117 - Interpreting NLP Model Predictions, with Sameer Singh

117 - Interpreting NLP Model Predictions, with Sameer Singh

Author: Allen Institute for Artificial Intelligence August 13, 2020 Duration: 56:56
We 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 discussing how explanations of model behavior can be evaluated, and some limitations and potential concerns in evaluation methods. Sameer Singh is an Assistant Professor of Computer Science at the University of California, Irvine. Some of the techniques discussed in this episode have been implemented in the AllenNLP Interpret framework (details and demo here: https://allennlp.org/interpret).

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
103 - Processing Language in Social Media, with Brendan O'Connor [not-audio_url] [/not-audio_url]

Duration: 43:12
We 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 Eng…
101 - The lottery ticket hypothesis, with Jonathan Frankle [not-audio_url] [/not-audio_url]

Duration: 41:16
In 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 (win…
100 - NLP Startups, with Oren Etzioni [not-audio_url] [/not-audio_url]

Duration: 30:55
For 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 ou…
98 - Analyzing Information Flow In Transformers, With Elena Voita [not-audio_url] [/not-audio_url]

Duration: 37:05
What 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 severa…
95 - Common sense reasoning, with Yejin Choi [not-audio_url] [/not-audio_url]

Duration: 35:29
In this episode, we invite Yejin Choi to talk about common sense knowledge and reasoning, a growing area in NLP. We start by discussing a working definition of “common sense” and the practical utility of studying it. We…
94 - Decompositional Semantics, with Aaron White [not-audio_url] [/not-audio_url]

Duration: 27:50
In this episode, Aaron White tells us about the decompositional semantics initiative (Decomp), an attempt to re-think the prototypical approach to semantic representation and annotation. The basic idea is to decompose co…