相关论文: EnsembleLink: Accurate Record Linkage Without Trai…

We present a joint model for entity-level relation extraction from documents. In contrast to other approaches - which focus on local intra-sentence mention pairs and thus require annotations on mention level - our model operates on entity…

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

An effective ranking model usually requires a large amount of training data to learn the relevance between documents and queries. User clicks are often used as training data since they can indicate relevance and are cheap to collect, but…

The cold-start issue is the challenge when we talk about recommender systems, especially in the case when we do not have the past interaction data of new users or new items. Content-based features or hybrid solutions are common as…

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible…

Quality pretraining data is often seen as the key to high-performance language models. However, progress in understanding pretraining data has been slow due to the costly pretraining runs required for data selection experiments. We present…

In a social community, multiple persons may share the same name, phone number or some other identifying attributes. This, along with other phenomena, such as name abbreviation, name misspelling, and human error leads to erroneous…

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…

Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…

Novel contexts may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature, that may not explicitly refer to entities or canonical concept forms occurring in any fact- or rule-based…

Entity matching (EM) is the problem of determining whether two records refer to same real-world entity, which is crucial in data integration, e.g., for product catalogs or address databases. A major drawback of many EM approaches is their…

Detection and disambiguation of all entities in text is a crucial task for a wide range of applications. The typical formulation of the problem involves two stages: detect mention boundaries and link all mentions to a knowledge base. For a…

Improper or erroneous labelling can pose a hindrance to reliable generalization for supervised learning. This can have negative consequences, especially for critical fields such as healthcare. We propose an effective new approach for…

Spoken Language Models (SLMs) aim to learn linguistic competence directly from speech using discrete units, widening access to Natural Language Processing (NLP) technologies for languages with limited written resources. However, progress…

The goal of entity matching is to find the corresponding records representing the same real-world entity from different data sources. At present, in the mainstream methods, rule-based entity matching methods need tremendous domain…

This paper presents an effective transfer learning framework for language adaptation in text-to-speech systems, with a focus on achieving language adaptation using minimal labeled and unlabeled data. While many works focus on reducing the…

Entity linking is the task of linking mentions of named entities in natural language text, to entities in a curated knowledge-base. This is of significant importance in the biomedical domain, where it could be used to semantically annotate…

Joint entity and relation extraction is a process that identifies entity pairs and their relations using a single model. We focus on the problem of joint extraction in distantly-labeled data, whose labels are generated by aligning entity…

We introduce SMALLTALK LM, an innovative method for training a mixture of language models in an almost asynchronous manner. Each model of the mixture specializes in distinct parts of the data distribution, without the need for…

Crowdsourcing has become a popular method for collecting labeled training data. However, in many practical scenarios traditional labeling can be difficult for crowdworkers (for example, if the data is high-dimensional or unintuitive, or the…