NLIP Seminar Series

The field of NLP is in the midst of a disruptive shift, fueled most recently by the advent of large language models (LLMs), with impacts on our methodologies, funding and public perception. While the core technologies and scope of real-world impact of our field may be changing (everything is different!), many of the same...

An overview of the mis/disinformation space, a framework for breaking it down into meaningful problems, and a look at some of the new tools and technology coming from Google to support fact-checkers and expert users around the world. Bio: Mevan Babakar is the News and Information Credibility Lead at Google, working to...

In this talk, Alexander will cover from different perspectives how search systems can respond to comparative questions, which was the main focus of his PhD studies. He will discuss approaches to identifying comparative questions and identifying important constituents of comparative questions, such as the options being...

Neural models -- including language models such as ChatGPT -- can exhibit remarkable abilities; paradoxically, they also struggle with algorithmic tasks where much simpler models excel. To solve these issues, we propose Implicit Maximum Likelihood Estimation (IMLE), a framework for end-to-end learning of models combining...

My research focuses on the cognitive plausibility of NLP models and I will discuss two examples of using human processing data for analyzing language processing in computational models. We look into similarities and differences in representing the input and in the sensitivity to structural complexity. Our research...

Abstract: The availability of large, high-quality datasets has been one of the main drivers of recent progress in generation tasks like summarization, QA. Such annotated datasets however are difficult and costly to collect, and rarely exist in languages other than English, rendering the technology inaccessible to...

Standard probabilistic language generators often fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics, e.g., perplexity. This discrepancy has puzzled the language generation community for the last few years. In this talk, we’ll take a...

Zipf posited that wordforms are optimized to minimize utterances’ communicative costs. He supported this claim by showing that words’ lengths are inversely correlated with their frequencies. This correlation, however, is only expected if one assumes that a words’ communicative cost is given by its length. We explore this...

Abstract not available

Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accuracy over beam search in conditional language generation problems and especially neural machine translation, in both human and automatic...