA) for multilingual documents. Experiments with different weighting schemes show that a weighting method favoring…

Parallel texts are a relatively rare language resource, however, they constitute a very useful research material with a wide range of applications. This study presents and analyses new methodologies we developed for obtaining such data from…

Recent advances in semantic correspondence have been largely driven by the use of pre-trained large-scale models. However, a limitation of these approaches is their dependence on high-resolution input images to achieve optimal performance,…

Retrieval-augmented generation improves large language models by grounding outputs in external knowledge sources, reducing hallucinations and addressing knowledge cutoffs. However, standard embedding-based retrieval fails to capture the…

This paper develops a model that addresses sentence embedding, a hot topic in current natural language processing research, using recurrent neural networks with Long Short-Term Memory (LSTM) cells. Due to its ability to capture long term…

We explore leveraging corpus-specific vocabularies that improve both efficiency and effectiveness of learned sparse retrieval systems. We find that pre-training the underlying BERT model on the target corpus, specifically targeting…

The fine-tuning of open-source large language models (LLMs) for machine translation has recently received considerable attention, marking a shift towards data-centric research from traditional neural machine translation. However, the area…

We present an online algorithm to deal with pattern matching in strings. The problem we investigate is commonly known as string matching with mismatches in which the objective is to report the number of characters that match when a pattern…

We study the problem of semantic matching in product search, that is, given a customer query, retrieve all semantically related products from the catalog. Pure lexical matching via an inverted index falls short in this respect due to…

Word embeddings learnt from large corpora have been adopted in various applications in natural language processing and served as the general input representations to learning systems. Recently, a series of post-processing methods have been…

We present an algorithm that takes an unannotated corpus as its input, and returns a ranked list of probable morphologically related pairs as its output. The algorithm tries to discover morphologically related pairs by looking for pairs…