Weak Supervision

We present a new approach to relation ex- traction that requires only a handful of train- ing examples. Given a few pairs of named entities known to exhibit or not …...

Much previous work has investigated weak supervision with HMMs and tag dictionar- ies for part-of-speech tagging, but there have been no similar investigations for the harder problem of supertagging. Here, …...

Information extraction (IE) holds the promise of generating a large-scale knowledge base from the Web’s natural language text. Knowledge-based weak supervision, using structured data to heuristically label a training corpus, …...

We present a method for training a semantic parser using only a knowledge base and an un- labeled text corpus, without any individually annotated sentences. Our key observation is that …...

AbstractThe context in which language is used provides a strong signal for learning to recover its meaning. In this paper, we show it can be used within a grounded CCG …...

A promising approach to relation extrac- tion, called weak or distant supervision, exploits an existing database of facts as training data, by aligning it to an unla- beled collection of …...

Correctly predicting abbreviations given the full forms is important in many natu- ral language processing systems. In this paper we propose a two-stage method to find the corresponding abbreviation given …...

AbstractThis paper investigates the advantages and limits of data programming for the task of learning discourse structure. The data programming paradigm implemented in the Snorkel framework allows a user to …...

AbstractIn many machine learning scenarios, supervision by gold labels is not available and conse quently neural models cannot be trained directly by maximum likelihood estimation. In a weak supervision scenario, …...

AbstractEntity normalization (or entity linking) is an important subtask of information extraction that links entity mentions in text to categories or concepts in a reference vocabulary. Machine learning based normalization …...

AbstractStructured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation. Learning the implicit structured representations of entity names without context and external …...

AbstractNamed Entity Recognition (NER) performance often degrades rapidly when applied to target domains that differ from the texts observed during training. When in-domain labelled data is available, transfer learning techniques …...

AbstractFor many prediction tasks, stakeholders desire not only predictions but also supporting evidence that a human can use to verify its correctness. However, in practice, evidence annotations may only be …...

AbstractTask-oriented dialogue systems typically require manual annotation of dialogue slots in training data, which is costly to obtain. We propose a method that eliminates this requirement: We use weak supervision …...

AbstractDetection of toxic spans - detecting toxicity of contents in the granularity of tokens - is crucial for effective moderation of online discussions. The baseline approach for this problem using …...

AbstractFine-tuned pre-trained language models (LMs) have achieved enormous success in many natural language processing (NLP) tasks, but they still require excessive labeled data in the fine-tuning stage. We study the …...

Weakly supervised methods estimate the la- bels for a dataset using the predictions of sev- eral noisy supervision sources. Many machine learning practitioners have begun using weak supervision to more …...

AbstractWeak supervision has shown promising results in many natural language processing tasks, such as Named Entity Recognition (NER). Existing work mainly focuses on learning deep NER models only with weak …...

The paradigm of data programming, which uses weak supervision in the form of rules/labelling functions, and semi-supervised learning, which augments small amounts of labelled data with a large unlabelled dataset, …...

AbstractWe study the problem of building entity tagging systems by using a few rules as weak supervision. Previous methods mostly focus on disambiguating entity types based on contexts and expert-provided …...

AbstractIn this paper, we explore text classification with extremely weak supervision, i.e., only relying on the surface text of class names. This is a more challenging setting than the seed-driven …...

AbstractPredicting difficulty of questions is crucial for technical interviews. However, such questions are long-form and more open-ended than factoid and multiple choice questions explored so far for question difficulty prediction. …...

AbstractWe introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, …...

This paper presents a new human-in-the- loop text classification framework with no labeled data incorporating weak supervision and Bayesian active learning with a seman- tic clustering constraint. Labeling function (LF)-based …...

AbstractWord and morpheme segmentation are fundamental steps of language documentation as they allow to discover lexical units in a language for which the lexicon is unknown. However, in most language …...

AbstractFor the task of fine-grained entity typing (FET), due to the use of a large number of entity types, it is usually considered too costly to manually annotating a training …...

AbstractLanguage documentation often requires segmenting transcriptions of utterances collected on the field into words and morphemes. While these two tasks are typically performed in succession, we study here Bayesian models …...