TechTalks from event: NAACL 2015
Best Paper Plenary Session
Retrofitting Word Vectors to Semantic LexiconsVector space word representations are learned from distributional information of words in large corpora. Although such statistics are semantically informative, they disregard the valuable information that is contained in semantic lexicons such as WordNet, FrameNet, and the Paraphrase Database. This paper proposes a method for refining vector space representations using relational information from semantic lexicons by encouraging linked words to have similar vector representations, and it makes no assumptions about how the input vectors were constructed. Evaluated on a battery of standard lexical semantic evaluation tasks in several languages, we obtain substantial improvements starting with a variety of word vector models. Our refinement method outperforms prior techniques for incorporating semantic lexicons into the word vector training algorithms.
Youre Mr. Lebowski, Im the Dude: Inducing Address Term Formality in Signed Social NetworksWe present an unsupervised model for inducing signed social networks from the content exchanged across network edges. Inference in this model solves three problems simultaneously: (1) identifying the sign of each edge; (2) characterizing the distribution over content for each edge type; (3) estimating weights for triadic features that map to theoretical models such as structural balance. We apply this model to the problem of inducing the social function of address terms, such as Madame, comrade, and dude. On a dataset of movie scripts, our system obtains a coherent clustering of address terms, while at the same time making intuitively plausible judgments of the formality of social relations in each film. As an additional contribution, we provide a bootstrapping technique for identifying and tagging address terms in dialogue.
Unsupervised Morphology Induction Using Word EmbeddingsWe present a language agnostic, unsupervised method for inducing morphological transformations between words. The method relies on certain regularities manifest in high-dimensional vector spaces. We show that this method is capable of discovering a wide range of morphological rules, which in turn are used to build morphological analyzers. We evaluate this method across six different languages and nine datasets, and show significant improvements across all languages.
Invited Talk: “Big data pragmatics!”, or, “Putting the ACL in computational social science”, or, if you think these title alternatives could turn people on, turn people off, or otherwise have an effect, this talk might be for you.What effect does language have on people?You might say in response, "Who are you to discuss this problem?" and you would be right to do so; this is a Major Question that science has been tackling for many years. But as a field, I think natural language processing and computational linguistics have much to contribute to the conversation, and I hope to encourage the community to further address these issues.This talk will focus on the effect of phrasing, emphasizing aspects that go beyond just the selection of one particular word over another. The issues we'll consider include: Does the way in which something is worded in and of itself have an effect on whether it is remembered or attracts attention, beyond its content or context? Can we characterize how different sides in a debate frame their arguments, in a way that goes beyond specific lexical choice (e.g., "pro-choice" vs. "pro-life")? The settings we'll explore range from movie quotes that achieve cultural prominence; to posts on Facebook, Wikipedia, Twi
A Quest for Visual Intelligence in ComputersMore than half of the human brain is involved in visual processing. While it took mother nature billions of years to evolve and deliver us a remarkable human visual system, computer vision is one of the youngest disciplines of AI, born with the goal of achieving one of the loftiest dreams of AI. The central problem of computer vision is to turn millions of pixels of a single image into interpretable and actionable concepts so that computers can understand pictures just as well as humans do, from objects, to scenes, activities, events and beyond. Such technology will have a fundamental impact in almost every aspect of our daily life and the society as a whole, ranging from e-commerce, image search and indexing, assistive technology, autonomous driving, digital health and medicine, surveillance, national security, robotics and beyond. In this talk, I will give an overview of what computer vision technology is about and its brief history. I will then discuss some of the recent work from my lab towards large scale object recognition and visual scene story telling. I will particularly emphasize on what we call the "three pillars" of AI in our quest for visual intelligence: data, learning and knowledge. Each of them is critical towards the final solution, yet dependent on the other. This talk draws upon a number of projects ongoing at the Stanford Vision Lab.