126 - Optimizing Continuous Prompts for Generation, with Lisa Li

126 - Optimizing Continuous Prompts for Generation, with Lisa Li

Author: Allen Institute for Artificial Intelligence May 24, 2021 Duration: 47:38
We 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 is a Phd student at Stanford University. Lisa's webpage: https://xiangli1999.github.io/ The hosts for this episode are Pradeep Dasigi and Ana Marasović.

While NLP Highlights is currently on hiatus, its archive remains a compelling snapshot of conversations from the front lines of computational linguistics. Produced by the Allen Institute for Artificial Intelligence, this science podcast carved out a space for deep, researcher-led discussions about natural language processing. Each episode functions as an informal seminar, where the people actively designing algorithms and pushing the field forward explain their work in their own words. You'll hear about the nuanced challenges behind making machines understand, generate, and reason with human language, from foundational theories to unexpected applications. The dialogue in this podcast often delves into the "why" behind the research, not just the results, offering clarity on complex topics like machine translation, sentiment analysis, or large language models. It’s a chance to listen as experts articulate their thought processes, debates, and moments of insight, with all the candidness that comes from a conversation between peers. The views shared are personal perspectives from the hosts and their guests, independent of their affiliated institutions. For anyone curious about how machines learn to parse meaning, the archived episodes of NLP Highlights provide a thoughtful and accessible entry point.
Author: Language: English Episodes: 100

NLP Highlights
Podcast Episodes
93 - NLP/ML for clinical data, with Alistair Johnson [not-audio_url] [/not-audio_url]

Duration: 37:21
In this episode, we invite Alistair Johnson to discuss the main challenge in applying NLP/ML to clinical domains: the lack of data. We discuss privacy concerns, de-identification, synthesizing records, legal liabilities…
92 - Computational Humanities, with David Bamman [not-audio_url] [/not-audio_url]

Duration: 33:56
In this episode, we invite David Bamman to give an overview of computational humanities. We discuss examples of questions studied in computational humanities (e.g., characterizing fictionality, assessing novelty, measuri…
91 - (Executable) Semantic Parsing, with Jonathan Berant [not-audio_url] [/not-audio_url]

Duration: 42:10
In this episode, we invite Jonathan Berant to talk about executable semantic parsing. We discuss what executable semantic parsing is and how it differs from related tasks such as semantic dependency parsing and abstract…
89 - Dialog Systems, with Zhou Yu [not-audio_url] [/not-audio_url]

Duration: 37:23
In this episode, we invite Zhou Yu to give an overview of dialogue systems. We discuss different types of dialogue systems (task-oriented vs. non-task-oriented), the main building blocks and how they relate to other rese…
86 - NLP for Evidence-based Medicine, with Byron Wallace [not-audio_url] [/not-audio_url]

Duration: 32:02
In this episode, Byron Wallace tells us about interdisciplinary work between evidence based medicine and natural language processing. We discuss extracting PICO frames from articles describing clinical trials and data av…
85 - Stress in Research, with Charles Sutton [not-audio_url] [/not-audio_url]

Duration: 36:36
In this episode, Charles Sutton walks us through common sources of stress for researchers and suggests coping strategies to maintain your sanity. We talk about how pursuing a research career is similar to participating i…
84 - Large Teams Develop, Small Groups Disrupt, with Lingfei Wu [not-audio_url] [/not-audio_url]

Duration: 38:34
In a recent Nature paper, Lingfei Wu (Ling) suggests that smaller teams of scientists tend to do more disruptive work. In this episode, we invite Ling to discuss their results, how they define disruption and possible rea…