BEGIN:VCALENDAR VERSION:2.0 PRODID:-//128.220.36.25//NONSGML kigkonsult.se iCalcreator 2.26.9// CALSCALE:GREGORIAN METHOD:PUBLISH X-FROM-URL:https://www.clsp.jhu.edu X-WR-TIMEZONE:America/New_York BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:STANDARD DTSTART:20231105T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RDATE:20241103T020000 TZNAME:EST END:STANDARD BEGIN:DAYLIGHT DTSTART:20240310T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RDATE:20250309T020000 TZNAME:EDT END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:ai1ec-21275@www.clsp.jhu.edu DTSTAMP:20240329T021640Z CATEGORIES;LANGUAGE=en-US:Student Seminars CONTACT: DESCRIPTION:Abstract\n\n\n\nAutomatic discovery of phone or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ contrastive predictive coding (CPC)\, where the model lear ns representations by predicting the next frame given past context. Howeve r\, CPC only looks at the audio signal’s structure at the frame level. The speech structure exists beyond frame-level\, i.e.\, at phone level or eve n higher. We propose a segmental contrastive predictive coding (SCPC) fram ework to learn from the signal structure at both the frame and phone level s.\n\nSCPC is a hierarchical model with three stages trained in an end-to- end manner. In the first stage\, the model predicts future feature frames and extracts frame-level representation from the raw waveform. In the seco nd stage\, a differentiable boundary detector finds variable-length segmen ts. In the last stage\, the model predicts future segments to learn segmen t representations. Experiments show that our model outperforms existing ph one and word segmentation methods on TIMIT and Buckeye datasets. DTSTART;TZID=America/New_York:20220211T120000 DTEND;TZID=America/New_York:20220211T131500 LOCATION:Ames Hall 234 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Student Seminar – Saurabhchand Bhati “Segmental Contrastive Predict ive Coding for Unsupervised Acoustic Segmentation” URL:https://www.clsp.jhu.edu/events/student-seminar-saurabhchand-bhati/ X-COST-TYPE:free X-ALT-DESC;FMTTYPE=text/html:\\n\\n
\\nAbstr act
\n\n\n\n\nAutomatic discovery of phone or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ contrastive predictive coding (CPC)\, where the model learns repre sentations by predicting the next frame given past context. However\, CPC only looks at the audio signal’s structure at the frame level. The speech structure exists beyond frame-level\, i.e.\, at phone level or even higher . We propose a segmental contrastive predictive coding (SCPC) framework to learn from the signal structure at both the frame and phone levels.\n\n\nSCPC is a hierarchical mode l with three stages trained in an end-to-end manner. In the first stage\, the model predicts future feature frames and extracts frame-level represen tation from the raw waveform. In the second stage\, a differentiable bound ary detector finds variable-length segments. In the last stage\, the model predicts future segments to learn segment representations. Experiments sh ow that our model outperforms existing phone and word segmentation methods on TIMIT and Buckeye datasets.
Abstr act
\nAs humans\, our understanding of language is grounded
in a rich mental model about “how the world works” – that we learn throug
h perception and interaction. We use this understanding to reason beyond w
hat we literally observe or read\, imagining how situations might unfold i
n the world. Machines today struggle at this kind of reasoning\, which lim
its how they can communicate with humans.
In my talk\, I will discuss three lines of work to bridge
this gap between machines and humans. I will first discuss how we might m
easure grounded understanding. I will introduce a suite of approaches for
constructing benchmarks\, using machines in the loop to filter out spuriou
s biases. Next\, I will introduce PIGLeT: a model that learns physical com
monsense understanding by interacting with the world through simulation\,
using this knowledge to ground language. From an English-language descript
ion of an event\, PIGLeT can anticipate how the world state might change –
outperforming text-only models that are orders of magnitude larger. Final
ly\, I will introduce MERLOT\, which learns about situations in the world
by watching millions of YouTube videos with transcribed speech. Through tr
aining objectives inspired by the developmental psychology idea of multimo
dal reentry\, MERLOT learns to fuse language\, vision\, and sound together
into powerful representations.
Together\, these directions suggest a path forward for building mac
hines that learn language rooted in the world.
Biography strong>
\nRowan Zellers is a final year PhD candidate at the Univers ity of Washington in Computer Science & Engineering\, advised by Yejin Cho i and Ali Farhadi. His research focuses on enabling machines to understand language\, vision\, sound\, and the world beyond these modalities. He has been recognized through an NSF Graduate Fellowship and a NeurIPS 2021 out standing paper award. His work has appeared in several media outlets\, inc luding Wired\, the Washington Post\, and the New York Times. In the past\, he graduated from Harvey Mudd College with a B.S. in Computer Science & M athematics\, and has interned at the Allen Institute for AI.
\n< /HTML> X-TAGS;LANGUAGE=en-US:2022\,February\,Zellers END:VEVENT BEGIN:VEVENT UID:ai1ec-23304@www.clsp.jhu.edu DTSTAMP:20240329T021640Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract\nTransformers are essential to pretraining. As we appr oach 5 years of BERT\, the connection between attention as architecture an d transfer learning remains key to this central thread in NLP. Other archi tectures such as CNNs and RNNs have been used to replicate pretraining res ults\, but these either fail to reach the same accuracy or require supplem ental attention layers. This work revisits the semanal BERT result and con siders pretraining without attention. We consider replacing self-attention layers with recently developed approach for long-range sequence modeling and transformer architecture variants. Specifically\, inspired by recent p apers like the structured space space sequence model (S4)\, we use simple routing layers based on state-space models (SSM) and a bidirectional model architecture based on multiplicative gating. We discuss the results of th e proposed Bidirectional Gated SSM (BiGS) and present a range of analysis into its properties. Results show that architecture does seem to have a no table impact on downstream performance and a different inductive bias that is worth exploring further.\nBiography\nAlexander “Sasha” Rush is an Asso ciate Professor at Cornell Tech. His work is at the intersection of natura l language processing and generative modeling with applications in text ge neration\, efficient inference\, and controllability. He has written sever al popular open-source software projects supporting NLP research and data science\, and works part-time as a researcher at Hugging Face. He is the s ecretary of ICLR and developed software used to run virtual conferences du ring COVID. His work has received paper and demo awards at major NLP\, vis ualization\, and hardware conferences\, an NSF Career Award\, and a Sloan Fellowship. He tweets and blogs\, mostly about coding and ML\, at @srush_n lp. DTSTART;TZID=America/New_York:20230203T120000 DTEND;TZID=America/New_York:20230203T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Sasha Rush (Cornell University) “Pretraining Without Attention” URL:https://www.clsp.jhu.edu/events/sasha-rush-cornell-university/ X-COST-TYPE:free X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\nAbstr act
\nTransformers are essential to pretraining. As we appr oach 5 years of BERT\, the connection between attention as architecture an d transfer learning remains key to this central thread in NLP. Other archi tectures such as CNNs and RNNs have been used to replicate pretraining res ults\, but these either fail to reach the same accuracy or require supplem ental attention layers. This work revisits the semanal BERT result and con siders pretraining without attention. We consider replacing self-attention layers with recently developed approach for long-range sequence modeling and transformer architecture variants. Specifically\, inspired by recent p apers like the structured space space sequence model (S4)\, we use simple routing layers based on state-space models (SSM) and a bidirectional model architecture based on multiplicative gating. We discuss the results of th e proposed Bidirectional Gated SSM (BiGS) and present a range of analysis into its properties. Results show that architecture does seem to have a no table impact on downstream performance and a different inductive bias that is worth exploring further.
\nBiography
\n