AI is poised to drive the next wave of technological disruption across industries. Like previous technology revolutions in Web and mobile, however, there will be huge dividends for those organizations who can harness this technology for competitive advantage.

We propose post-processing method for enriching not only word representation but also its vector space using semantic lexicons, which we call extrofitting. The method consists of 3 steps as follows: (i) Expanding 1 or more dimension(s) on all the word vectors, filling with their representative value. (ii) Transferring semantic knowledge by averaging each representative values of synonyms and filling them in the expanded dimension(s). These two steps make representations of the synonyms close together. (iii) Projecting the vector space using Linear Discriminant Analysis, which eliminates the expanded dimension(s) with semantic knowledge. When experimenting with GloVe, we find that our method outperforms Faruqui's retrofitting on some of word similarity task. We also report further analysis on our method in respect to word vector dimensions, vocabulary size as well as other well-known pretrained word vectors (e.g., Word2Vec, Fasttext).

We introduce KBGAN, an adversarial learning framework to improve the performances of a wide range of existing knowledge graph embedding models. Because knowledge graphs typically only contain positive facts, sampling useful negative training examples is a non-trivial task. Replacing the head or tail entity of a fact with a uniformly randomly selected entity is a conventional method for generating negative facts, but the majority of the generated negative facts can be easily discriminated from positive facts, and will contribute little towards the training. Inspired by generative adversarial networks (GANs), we use one knowledge graph embedding model as a negative sample generator to assist the training of our desired model, which acts as the discriminator in GANs. This framework is independent of the concrete form of generator and discriminator, and therefore can utilize a wide variety of knowledge graph embedding models as its building blocks. In experiments, we adversarially train two translation-based models, TransE and TransD, each with assistance from one of the two probability-based models, DistMult and ComplEx. We evaluate the performances of KBGAN on the link prediction task, using three knowledge base completion datasets: FB15k-237, WN18 and WN18RR. Experimental results show that adversarial training substantially improves the performances of target embedding models under various settings.

Google's mobile site as well as its iOS and Android apps introduced a feature that aims to track down information on medical symptoms. Instead of having to search for a condition, you can search for a certain symptom, such as "my stomach hurts."

A modular conversational dialog system, in contrast to end-to-end, includes natural language understanding, dialog management, and natural language generation components. A dialog system framework simplifies development and maintenance of modular dialog systems. We propose a knowledge graph driven framework (KGD) based on the Information State Update (ISU) approach and adapted for practical task oriented applications. With the proposed framework, a system is defined declaratively by describing the information structure of a domain. We demonstrate the effectiveness of the approach in enabling rich conversational dialog in food ordering domain.

Knowledge Graph Embedding methods aim at representing entities and relations in a knowledge base as points or vectors in a continuous vector space. Several approaches using embeddings have shown promising results on tasks such as link prediction, entity recommendation, question answering, and triplet classification. However, only a few methods can compute low-dimensional embeddings of very large knowledge bases. In this paper, we propose KG2Vec, a novel approach to Knowledge Graph Embedding based on the skip-gram model. Instead of using a predefined scoring function, we learn it relying on Long Short-Term Memories. We evaluated the goodness of our embeddings on knowledge graph completion and show that KG2Vec is comparable to the quality of the scalable state-of-the-art approaches and can process large graphs by parsing more than a hundred million triples in less than 6 hours on common hardware.

AI is poised to drive the next wave of technological disruption across industries. Like previous technology revolutions in Web and mobile, however, there will be huge dividends for those organizations who can harness this technology for competitive advantage. I spend a lot of time working with customers, many of whom are investing significant time and effort in building AI applications for this very reason. From the outside, these applications couldn't be more diverse – fraud detection, retail recommendation engines, knowledge sharing – but I see a sweeping opportunity across the board: context. Without context (who the user is, what they are searching for, what similar users have searched for in the past, and how all these connections play together) these AI applications may never reach their full potential.

Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a few top dominating directions from the word vectors -- that renders off-the-shelf representations {\em even stronger}. The postprocessing is empirically validated on a variety of lexical-level intrinsic tasks (word similarity, concept categorization, word analogy) and sentence-level tasks (semantic textural similarity and { text classification}) on multiple datasets and with a variety of representation methods and hyperparameter choices in multiple languages; in each case, the processed representations are consistently better than the original ones.

To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based and path-based methods for knowledge-graph-aware recommendation, we propose Ripple Network, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems. Similar to actual ripples propagating on the surface of water, Ripple Network stimulates the propagation of user preferences over the set of knowledge entities by automatically and iteratively extending a user's potential interests along links in the knowledge graph. The multiple "ripples" activated by a user's historically clicked items are thus superposed to form the preference distribution of the user with respect to a candidate item, which could be used for predicting the final clicking probability. Through extensive experiments on real-world datasets, we demonstrate that Ripple Network achieves substantial gains in a variety of scenarios, including movie, book and news recommendation, over several state-of-the-art baselines.

IDO DAGAN TITLE: Open Knowledge Graphs: Consolidating and Exploring Textual Information ABSTRACT: How can we capture effectively the information expressed in multiple texts? How can we allow people, as well as computer applications, to easily explore it? The current semantic NLP pipeline typically ends at the single sentence level, putting the burden on applications to consolidate related information that is spread across different texts. Further, semantic representations are often based on non-trivial pre-specified schemata, which require expert annotation and hence complicate the creation of large scale corpora for effective training. In this talk, I will outline a proposal for a novel open representation of the information exressed jointly by multiple texts, which we term Open Knowledge Graphs (OKG). First, we follow the spirit of "open" semantic approaches, such as Open Information Extraction (OIE) and more concretely the recent Question-Answer SRL (QA-SRL) paradigm, which represent semantic structure solely via natural language expressions.