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-21267@www.clsp.jhu.edu
DTSTAMP:20240328T182602Z
CATEGORIES;LANGUAGE=en-US:Seminars
CONTACT:
DESCRIPTION:
Abstract
\nIn this talk\, I present a
multipronged strategy for zero-shot cross-lingual Information Extraction\
, that is the construction of an IE model for some target language\, given
existing annotations exclusively in some other language. This work is par
t of the JHU team’s effort under the IARPA BETTER program. I explore data
augmentation techniques including data projection and self-training\, and
how different pretrained encoders impact them. We find through extensive e
xperiments and extension of techniques that a combination of approaches\,
both new and old\, leads to better performance than any one cross-lingual
strategy in particular.
\nBiography
\nMahsa
Yarmohammadi is an assistant research scientist in CLSP\, JHU\, who leads
state-of-the-art research in cross-lingual language and speech applicatio
ns and algorithms. A primary focus of Yarmohammadi’s research is using dee
p learning techniques to transfer existing resources into other languages
and to learn representations of language from multilingual data. She also
works in automatic speech recognition and speech translation. Yarmohammadi
received her PhD in computer science and engineering from Oregon Health &
Science University (2016). She joined CLSP as a post-doctoral fellow in 2
017.
\n
DTSTART;TZID=America/New_York:20220204T120000
DTEND;TZID=America/New_York:20220204T131500
LOCATION:Ames 234 Presented Virtually via Zoom https://wse.zoom.us/j/967351
83473
SEQUENCE:0
SUMMARY:Mahsa Yarmohammadi (Johns Hopkins University) “Data Augmentation fo
r Zero-shot Cross-Lingual Information Extraction”
URL:https://www.clsp.jhu.edu/events/mahsa-yarmohammadi-johns-hopkins-univer
sity-data-augmentation-for-zero-shot-cross-lingual-information-extraction/
X-COST-TYPE:free
X-TAGS;LANGUAGE=en-US:2022\,February\,Yarmohammadi
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-21275@www.clsp.jhu.edu
DTSTAMP:20240328T182602Z
CATEGORIES;LANGUAGE=en-US:Student Seminars
CONTACT:
DESCRIPTION:Abstract
\n\n
\n\n
Automatic discovery of phon
e 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 representations 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.\, a
t phone level or even higher. We propose a segmental contrastive predictiv
e coding (SCPC) framework to learn from the signal structure at both the f
rame and phone levels.\n
\n
SCPC is a hierarchical model with three stages trained in an end-to-end m
anner. In the first stage\, the model predicts future feature frames and e
xtracts frame-level representation from the raw waveform. In the second st
age\, a differentiable boundary detector finds variable-length segments. I
n the last stage\, the model predicts future segments to learn segment rep
resentations. Experiments show that our model outperforms existing phone a
nd word segmentation methods on TIMIT and Buckeye datasets.
\n
\n
\n
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-TAGS;LANGUAGE=en-US:2022\,Bhati\,Februray
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-22395@www.clsp.jhu.edu
DTSTAMP:20240328T182602Z
CATEGORIES;LANGUAGE=en-US:Seminars
CONTACT:
DESCRIPTION:Abstract
\nRecursive call
s over recursive data are widely useful for generating probability distrib
utions\, and probabilistic programming allows computations over these dist
ributions to be expressed in a modular and intuitive way. Exact inference
is also useful\, but unfortunately\, existing probabilistic programming la
nguages do not perform exact inference on recursive calls over recursive d
ata\, forcing programmers to code many applications manually. We introduce
a probabilistic language in which a wide variety of recursion can be expr
essed naturally\, and inference carried out exactly. For instance\, probab
ilistic pushdown automata and their generalizations are easy to express\,
and polynomial-time parsing algorithms for them are derived automatically.
We eliminate recursive data types using program transformations related t
o defunctionalization and refunctionalization. These transformations are a
ssured correct by a linear type system\, and a successful choice of transf
ormations\, if there is one\, is guaranteed to be found by a greedy algori
thm. I will also describe the implementation of this language in two phase
s: first\, compilation to a factor graph grammar\, and second\, computing
the sum-product of the factor graph grammar.
\n
\nBiography
\nDavid Chiang (PhD\, University of Pennsylvania\, 2004) is an assoc
iate professor in the Department of Computer Science and Engineering at th
e University of Notre Dame. His research is on computational models for le
arning human languages\, particularly how to translate from one language t
o another. His work on applying formal grammars and machine learning to tr
anslation has been recognized with two best paper awards (at ACL 2005 and
NAACL HLT 2009). He has received research grants from DARPA\, NSF\, Google
\, and Amazon\, has served on the executive board of NAACL and the editori
al board of Computational Linguistics and JAIR\, and is currently on the e
ditorial board of Transactions of the ACL.
DTSTART;TZID=America/New_York:20221017T120000
DTEND;TZID=America/New_York:20221017T131500
LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218
SEQUENCE:0
SUMMARY:David Chiang (University of Notre Dame) “Exact Recursive Probabilis
tic Programming with Colin McDonald\, Darcey Riley\, Kenneth Sible (Notre
Dame) and Chung-chieh Shan (Indiana)”
URL:https://www.clsp.jhu.edu/events/david-chiang-university-of-notre-dame/
X-COST-TYPE:free
X-TAGS;LANGUAGE=en-US:2022\,Chiang\,October
END:VEVENT
END:VCALENDAR