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-21280@www.clsp.jhu.edu DTSTAMP:20240329T023550Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:
Abstract
\nAs AI-driven lan guage interfaces (such as chat-bots) become more integrated into our lives \, they need to become more versatile and reliable in their communication with human users. How can we make progress toward building more “general” models that are capable of understanding a broader spectrum of language co mmands\, given practical constraints such as the limited availability of l abeled data?
\nIn this talk\, I will describe my research toward addressing this question along two dimensions of generality. First I will discuss progress in “breadth” — models that address a wider variety of tasks and abilities\, drawing inspiration from existing statistical le arning techniques such as multi-task learning. In particular\, I will show case a system that works well on several QA benchmarks\, resulting in stat e-of-the-art results on 10 benchmarks. Furthermore\, I will show its exten sion to tasks beyond QA (such as text generation or classification) that c an be “defined” via natural language. In the second part\, I will focus o n progress in “depth” — models that can handle complex inputs such as comp ositional questions. I will introduce Text Modular Networks\, a general fr amework that casts problem-solving as natural language communication among simpler “modules.” Applying this framework to compositional questions by leveraging discrete optimization and existing non-compositional closed-box QA models results in a model with strong empirical performance on multipl e complex QA benchmarks while providing human-readable reasoning.
\nI will conclude with future research directions toward broader N LP systems by addressing the limitations of the presented ideas and other missing elements needed to move toward more general-purpose interactive la nguage understanding systems.
\nBiography
\nDaniel Khashabi is a postdoctoral researcher at the Al len Institute for Artificial Intelligence (AI2)\, Seattle. Previously\, he completed his Ph.D. in Computer and Information Sciences at the Universit y of Pennsylvania in 2019. His interests lie at the intersection of artifi cial intelligence and natural language processing\, with a vision toward m ore general systems through unified algorithms and theories.
DTSTART;TZID=America/New_York:20220218T120000 DTEND;TZID=America/New_York:20220218T131500 LOCATION:Ames Hall 234 - Presented Virtually Via Zoom https://wse.zoom.us/j /96735183473 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Daniel Khashabi (Allen Institute for Artificial Intelligence) “The Quest Toward Generality in Natural Language Understanding” URL:https://www.clsp.jhu.edu/events/daniel-khashabi-allen-institute-for-art ificial-intelligence/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,February\,Khashabi END:VEVENT BEGIN:VEVENT UID:ai1ec-22374@www.clsp.jhu.edu DTSTAMP:20240329T023550Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nIn recent years\, the fiel d of Natural Language Processing has seen a profusion of tasks\, datasets\ , and systems that facilitate reasoning about real-world situations throug h language (e.g.\, RTE\, MNLI\, COMET). Such systems might\, for example\, be trained to consider a situation where “somebody dropped a glass on the floor\,” and conclude it is likely that “the glass shattered” as a result . In this talk\, I will discuss three pieces of work that revisit assumpti ons made by or about these systems. In the first work\, I develop a Defeas ible Inference task\, which enables a system to recognize when a prior ass umption it has made may no longer be true in light of new evidence it rece ives. The second work I will discuss revisits partial-input baselines\, wh ich have highlighted issues of spurious correlations in natural language r easoning datasets and led to unfavorable assumptions about models’ reasoni ng abilities. In particular\, I will discuss experiments that show models may still learn to reason in the presence of spurious dataset artifacts. F inally\, I will touch on work analyzing harmful assumptions made by reason ing models in the form of social stereotypes\, particularly in the case of free-form generative reasoning models.
\nBiography
\nRachel Rudinger is an Assistant Professor in the Department of Co mputer Science at the University of Maryland\, College Park. She holds joi nt appointments in the Department of Linguistics and the Institute for Adv anced Computer Studies (UMIACS). In 2019\, Rachel completed her Ph.D. in C omputer Science at Johns Hopkins University in the Center for Language and Speech Processing. From 2019-2020\, she was a Young Investigator at the A llen Institute for AI in Seattle\, and a visiting researcher at the Univer sity of Washington. Her research interests include computational semantics \, common-sense reasoning\, and issues of social bias and fairness in NLP.
DTSTART;TZID=America/New_York:20220916T120000 DTEND;TZID=America/New_York:20220916T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Rachel Rudinger (University of Maryland\, College Park) “Not So Fas t!: Revisiting Assumptions in (and about) Natural Language Reasoning” URL:https://www.clsp.jhu.edu/events/rachel-rudinger-university-of-maryland- college-park-not-so-fast-revisiting-assumptions-in-and-about-natural-langu age-reasoning/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,Rudinger\,September END:VEVENT BEGIN:VEVENT UID:ai1ec-23886@www.clsp.jhu.edu DTSTAMP:20240329T023550Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nThe arms race to build inc reasingly larger\, powerful language models (LMs) in the past year has bee n remarkable. Yet incorporating LMs effectively into practical application s that facilitate manual workflows remains challenging. I will discuss LMs ’ limiting factors and our efforts to overcome them. I will start with cha llenges surrounding efficient and robust LM alignment. I will share insigh ts from our recent paper “Sel f-Instruct” (ACL 2023)\, where we used vanilla (unaligned) LMs for ali gning itself\, an approach that has yielded some success. Then\, I will mo ve on to the challenge of tracing the output of LMs to reliable sources\, a weakness that makes them prone to hallucinations. I will discuss our rec ent approach of ‘according-to’ prom pting\, which steers LMs to quote directly from sources observed in it s pre-training. If time permits\, I will discuss our ongoing project to ad apt LMs to interact with web pages. Throughout the presentation\, I will h ighlight our progress\, and end with questions about our future progress.< /p>\n
Biography
\nDaniel Khashabi is an assistant professor in computer science at Johns Hopkins University and the Center for Language and Speech Processing (CLSP) member. He is interested in bui lding reasoning-driven modular NLP systems that are robust\, transparent\, and communicative\, particularly those that use natural language as the c ommunication medium. Khashabi has published over 40 papers on natural lang uage processing and AI in top-tier venues. His work touches upon developin g. His research has won the ACL 2023 Outstanding Paper Award\, NAACL 2022 Best Paper Award\, research gifts from the Allen Institute for AI\, and an Amazon Research Award 2023. Before joining Hopkins\, he was a postdoctora l fellow at the Allen Institute for AI (2019-2022) and obtained a Ph.D. fr om the University of Pennsylvania in 2019.
DTSTART;TZID=America/New_York:20230908T120000 DTEND;TZID=America/New_York:20230908T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Daniel Khashabi (Johns Hopkins University) “Building More Helpful L anguage Models” URL:https://www.clsp.jhu.edu/events/daniel-khashabi-johns-hopkins-universit y/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2023\,Khashabi\,September END:VEVENT END:VCALENDAR