Whereas people learn many different types of knowledge from diverse experiences over many years, and become better learners over time, most current machine learning systems are much more narrow, learning just a single function or data model based on statistical analysis of a single data set. We suggest that people learn better than computers precisely because of this difference, and we suggest a key direction for machine learning research is to develop software architectures that enable intelligent agents to also learn many types of knowledge, continuously over many years, and to become better learners over time. In this paper we define more precisely this never-ending learning paradigm for machine learning, and we present one case study: the Never-Ending Language Learner (NELL), which achieves a number of the desired properties of a never-ending learner. NELL has been learning to read the Web 24hrs/ day since January 2010, and so far has acquired a knowledge base with 120mn diverse, confidence-weighted beliefs (e.g., servedWith(tea,biscuits)), while learning thousands of interrelated functions that continually improve its reading competence over time. NELL has also learned to reason over its knowledge base to infer new beliefs it has not yet read from those it has, and NELL is inventing new relational predicates to extend the ontology it uses to represent beliefs. We describe the design of NELL, experimental results illustrating its behavior, and discuss both its successes and shortcomings as a case study in never-ending learning. NELL can be tracked online at http://rtw.ml.cmu.edu, and followed on Twitter at @CMUNELL. 2. RELATED WORK Previous research has considered the problem of designing machine learning agents that persist over long periods research highlights

In this paper, we propose to model and analyze changes that occur to an entity in terms of changes in the words that co-occur with the entity over time. We propose to do an in-depth analysis of how this co-occurrence changes over time, how the change influences the state (semantic, role) of the entity, and how the change may correspond to events occurring in the same period of time. We propose to identify clusters of topics surrounding the entity over time using Topics-Over-Time (TOT) and k-means clustering. We conduct this analysis on Google Books Ngram dataset. We show how clustering words that co-occur with an entity of interest in 5-grams can shed some lights to the nature of change that occurs to the entity and identify the period for which the change occurs. We find that the period identified by our model precisely coincides with events in the same period that correspond to the change that occurs.

Recent research has made significant advances in automatically constructing knowledge bases by extracting relational facts (e.g., Bill Clinton-presidentOf-US) from large text corpora. Temporally scoping such relational facts in the knowledge base (i.e., determining that Bill Clinton-presidentOf-US is true only during the period 1993 -2001) is an important, but relatively unexplored problem. In this paper, we propose a joint inference framework for this task, which leverages fact-specific temporal constraints, and weak supervision in the form of a few labeled examples. Our proposed framework, CoTS (Coupled Temporal Scoping), exploits temporal containment, alignment, succession, and mutual exclusion constraints among facts from within and across relations. Our contribution is multi-fold. Firstly, while most previous research has focused on micro-reading approaches for temporal scoping, we pose it in a macroreading fashion, as a change detection in a time series of facts' features computed from a large number of documents. Secondly, to the best of our knowledge, there is no other work that has used joint inference for temporal scoping. We show that joint inference is effective compared to doing temporal scoping of individual facts independently. We conduct our experiments on large scale open-domain publicly available time-stamped datasets, such as English Gigaword Corpus and Google Books Ngrams, demonstrating CoTS's effectiveness.

We conduct the most comprehensive study to date into translating words via images. To facilitate research on the task, we introduce a large-scale multilingual corpus of images, each labeled with the word it represents. Past datasets have been limited to only a few high-resource languages and unrealistically easy translation settings. In contrast, we have collected by far the largest available dataset for this task, with images for approximately 10,000 words in each of 100 languages. We run experiments on a dozen high resource languages and 20 low resources languages, demonstrating the effect of word concreteness and part-of-speech on translation quality. To improve image-based translation, we introduce a novel method of predicting word concreteness from images, which improves on a previous stateof-the-art unsupervised technique. This allows us to predict when image-based translation may be effective, enabling consistent improvements to a state-of-the-art text-based word translation system. Our code and the Massively Multilingual Image Dataset (MMID) are available at http: //multilingual-images.org/.

Different news articles about the same topic often offer a variety of perspectives: an article written about gun violence might emphasize gun control, while another might promote 2nd Amendment rights, and yet a third might focus on mental health issues. In communication research, these different perspectives are known as "frames", which, when used in news media will influence the opinion of their readers in multiple ways. In this paper, we present a method for effectively detecting frames in news headlines. Our training and performance evaluation is based on a new dataset of news headlines related to the issue of gun violence in the United States. This Gun Violence Frame Corpus (GVFC) was curated and annotated by journalism and communication experts. Our proposed approach sets a new state-of-the-art performance for multiclass news frame detection, significantly outperforming a recent baseline by 35.9% absolute difference in accuracy. We apply our frame detection approach in a large scale study of 88k news headlines about the coverage of gun violence in the U.S. between 2016 and 2018.