Conferences, Lectures, & Seminars
Events for August
-
NL Seminar-Reasoning about objects, their components, and their descriptors
Fri, Aug 10, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: James Mullenbach , USC/ISI
Talk Title: Reasoning about objects, their components, and their descriptors
Series: Natural Language Seminar
Abstract: How do adjectives project from a noun to its parts and other aspects? If a motorcycle is red, are its wheels red? Is a sharp knifes handle sharp? Questions like this are common sense for humans, using our understanding of the world, but difficult for computers. I will describe our process for curating and annotating a large dataset consisting of related object pairs and adjectives, and a set of experiments that aim to discover the extent to which modern approaches can learn these relationships from purely textual sources.
Biography: James is a Masters Student in Computer Science at the Georgia Institute of Technology, where he works on machine learning for healthcare using written electronic health record notes. At ISI, he is working with Jonathan May and Nanyun Peng on building a dataset and models for textual commonsense reasoning. He aims to work on NLP and ML in industry for a year or so before applying for PhD programs.
Host: Nanyun Peng
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Floor Conf Rm-CR# 689
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar-Decipherment for Universal Language Tools A case study for Unsupervised Part of Speech Induction
Fri, Aug 17, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Ronald Cardenas, USC
Talk Title: Decipherment for Universal Language Tools A case study for Unsupervised Part of Speech Induction
Series: Natural Language Seminar
Abstract: Unsupervised Part of Speech induction can be viewed as a two-steps task. The first step infers a sequence of states, while the second step maps this sequence to an actual Part-of-Speech sequence at training or testing time. Hence, this last step requires reference tagged data, a luxury low-resource target languages might not have. In this talk, we present an alternative approach to the second step, modeling it as a decipherment problem in which the ciphered text is the sequence of states and the original text we want to recover is the POS sequence. This approach requires no reference data in the target language and allows to leverage POS sequences in much richer languages. Our experiments show that our approach benefits the most from simple strategies for inferring state sequences, such as Brown clustering. This allow our method to obtain reasonable performance in low-resource and limited-time scenarios.
Biography: Ronald Cardenas is a Master's student in the Language and Communication Technologies programme at Charles University in Prague. His research interests span morphological analysis and parsing of low-resource languages. At ISI, he works with Jonatan May on developing universal language tools.
Host: Nanyun Peng
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar-T1. Constraints for Transfer Learning for Machine Translation T2.SAY YES AND: BUILDING A SPECIALIZED CORPUS FOR DIGITAL IMPROVISED COMEDY
Fri, Aug 17, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Mozhdeh Gheini, Xinyu Wang , USC/ISI
Talk Title: T1. Constraints for Transfer Learning for Machine Translation T2.SAY YES-AND: BUILDING A SPECIALIZED CORPUS FOR DIGITAL IMPROVISED COMEDY
Series: Natural Language Seminar
Abstract: T1.Can we detect the parts responsible for a generic behavior in a model to transfer it to another? In this talk, we first see why this might be a good idea, especially for low resource machine translation. Then we focus on our approach to isolating a behavior. In our case, we specifically focus on coverage during machine translation. We present our results across different languages that show how neural models try to ensure coverage.
T2. In improvised comedy, saying yes, and.. is a rule of thumb that suggests that one person should accept the other person's offer yes, and then add related information on top of that and. Collecting a yes, and.. corpus is not only helpful for building an improv agent, but can also be used for building conversational skill training tool, improving a dialogue system, etc. I will discuss the methods we have used for building such a dataset, data we have got so far and future considerations.
Biography: Mozhdeh Gheini is a last semester Computer Science master's student at USC Viterbi School of Engineering. At ISI, she works on improving neural low-resource machine translation under the supervision of Jonathan May. She will be applying for Ph.D. programs this Fall.
Xinyu is a 2018 summer intern working with Dr. Jonathan May and Dr. Nanyun Peng on computerized improvised comedy. She will be joinging the Language Technologies Institute at Carnegie Mellon University in 2018 fall.
Host: Nanyun Peng
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
