Weak Supervision for Learning Discourse Structure

Badene, Sonia; Thompson, Kate; Lorré, Jean-Pierre; Asher, Nicholas

doi:10.18653/v1/d19-1234

Cited by 7 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various weak supervision approaches can be represented by labelling functions, such as distant supervision, heuristics or the results of crowd-sourcing annotations. Weak supervision has already been successfully applied in other problems in the area of natural language processing and information retrieval [4,13,16]. In this paper, we focus on the usage of heuristics to create the labelling functions for intent classification.…”

Section: Weak Supervisionmentioning

confidence: 99%

ORCAS-I: Queries Annotated with Intent using Weak Supervision

Alexander,

Kusa,

de Vries

2022

Preprint

View full text Add to dashboard Cite

User intent classification is an important task in information retrieval. In this work, we introduce a revised taxonomy of user intent. We take the widely used differentiation between navigational, transactional and informational queries as a starting point, and identify three different sub-classes for the informational queries: instrumental, factual and abstain. The resulting classification of user queries is more fine-grained, reaches a high level of consistency between annotators, and can serve as the basis for an effective automatic classification process. The newly introduced categories help distinguish between types of queries that a retrieval system could act upon, for example by prioritizing different types of results in the ranking.We have used a weak supervision approach based on Snorkel to annotate the ORCAS dataset according to our new user intent taxonomy, utilising established heuristics and keywords to construct rules for the prediction of the intent category. We then present a series of experiments with a variety of machine learning models, using the labels from the weak supervision stage as training data, but find that the results produced by Snorkel are not outperformed by these competing approaches and can be considered state-of-theart. The advantage of a rule-based approach like Snorkel's is its efficient deployment in an actual system, where intent classification would be executed for every query issued.The resource released with this paper is the ORCAS-I dataset: a labelled version of the ORCAS click-based dataset of Web queries, which provides 18 million connections to 10 million distinct queries. We anticipate the usage of this resource in a scenario where the retrieval system would change its internal workings and search user interface to match the type of information request. For example, a navigational query could trigger just a short result list; and, for instrumental intent the system could rank tutorials and instructions higher than for other types of queries.

show abstract

Section: Weak Supervisionmentioning

confidence: 99%

ORCAS-I: Queries Annotated with Intent using Weak Supervision

Alexander,

Kusa,

de Vries

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Our approach is based on the data-programming paradigm (Ratner et al, 2016), a weak supervision framework that has been applied mainly to information extraction problems in NLP, but also recently to discourse analysis (Badene et al, 2019), specifically for discourse structure prediction. We are unaware of similar work on discourse segmentation or on multi-modal text/speech classification problems.…”

Section: Related Workmentioning

confidence: 99%

Weakly supervised discourse segmentation for multiparty oral conversations

Gravellier¹,

Hunter²,

Muller³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Discourse segmentation, the first step of discourse analysis, has been shown to improve results for text summarization, translation and other NLP tasks. While segmentation models for written text tend to perform well, they are not directly applicable to spontaneous, oral conversation, which has linguistic features foreign to written text. Segmentation is less studied for this type of language, where annotated data is scarce, and existing corpora more heterogeneous. We develop a weak supervision approach to adapt, using minimal annotation, a state of the art discourse segmenter trained on written text to French conversation transcripts. Supervision is given by a latent model bootstrapped by manually defined heuristic rules that use linguistic and acoustic information. The resulting model improves the original segmenter, especially in contexts where information on speaker turns is lacking or noisy, gaining up to 13% in F-score. Evaluation is performed on data like those used to define our heuristic rules, but also on transcripts from two other corpora.

show abstract

“…Weak supervision is another approach for the curation of data for model training [36,46]. Weakly supervised learning is an umbrella term for a family of techniques for the mitigation of data scarcity.…”

Section: Weakly Supervised Learningmentioning

confidence: 99%

Return on Investment in Machine Learning: Crossing the Chasm between Academia and Business

Mizgajski

Szymczak

Morzy

et al. 2020

Foundations of Computing and Decision Sciences

View full text Add to dashboard Cite

Academia remains the central place of machine learning education. While academic culture is the predominant factor influencing the way we teach machine learning to students, many practitioners question this culture, claiming the lack of alignment between academic and business environments. Drawing on professional experiences from both sides of the chasm, we describe the main points of contention, in the hope that it will help better align academic syllabi with the expectations towards future machine learning practitioners. We also provide recommendations for teaching of the applied aspects of machine learning.

show abstract

Weak Supervision for Learning Discourse Structure

Cited by 7 publications

References 19 publications

ORCAS-I: Queries Annotated with Intent using Weak Supervision

ORCAS-I: Queries Annotated with Intent using Weak Supervision

Weakly supervised discourse segmentation for multiparty oral conversations

Return on Investment in Machine Learning: Crossing the Chasm between Academia and Business

Contact Info

Product

Resources

About