An official website of the United States government
This tutorial targets researchers and practitioners who are interested in ML technologies for NLP from indirect supervision. In particular, we will present a diverse thread of indirect supervision studies that try to answer the following questions: (i) when and how can we provide supervision for a target task T, if all we have is data that corresponds to a “related” task T′? (ii) humans do not use exhaustive supervision; they rely on occasional feedback, and learn from incidental signals from various sources; how can we effectively incorporate such supervision in machine learning? (iii) how can we leverage multi-modal supervision to help NLP? To the end, we will discuss several lines of research that address those challenges, including (i) indirect supervision from T ′ that handles T with outputs spanning from a moderate size to an open space, (ii) the use of sparsely occurring and incidental signals, such as partial labels, noisy labels, knowledge-based constraints, and cross-domain or cross-task annotations—all having statistical associations with the task, (iii) principled ways to measure and understand why these incidental signals can contribute to our target tasks, and (iv) indirect supervision from vision-language signals. We will conclude the tutorial by outlining directions for further investigation.
more »
« less
New Frontiers of Information Extraction
This tutorial targets researchers and practitioners who are interested in AI and ML technologies for structural information extraction (IE) from unstructured textual sources. Particularly, this tutorial will provide audience with a systematic introduction to recent advances of IE, by answering several important research questions. These questions include (i) how to develop an robust IE system from noisy, insufficient training data, while ensuring the reliability of its prediction? (ii) how to foster the generalizability of IE through enhancing the system’s cross-lingual, cross-domain, cross-task and cross-modal transferability? (iii) how to precisely support extracting structural information with extremely fine-grained, diverse and boundless labels? (iv) how to further improve IE by leveraging indirect supervision from other NLP tasks, such as NLI, QA or summarization, and pre-trained language models? (v) how to acquire knowledge to guide the inference of IE systems? We will discuss several lines of frontier research that tackle those challenges, and will conclude the tutorial by outlining directions for further investigation.
more »
« less
- Award ID(s):
- 2105329
- PAR ID:
- 10343363
- Date Published:
- Journal Name:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorials
- Page Range / eLocation ID:
- 14 to 25
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Modeling how people interact with search interfaces is core to the field of Interactive Information Retrieval. While various models have been proposed ranging from conceptual (e.g., Belkin’s ASK[12], Berry picking[11], Everyday-life information seeking, etc.) to theoretical (e.g., Information foraging theory[50], Economic theory[4], etc.), more recently there has been a body of working explore how people’s biases and the heuristics that they take influence how they search. This has led to the development of new models of the search process drawing upon Behavioural Economics and Psychology. This half day tutorial will provide a starting point for researchers seeking to learn more about information searching under uncertainty. The tutorial will be structured into two parts. First, we will provide an introduction of the biases and heuristics program put forward by Tversky and Kahneman [59] which assumes that people are not always rational. The second part of the tutorial will provide an overview of the types and space of biases in search [6, 42], before doing a deep dive into several specific examples and the impact of biases on different types of decisions (e.g., health/medical, financial etc.). The tutorial will wrap up with a discussion of some of the practical implication for how we can better design and evaluate IR systems in the light of cognitive biases.more » « less
-
This tutorial will provide an overview of recent advances on neuro- symbolic approaches for information retrieval. A decade ago, knowl- edge graphs and semantic annotations technology led to active research on how to best leverage symbolic knowledge. At the same time, neural methods have demonstrated to be versatile and highly effective. From a neural network perspective, the same representation approach can service document ranking or knowledge graph rea- soning. End-to-end training allows to optimize complex methods for downstream tasks. We are at the point where both the symbolic and the neural research advances are coalescing into neuro-symbolic approaches. The underlying research questions are how to best combine sym- bolic and neural approaches, what kind of symbolic/neural ap- proaches are most suitable for which use case, and how to best integrate both ideas to advance the state of the art in information retrieval. Materials are available online: https://github.com/laura-dietz/ neurosymbolic-representations-for-IRmore » « less
-
This tutorial will provide an overview of recent advances on neuro-symbolic approaches for information retrieval. A decade ago, knowledge graphs and semantic annotations technology led to active re- search on how to best leverage symbolic knowledge. At the same time, neural methods have demonstrated to be versatile and highly effective. From a neural network perspective, the same representation approach can service document ranking or knowledge graph reasoning. End-to-end training allows to optimize complex methods for downstream tasks. We are at the point where both the symbolic and the neural research advances are coalescing into neuro-symbolic approaches. The underlying research questions are how to best combine symbolic and neural ap- proaches, what kind of symbolic/neural approaches are most suitable for which use case, and how to best integrate both ideas to advance the state of the art in information retrieval.more » « less
-
Understanding how people interact with search interfaces is core to the field of Interactive Information Retrieval (IIR). While various models have been proposed (e.g., Belkin's ASK, Berry picking, Everyday-life information seeking, Information foraging theory, Economic theory, etc.), they have largely ignored the impact of cognitive biases on search behaviour and performance. A growing body of empirical work exploring how people's cognitive biases influence search and judgments, has led to the development of new models of search that draw upon Behavioural Economics and Psychology. This full day tutorial will provide a starting point for researchers seeking to learn more about information seeking, search and retrieval under uncertainty. The tutorial will be structured into three parts. First, we will provide an introduction of the biases and heuristics program put forward by Tversky and Kahneman [60] (1974) which assumes that people are not always rational. The second part of the tutorial will provide an overview of the types and space of biases in search,[5, 40] before doing a deep dive into several specific examples and the impact of biases on different types of decisions (e.g., health/medical, financial). The third part will focus on a discussion of the practical implication regarding the design and evaluation human-centered IR systems in the light of cognitive biases - where participants will undertake some hands-on exercises.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2022.naacl-tutorials.3
