NLP Highlights
146 episodes - English - Latest episode: 3 months ago - ★★★★★ - 21 ratings**The podcast is currently on hiatus. For more active NLP content, check out the Holistic Intelligence Podcast linked below.**
Welcome to the NLP highlights podcast, where we invite researchers to talk about their work in various areas in natural language processing. All views expressed belong to the hosts/guests, and do not represent their employers.
Homepage Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Episodes
Are LLMs safe?
February 29, 2024 22:57 - 42 minutes - 4.83 GBCurious about the safety of LLMs? 🤔 Join us for an insightful new episode featuring Suchin Gururangan, Young Investigator at Allen Institute for Artificial Intelligence and Data Science Engineer at Appuri. 🚀 Don't miss out on expert insights into the world of LLMs!
"Imaginative AI" with Mohamed Elhoseiny
January 08, 2024 16:31 - 23 minutes - 2.91 GBThis podcast episode features Dr. Mohamed Elhoseiny, a true luminary in the realm of computer vision with over a decade of groundbreaking research. As an Assistant Professor at KAUST, Dr. Elhoseiny's work delves into the intersections of Computer Vision, Language & Vision, and Computational Creativity in Art, Fashion, and AI. Notably, he co-organized the 1st and 2nd Workshops on Closing the Loop between Vision and Language, demonstrating his commitment to advancing interdisciplinary research....
142 - Science Of Science, with Kyle Lo
December 28, 2023 02:39 - 48 minutes - 3.74 GBOur first guest with this new format is Kyle Lo, the most senior lead scientist in the Semantic Scholar team at Allen Institute for AI (AI2), who kindly agreed to share his perspective on #Science of #Science (#scisci) on our podcast. SciSci is concerned with studying how people do science, and includes developing methods and tools to help people consume AND produce science. Kyle has made several critical contributions in this field which enabled a lot of SciSci work over the past 5+ years, r...
141 - Building an open source LM, with Iz Beltagy and Dirk Groeneveld
June 29, 2023 19:41 - 29 minutes - 67.7 MBIn this special episode of NLP Highlights, we discussed building and open sourcing language models. What is the usual recipe for building large language models? What does it mean to open source them? What new research questions can we answer by open sourcing them? We particularly focused on the ongoing Open Language Model (OLMo) project at AI2, and invited Iz Beltagy and Dirk Groeneveld, the research and engineering leads of the OLMo project to chat. Blog post announcing OLMo: https://blog.a...
140 - Generative AI and Copyright, with Chris Callison-Burch
June 06, 2023 00:00 - 51 minutes - 70.6 MBIn this special episode, we chatted with Chris Callison-Burch about his testimony in the recent U.S. Congress Hearing on the Interoperability of AI and Copyright Law. We started by asking Chris about the purpose and the structure of this hearing. Then we talked about the ongoing discussion on how the copyright law is applicable to content generated by AI systems, the potential risks generative AI poses to artists, and Chris’ take on all of this. We end the episode with a recording of Chris’ o...
139 - Coherent Long Story Generation, with Kevin Yang
March 24, 2023 16:42 - 45 minutes - 104 MBHow can we generate coherent long stories from language models? Ensuring that the generated story has long range consistency and that it conforms to a high level plan is typically challenging. In this episode, Kevin Yang describes their system that prompts language models to first generate an outline, and iteratively generate the story while following the outline and reranking and editing the outputs for coherence. We also discussed the challenges involved in evaluating long generated texts. ...
138 - Compositional Generalization in Neural Networks, with Najoung Kim
January 20, 2023 17:53 - 48 minutes - 44.2 MBCompositional generalization refers to the capability of models to generalize to out-of-distribution instances by composing information obtained from the training data. In this episode we chatted with Najoung Kim, on how to explicitly evaluate specific kinds of compositional generalization in neural network models of language. Najoung described COGS, a dataset she built for this, some recent results in the space, and why we should be careful about interpreting the results given the current pr...
137 - Nearest Neighbor Language Modeling and Machine Translation, with Urvashi Khandelwal
January 13, 2023 22:59 - 35 minutes - 32.8 MBWe invited Urvashi Khandelwal, a research scientist at Google Brain to talk about nearest neighbor language and machine translation models. These models interpolate parametric (conditional) language models with non-parametric distributions over the closest values in some data stores built from relevant data. Not only are these models shown to outperform the usual parametric language models, they also have important implications on memorization and generalization in language models. Urvashi's...
136 - Including Signed Languages in NLP, with Kayo Yin and Malihe Alikhani
May 19, 2022 18:39 - 1 hour - 56.9 MBIn this episode, we talk with Kayo Yin, an incoming PhD at Berkeley, and Malihe Alikhani, an assistant professor at the University of Pittsburgh, about opportunities for the NLP community to contribute to Sign Language Processing (SLP). We talked about history and misconceptions about sign languages, high-level similarities and differences between spoken and sign languages, distinct linguistic features of signed languages, representations, computational resources, SLP tasks, and suggestions f...
135 - PhD Application Series: After Submitting Applications
March 02, 2022 21:56 - 36 minutes - 29.2 MBThis episode is the third in our current series on PhD applications. We talk about what the PhD application process looks like after applications are submitted. We start with a general overview of the timeline, then talk about how to approach interviews and conversations with faculty, and finish by discussing the different factors to consider in deciding between programs. The guests for this episode are Rada Mihalcea (Professor at the University of Michigan), Aishwarya Kamath (PhD student a...
134 - PhD Application Series: PhDs in Europe versus the US, with Barbara Plank and Gonçalo Correia
October 19, 2021 17:16 - 38 minutes - 35.2 MBThis episode is the second in our current series on PhD applications. How do PhD programs in Europe differ from PhD programs in the US, and how should people decide between them? In this episode, we invite Barbara Plank (Professor at ITU, IT University of Copenhagen) and Gonçalo Correia (ELLIS PhD student at University of Lisbon and University of Amsterdam) to share their perspectives on this question. We start by talking about the main differences between pursuing a PhD in Europe and the U...
134 - PhD Application Series: PhDs in Europe versus the US
October 19, 2021 17:16 - 38 minutes - 35.2 MBThis episode is the second in our current series on PhD applications. How do PhD programs in Europe differ from PhD programs in the US, and how should people decide between them? In this episode, we invite Barbara Plank (Professor at ITU, IT University of Copenhagen) and Gonçalo Correia (ELLIS PhD student at University of Lisbon and University of Amsterdam) to share their perspectives on this question. We start by talking about the main differences between pursuing a PhD in Europe and the U...
133 - PhD Application Series: Preparing Application Materials, with Nathan Schneider and Roma Patel
October 06, 2021 00:32 - 43 minutes - 40.1 MBThis episode is the first in our current series on PhD applications. How should people prepare their applications to PhD programs in NLP? In this episode, we invite Nathan Schneider (Professor of Linguistics and Computer Science at Georgetown University) and Roma Patel (PhD student in Computer Science at Brown University) to share their perspectives on preparing application materials. We start by talking about what factors should go into the decision to apply for PhD programs and how to gai...
132 - Alexa Prize Socialbot Grand Challenge and Alquist 4.0, with Petr Marek
September 27, 2021 22:22 - 41 minutes - 38.1 MBIn this episode, we discussed the Alexa Prize Socialbot Grand Challenge and this year's winning submission, Alquist 4.0, with Petr Marek, a member of the winning team. Petr gave us an overview of their submission, the design choices that led to them winning the competition, including combining a hardcoded dialog tree and a neural generator model and extracting implicit personal information about users from their responses, and some outstanding challenges. Petr Marek is a PhD student at the C...
131 - Opportunities and Barriers between HCI and NLP, with Nanna Inie and Leon Derczynski
August 20, 2021 21:40 - 46 minutes - 42.8 MBWhat can NLP researchers learn from Human Computer Interaction (HCI) research? We chatted with Nanna Inie and Leon Derczynski to find out. We discussed HCI's research processes including methods of inquiry, the data annotation processes used in HCI, and how they are different from NLP, and the cognitive methods used in HCI for qualitative error analyses. We also briefly talked about the opportunities the field of HCI presents for NLP researchers. This discussion is based on the following pap...
130 - Linking human cognitive patterns to NLP Models, with Lisa Beinborn
August 09, 2021 16:23 - 44 minutes - 40.2 MBIn this episode, we talk with Lisa Beinborn, an assistant professor at Vrije Universiteit Amsterdam, about how to use human cognitive signals to improve and analyze NLP models. We start by discussing different kinds of cognitive signals—eye-tracking, EEG, MEG, and fMRI—and challenges associated with using them. We then turn to Lisa’s recent work connecting interpretability measures with eye-tracking data, which reflect the relative importance measures of different tokens in human reading comp...
129 - Transformers and Hierarchical Structure, with Shunyu Yao
July 02, 2021 20:19 - 35 minutes - 23.4 MBIn this episode, we talk to Shunyu Yao about recent insights into how transformers can represent hierarchical structure in language. Bounded-depth hierarchical structure is thought to be a key feature of natural languages, motivating Shunyu and his coauthors to show that transformers can efficiently represent bounded-depth Dyck languages, which can be thought of as a formal model of the structure of natural languages. We went on to discuss some of the intuitive ideas that emerge from the proo...
128 - Dynamic Benchmarking, with Douwe Kiela
June 19, 2021 00:40 - 47 minutes - 42.9 MBWe discussed adversarial dataset construction and dynamic benchmarking in this episode with Douwe Kiela, a research scientist at Facebook AI Research who has been working on a dynamic benchmarking platform called Dynabench. Dynamic benchmarking tries to address the issue of many recent datasets getting solved with little progress being made towards solving the corresponding tasks. The idea is to involve models in the data collection loop to encourage humans to provide data points that are har...
127 - Masakhane and Participatory Research for African Languages, with Tosin Adewumi and Perez Ogayo
June 08, 2021 21:48 - 47 minutes - 64.9 MBWe invited members of Masakhane, Tosin Adewumi and Perez Ogayo, to talk about their EMNLP Findings paper that discusses why typical research is limited for low-resourced NLP and how participatory research can help. As a result of participatory research, Masakhane has many, many success stories: first datasets and benchmarks in African languages, first research on human evaluation specifically for MT for low-resource languages, etc. In this episode, we talked about one of them—MasakhaNER—in...
126 - Optimizing Continuous Prompts for Generation, with Lisa Li
May 24, 2021 17:42 - 47 minutes - 43.5 MBWe invited Lisa Li to talk about her recent work, Prefix-Tuning: Optimizing Continuous Prompts for Generation. Prefix tuning is a lightweight alternative to finetuning, and the idea is to tune only a fixed-length task-specific continuous vector, and to keep the pretrained transformer parameters frozen. We discussed how prefix tuning compares with finetuning and other efficient alternatives on two tasks in various experimental settings, and in what scenarios prefix tuning is preferable. Lisa ...
125 - VQA for Real Users, with Danna Gurari
May 04, 2021 00:51 - 42 minutes - 38.5 MBHow can we build Visual Question Answering systems for real users? For this episode, we chatted with Danna Gurari, about her work in building datasets and models towards VQA for people who are blind. We talked about the differences between the existing datasets, and Vizwiz, a dataset built by Gurari et al., and the resulting algorithmic changes. We also discussed the unsolved challenges in this field, and the new tasks they result in. Danna Gurari is an Assistant Professor as well as Foundin...
124 - Semantic Machines and Task-Oriented Dialog, with Jayant Krishnamurthy and Hao Fang
April 14, 2021 00:12 - 45 minutes - 41.7 MBWe invited Jayant Krishnamurthy and Hao Fang, researchers at Microsoft Semantic Machines to discuss their platform for building task-oriented dialog systems, and their recent TACL paper on the topic. The paper introduces a new formalism for task-oriented dialog to effectively handle references and revisions in complex dialog, and a large realistic dataset that uses this formalism. Leaderboard associated with the dataset: https://microsoft.github.io/task_oriented_dialogue_as_dataflow_synthesi...
123 - Robust NLP, with Robin Jia
April 05, 2021 22:56 - 47 minutes - 43.8 MBIn this episode, Robin Jia talks about how to build robust NLP systems. We discuss the different senses in which a system can be robust, reasons to care about system robustness, and the challenges involved in evaluating robustness of NLP models. We talk about how to build certifiably robust models through interval bound propagation and discrete encoding functions, as well as how to modify data collection procedures through active learning for more robust model development. Robin Jia is curre...
122 - Statutory Reasoning in Tax Law, with Nils Holzenberger
November 12, 2020 01:10 - 46 minutes - 42.3 MBWe invited Nils Holzenberger, a PhD student at JHU to talk about a dataset involving statutory reasoning in tax law Holzenberger et al. released recently. This dataset includes difficult textual entailment and question answering problems that involve reasoning about how sections in tax law are applicable to specific cases. They also released a Prolog solver that fully solves the problems, and show that learned models using dense representations of text perform poorly. We discussed why this is...
121 - Language and the Brain, with Alona Fyshe
October 30, 2020 17:41 - 42 minutes - 38.9 MBWe invited Alona Fyshe to talk about the link between NLP and the human brain. We began by talking about what we currently know about the connection between representations used in NLP and representations recorded in the brain. We also discussed how different brain imaging techniques compare to each other. We then dove into experiments investigating how hidden states of LSTM language models correlate with EEG brain imaging data on three types of language inputs: well-formed grammatical senten...
120 - Evaluation of Text Generation, with Asli Celikyilmaz
October 03, 2020 00:36 - 55 minutes - 50.4 MBWe invited Asli Celikyilmaz for this episode to talk about evaluation of text generation systems. We discussed the challenges in evaluating generated text, and covered human and automated metrics, with a discussion of recent developments in learning metrics. We also talked about some open research questions, including the difficulties in evaluating factual correctness of generated text. Asli Celikyilmaz is a Principal Researcher at Microsoft Research. Link to a survey co-authored by Asli on ...
119 - Social NLP, with Diyi Yang
September 03, 2020 22:26 - 53 minutes - 48.9 MBIn this episode, Diyi Yang gives us an overview of using NLP models for social applications, including understanding social relationships, processes, roles, and power. As NLP systems are getting used more and more in the real world, they additionally have increasing social impacts that must be studied. We talk about how to get started in this field, what datasets exist and are commonly used, and potential ethical issues. We additionally cover two of Diyi's recent papers, on neutralizing su...
118 - Coreference Resolution, with Marta Recasens
August 26, 2020 21:53 - 47 minutes - 43.4 MBIn this episode, we talked about Coreference Resolution with Marta Recasens, a Research Scientist at Google. We discussed the complexity involved in resolving references in language, the simplification of the problem that the NLP community has focused on by talking about specific datasets, and the complex coreference phenomena that are not yet captured in those datasets. We also briefly talked about how coreference is handled in languages other than English, and how some of the notions we hav...
117 - Interpreting NLP Model Predictions, with Sameer Singh
August 13, 2020 00:41 - 56 minutes - 52 MBWe interviewed Sameer Singh for this episode, and discussed an overview of recent work in interpreting NLP model predictions, particularly instance-level interpretations. We started out by talking about why it is important to interpret model outputs and why it is a hard problem. We then dove into the details of three kinds of interpretation techniques: attribution based methods, interpretation using influence functions, and generating explanations. Towards the end, we spent some time discussi...
116 - Grounded Language Understanding, with Yonatan Bisk
July 03, 2020 01:13 - 59 minutes - 54.3 MBWe invited Yonatan Bisk to talk about grounded language understanding. We started off by discussing an overview of the topic, its research goals, and the the challenges involved. In the latter half of the conversation, we talked about ALFRED (Shridhar et al., 2019), a grounded instruction following benchmark that simulates training a robot butler. The current best models built for this benchmark perform very poorly compared to humans. We discussed why that might be, and what could be done to ...
115 - AllenNLP, interviewing Matt Gardner
June 17, 2020 20:16 - 33 minutes - 30.5 MBIn this special episode, Carissa Schoenick, a program manager and communications director at AI2 interviewed Matt Gardner about AllenNLP. We chatted about the origins of AllenNLP, the early challenges in building it, and the design decisions behind the library. Given the release of AllenNLP 1.0 this week, we asked Matt what users can expect from the new release, what improvements the AllenNLP team is working on for the future versions.
114 - Behavioral Testing of NLP Models, with Marco Tulio Ribeiro
May 26, 2020 22:15 - 43 minutes - 39.8 MBWe invited Marco Tulio Ribeiro, a Senior Researcher at Microsoft, to talk about evaluating NLP models using behavioral testing, a framework borrowed from Software Engineering. Marco describes three kinds of black-box tests the check whether NLP models satisfy certain necessary conditions. While breaking the standard IID assumption, this framework presents a way to evaluate whether NLP systems are ready for real-world use. We also discuss what capabilities can be tested using this framework, h...
113 - Managing Industry Research Teams, with Fernando Pereira
May 22, 2020 21:41 - 42 minutes - 38.7 MBWe invited Fernando Pereira, a VP and Distinguished Engineer at Google, where he leads NLU and ML research, to talk about managing NLP research teams in industry. Topics we discussed include prioritizing research against product development and effective collaboration with product teams, dealing with potential research interest mismatch between individuals and the company, managing publications, hiring new researchers, and diversity and inclusion.
112 - Alignment of Multilingual Contextual Representations, with Steven Cao
May 13, 2020 20:25 - 33 minutes - 30.4 MBWe invited Steven Cao to talk about his paper on multilingual alignment of contextual word embeddings. We started by discussing how multilingual transformers work in general, and then focus on Steven’s work on aligning word representations. The core idea is to start from a list of words automatically aligned from parallel corpora and to ensure the representations of the aligned words are similar to each other while not moving too far away from their original representations. We discussed the ...
111 - Typologically diverse, multi-lingual, information-seeking questions, with Jon Clark
April 27, 2020 15:21 - 38 minutes - 35.2 MBWe invited Jon Clark from Google to talk about TyDi QA, a new question answering dataset, for this episode. The dataset contains information seeking questions in 11 languages that are typologically diverse, i.e., they differ from each other in terms of key structural and functional features. The questions in TyDiQA are information-seeking, like those in Natural Questions, which we discussed in the previous episode. In addition, TyDiQA also has questions collected in multiple languages using i...
110 - Natural Questions, with Tom Kwiatkowski and Michael Collins
April 06, 2020 18:52 - 43 minutes - 39.8 MBIn this episode, Tom Kwiatkowski and Michael Collins talk about Natural Questions, a benchmark for question answering research. We discuss how the dataset was collected to reflect naturally-occurring questions, the criteria used for identifying short and long answers, how this dataset differs from other QA datasets, and how easy it might be to game the benchmark with superficial processing of the text. We also contrast the holistic design in Natural Questions to deliberately targeting specifi...
109 - What Does Your Model Know About Language, with Ellie Pavlick
March 30, 2020 17:09 - 46 minutes - 43 MBHow do we know, in a concrete quantitative sense, what a deep learning model knows about language? In this episode, Ellie Pavlick talks about two broad directions to address this question: structural and behavioral analysis of models. In structural analysis, we often train a linear classifier for some linguistic phenomenon we'd like to probe (e.g., syntactic dependencies) while using the (frozen) weights of a model pre-trained on some tasks (e.g., masked language models). What can we conclude...
108 - Data-To-Text Generation, with Verena Rieser and Ondřej Dušek
March 23, 2020 16:08 - 49 minutes - 45.3 MBIn this episode we invite Verena Rieser and Ondřej Dušek on to talk to us about the complexities of generating natural language when you have some kind of structured meaning representation as input. We talk about when you might want to do this, which is often is some kind of a dialog system, but also generating game summaries, and even some language modeling work. We then talk about why this is hard, which in large part is due to the difficulty of collecting data, and how to evaluate the ...
107 - Multi-Modal Transformers, with Hao Tan and Mohit Bansal
February 24, 2020 17:29 - 37 minutes - 34.4 MBIn this episode, we invite Hao Tan and Mohit Bansal to talk about multi-modal training of transformers, focusing in particular on their EMNLP 2019 paper that introduced LXMERT, a vision+language transformer. We spend the first third of the episode talking about why you might want to have multi-modal representations. We then move to the specifics of LXMERT, including the model structure, the losses that are used to encourage cross-modal representations, and the data that is used. Along the ...
106 - Ethical Considerations In NLP Research, with Emily Bender
February 17, 2020 21:55 - 39 minutes - 36 MBIn this episode, we talked to Emily Bender about the ethical considerations in developing NLP models and putting them in production. Emily cited specific examples of ethical issues, and talked about the kinds of potential concerns to keep in mind, both when releasing NLP models that will be used by real people, and also while conducting NLP research. We concluded by discussing a set of open-ended questions about designing tasks, collecting data, and publishing results, that Emily has put toge...
105 - Question Generation, with Sudha Rao
February 10, 2020 20:15 - 42 minutes - 39.4 MBIn this episode we invite Sudha Rao to talk about question generation. We talk about different settings where you might want to generate questions: for human testing scenarios (rare), for data augmentation (has been done a bunch for SQuAD-like tasks), for detecting missing information / asking clarification questions, for dialog uses, and others. After giving an overview of the general area, we talk about the specifics of some of Sudha's work, including her ACL 2018 best paper on ranking cl...
104 - Model Distillation, with Victor Sanh and Thomas Wolf
February 03, 2020 20:47 - 31 minutes - 28.7 MBIn this episode we talked with Victor Sanh and Thomas Wolf from HuggingFace about model distillation, and DistilBERT as one example of distillation. The idea behind model distillation is compressing a large model by building a smaller model, with much fewer parameters, that approximates the output distribution of the original model, typically for increased efficiency. We discussed how model distillation was typically done previously, and then focused on the specifics of DistilBERT, including ...
103 - Processing Language in Social Media, with Brendan O'Connor
January 27, 2020 17:01 - 43 minutes - 39.6 MBWe talked to Brendan O’Connor for this episode about processing language in social media. Brendan started off by telling us about his projects that studied the linguistic and geographical patterns of African American English (AAE), and how obtaining data from Twitter made these projects possible. We then talked about how many tools built for standard English perform very poorly on AAE, and why collecting dialect-specific data is important. For the rest of the conversation, we discussed the is...
102 - Biomedical NLP research at the National Institute of Health with Dina Demner-Fushman
January 20, 2020 17:25 - 36 minutes - 33.8 MBWhat exciting NLP research problems are involved in processing biomedical and clinical data? In this episode, we spoke with Dina Demner-Fushman, who leads NLP and IR research at the Lister Hill National Center for Biomedical Communications, part of the National Library of Medicine. We talked about processing biomedical scientific literature, understanding clinical notes, and answering consumer health questions, and the challenges involved in each of these applications. Dina listed some specif...
101 - The lottery ticket hypothesis, with Jonathan Frankle
January 14, 2020 17:52 - 41 minutes - 37.8 MBIn this episode, Jonathan Frankle describes the lottery ticket hypothesis, a popular explanation of how over-parameterization helps in training neural networks. We discuss pruning methods used to uncover subnetworks (winning tickets) which were initialized in a particularly effective way. We also discuss patterns observed in pruned networks, stability of networks pruned at different time steps and transferring uncovered subnetworks across tasks, among other topics. A recent paper on the topi...
100 - NLP Startups, with Oren Etzioni
January 08, 2020 21:09 - 30 minutes - 28.3 MBFor our 100th episode, we invite AI2 CEO Oren Etzioni to talk to us about NLP startups. Oren has founded several successful startups, is himself an investor in startups, and helps with AI2's startup incubator. Some of our discussion topics include: What's the similarity between being a researcher and an entrepreneur? How do you transition from being a researcher to doing a startup? How do you evaluate early-stage startups? What advice would you give to a researcher who's thinking about a...
99 - Evaluating Protein Transfer Learning, With Roshan Rao And Neil Thomas
December 16, 2019 17:36 - 44 minutes - 41 MBFor this episode, we chatted with Neil Thomas and Roshan Rao about modeling protein sequences and evaluating transfer learning methods for a set of five protein modeling tasks. Learning representations using self-supervised pretaining objectives has shown promising results in transferring to downstream tasks in protein sequence modeling, just like it has in NLP. We started off by discussing the similarities and differences between language and protein sequence data, and how the contextual emb...
98 - Analyzing Information Flow In Transformers, With Elena Voita
December 09, 2019 17:51 - 37 minutes - 34 MBWhat function do the different attention heads serve in multi-headed attention models? In this episode, Lena describes how to use attribution methods to assess the importance and contribution of different heads in several tasks, and describes a gating mechanism to prune the number of effective heads used when combined with an auxiliary loss. Then, we discuss Lena’s work on studying the evolution of representations of individual tokens in transformers model. Lena’s homepage: https://lena-voi...
97 - Automated Analysis Of Historical Printed Documents, With Taylor Berg-Kirkpatrick
November 27, 2019 22:08 - 44 minutes - 40.5 MBIn this episode, we talk to Taylor Berg-Kirkpatrick about optical character recognition (OCR) on historical documents. Taylor starts off by describing some practical issues related to old scanning processes of documents that make performing OCR on them a difficult problem. Then he explains how one can build latent variable models for this data using unsupervised methods, the relative importance of various modeling choices, and summarizes how well the models do. We then take a higher level vie...
96 - Question Answering as an Annotation Format, with Luke Zettlemoyer
November 12, 2019 22:36 - 29 minutes - 27.4 MBIn this episode, we chat with Luke Zettlemoyer about Question Answering as a format for crowdsourcing annotations of various semantic phenomena in text. We start by talking about QA-SRL and QAMR, two datasets that use QA pairs to annotate predicate-argument relations at the sentence level. Luke describes how this annotation scheme makes it possible to obtain annotations from non-experts, and discusses the tradeoffs involved in choosing this scheme. Then we talk about the challenges involved i...