The UMass rising campaign provides faculty with the opportunity to make targeted gifts that are matched dollar for dollar by the campus. The current operation of the Initiative in Cognitive Science has been made possible in part by a recent faculty gift targeted at interdisciplinary language research. Please contact Joe Pater or Lisa Sanders if you would like to discuss the impact that your gift could have.

The American International Morphology Meeting is being held here at UMass this weekend, and has as a special theme morphological processing. The program can be found here. All are welcome, even those who haven’t registered.

Caren Rotello of UMass Cognitive Psychology will present in the Cognitive Brown Bag series at 12 p.m. The rest of this semester’s schedule follows:

10/7 –  Gerry Altmann (UConn)

10/14 –  David Ross

10/21 – Molly Potter (MIT)

10/28 – Jim Magnuson (UConn)

11/4 –  Dave Huber

11/11 – No meeting, Veterans Day

11/18 – No meeting, Psychonomics

11/25 – No meeting, Thanksgiving

12/2 – Louise Antony (UMass Philosophy)

12/9 – James Haxby (Dartmouth)

Karthik Narasimhan of MIT will present “Language Understanding For Text-based Games Using Deep Reinforcement Learning” in the Machine Learning and Friends Lunch at 1 p.m. in CS150 (arrive at 12:45 for pizza).

Abstract:
In this paper, we consider the task of learning control policies for text-based games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. We employ a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback. This framework enables us to map text descriptions into vector representations that capture the semantics of the game states. We evaluate our approach on two game worlds, comparing against baselines using bag-of-words and bag-of-bigrams for state representations. Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations.

Bio:
I’m a fourth year PhD student at CSAIL, working with Prof. Regina Barzilay. I am primarily interested and work in the area of Computational Semantics, specifically in language understanding, grounding and machine comprehension. My goal is to develop richer representations for meaning that can capture its variable nature and context sensitivity, while keeping learning tractable. Previously, I have worked on computational morphology – applied to Keyword Spotting and unsupervised analysis using Morphological Chains. I have a B.Tech in Computer Science from IIT Madras (2012) and an SM in Computer Science from MIT (2014).

Ashwini Deo (Yale) will give a talk on “The Semantic and Pragmatic Underpinnings of Grammaticalization Paths” in the Linguistics department on Friday, September 25, at 3:30 in ILC N400.

Abstract: It is a well-established fact that meanings associated with functional linguistic expressions evolve in systematic ways across time. But we have little precise understanding of why and how this happens. We know even less about how formal approaches to the meanings of functional categories like tense, aspect, negation can be reconciled with the typologically robust findings of grammaticalization research. In this talk, I will take a first step towards such an understanding by analyzing a robustly attested semantic change in natural languages — the progressive-to-imperfective shift.

Simon Kirby of the University of Edinburgh will be visiting UMass Friday April 22nd to give a talk co-sponsored by the Initiative in Cognitive Science and the 5 Colleges Cognitive Science Seminar, with the co-operation of the Computational Social Sciences Institute. He describes his research as follows:

My work concerns the origin and evolution of language, and the unique ways that culture and biology interact in our species. I have pioneered a new approach to understanding cultural evolution of behaviours such as language which we call Iterated Learning. A number of research groups around the world – in addition to my own – are now studying Iterated Learning using techniques as diverse as mathematical modelling, computational simulation, and psychological experiments. My view is that a complete understanding of human nature requires an account of the complex interactions between individual learning, cultural transmission and biological evolution in human populations.

The Initiative in Cognitive Science is sponsoring a visit by Jim Magnuson, who heads the Computational Cognitive Neurocience Lab at the University of Connecticut, on Weds. Oct. 28th. He will be speaking at noon, and will be available to meet with students and faculty. If you would like to meet with him, please contact Adrian Staub.

Elan Dresher of the University of Toronto will give a talk in Linguistics on Friday Sept. 18th at 1:30 in ILC N400. The title and abstract follow.

Contrastive Hierarchy Theory: An Overview.

In this talk I will present an overview of contrastive hierarchy theory, aka Modified Contrastive Specification (MCS) or ‘Toronto School’ phonology. I will set out the main tenets of this theory, and briefly review their antecedents in the history of phonology. I will then illustrate various applications of the theory to topics in synchronic and diachronic phonology, as well as its implications for typology.

Chuck Clifton (Psychology) will give the first cognitive brown bag talk this semester on Wednesday, September 16, at noon in Tobin 521B. The title and abstract follow.

How readers and listeners use their knowledge of grammar – and how they go beyond it

The realization that our ability to produce and comprehend language requires use of detailed and elaborate knowledge of syntax fueled the cognitive revolution of the 1960s. Over the following 20 years, we learned a great deal about how readers and listeners used this knowledge in real time to interpret sentences. The success of these analyses of how language comprehension was driven by grammatical knowledge led to competing analyses, emphasizing how various sources of extra-grammatical knowledge contribute to language comprehension. In the years since the peak of the debate between these contrasting positions, more nuanced approaches have developed. These approaches extend the analysis of grammar’s contributions to incorporate effects of prosody, semantics, and pragmatics, and recognize that different types of grammatical relations might be processed differently. Other recent approaches have gone beyond grammar to consider the role language statistics might play in comprehension. Currently, my colleagues and I are exploring how language users employ their knowledge of what speakers and writers are likely to intend, and what kinds of errors they are likely to make in producing language, to arrive at interpretations of sentences that violate the grammatical requirements of the language.

In the first part of this talk, I will summarize the changing views of how we comprehend what we read and hear, providing illustrations of theoretical claims and examples of experimental evidence. In the second part of the talk, I will describe some of the work my colleagues and I are currently doing on what we call “acceptable ungrammaticality,” in which readers’ and listeners’ interpretations of language are guided by what they know of how writers and speakers can misuse the grammar of their language.