Related papers: From Paraphrase Database to Compositional Paraphra…
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…
As Large language models (LLMs) are increasingly deployed in diverse applications, faithfully integrating evolving factual knowledge into these models remains a critical challenge. Continued pre-training on paraphrased data has shown…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i.e., texts with the same "message") and to create and analyze a corresponding dataset. When an image is reused on the Web, an original…
Keyphrase extraction is the task of finding several interesting phrases in a text document, which provide a list of the main topics within the document. Most existing graph-based models use co-occurrence links as cohesion indicators to…
Paraphrase generation is a long-standing task in natural language processing (NLP). Supervised paraphrase generation models, which rely on human-annotated paraphrase pairs, are cost-inefficient and hard to scale up. On the other hand,…
We present EntropyDB, an interactive data exploration system that uses a probabilistic approach to generate a small, query-able summary of a dataset. Departing from traditional summarization techniques, we use the Principle of Maximum…
Sentence embedding models play a key role in various Natural Language Processing tasks, such as in Topic Modeling, Document Clustering and Recommendation Systems. However, these models rely heavily on parallel data, which can be scarce for…
Distributed language representation has become the most widely used technique for language representation in various natural language processing tasks. Most of the natural language processing models that are based on deep learning…
There are massive amounts of textual data residing in databases, valuable for many machine learning (ML) tasks. Since ML techniques depend on numerical input representations, word embeddings are increasingly utilized to convert symbolic…
Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against…
We develop a methodology for analyzing language model task performance at the individual example level based on training data density estimation. Experiments with paraphrasing as a controlled intervention on finetuning data demonstrate that…
Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it…
In this paper we present the approach of introducing thesaurus knowledge into probabilistic topic models. The main idea of the approach is based on the assumption that the frequencies of semantically related words and phrases, which are met…
Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using…
Semantic sentence embeddings are usually supervisedly built minimizing distances between pairs of embeddings of sentences labelled as semantically similar by annotators. Since big labelled datasets are rare, in particular for non-English…
Compound nouns such as example noun compound are becoming more common in natural language and pose a number of difficult problems for NLP systems, notably increasing the complexity of parsing. In this paper we develop a probabilistic model…
In noisy environments, speech can be hard to understand for humans. Spoken dialog systems can help to enhance the intelligibility of their output, either by modifying the speech synthesis (e.g., imitate Lombard speech) or by optimizing the…
Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not…
Embedding-based retrieval aims to learn a shared semantic representation space for both queries and items, enabling efficient and effective item retrieval through approximate nearest neighbor (ANN) algorithms. In current industrial…