Session-based recommender systems (SBRSs) have shown superior performance over conventional methods. However, they show limited scalability on large-scale industrial datasets since most models learn one embedding per item. This leads to a large memory requirement (of storing one vector per item) and poor performance on sparse sessions with cold-start or unpopular items. Using one public and one large industrial dataset, we experimentally show that state-of-the-art SBRSs have low performance on sparse sessions with sparse items. We propose M2TRec, a Metadata-aware Multi-task Transformer model for session-based recommendations. Our proposed method learns a transformation function from item metadata to embeddings, and is thus, item-ID free (i.e., does not need to learn one embedding per item). It integrates item metadata to learn shared representations of diverse item attributes. During inference, new or unpopular items will be assigned identical representations for the attributes they share with items previously observed during training, and thus will have similar representations with those items, enabling recommendations of even cold-start and sparse items. Additionally, M2TRec is trained in a multi-task setting to predict the next item in the session along with its primary category and subcategories. Our multi-task strategy makes the model converge faster and significantly improves the overall performance. Experimental results show significant performance gains using our proposed approach on sparse items on the two datasets.

We present a novel interactive framework for patent retrieval leveraging distributed representations of concepts and entities extracted from the patents text. We propose a simple and practical interactive relevance feedback mechanism where the user is asked to annotate relevant/irrelevant results from the top n hits. We then utilize this feedback for query reformulation and term weighting where weights are assigned based on how good each term is at discriminating the relevant vs. irrelevant candidates. First, we demonstrate the efficacy of the distributed representations on the CLEF-IP 2010 dataset where we achieve significant improvement of 4.6% in recall over the keyword search baseline. Second, we simulate interactivity to demonstrate the efficacy of our interactive term weighting mechanism. Simulation results show that we can achieve significant improvement in recall from one interaction iteration outperforming previous semantic and interactive patent retrieval methods.

Explicit concept space models have proven efficacy for text representation in many natural language and text mining applications. The idea is to embed textual structures into a semantic space of concepts which captures the main topics of these structures. Despite their wide applicability, existing models have many shortcomings such as sparsity and being restricted to Wikipedia as the main knowledge source from which concepts are extracted. In this paper we highlight some of these limitations. We also describe Mined Semantic Analysis (MSA); a novel concept space model which employs unsupervised learning in order to uncover implicit relations between concepts. MSA leverages the discovered concept-concept associations to enrich the semantic representations. We evaluate MSA’s performance on benchmark data sets for measuring lexical semantic relatedness. Empirical results show superior performance of MSA compared to prior state-of-the-art methods.

Online job boards are one of the central components of modern recruitment industry. With millions of candidates browsing through job postings everyday, the need for accurate, effective, meaningful, and transparent job recommendations is apparent more than ever. While recommendation systems are successfully advancing in variety of online domains by creating social and commercial value, the job recommendation domain is less explored. Existing systems are mostly focused on content analysis of resumes and job descriptions, relying heavily on the accuracy and coverage of the semantic analysis and modeling of the content in which case, they end up usually suffering from rigidity and the lack of implicit semantic relations that are uncovered from users' behavior and could be captured by Collaborative Filtering (CF) methods. Few works which utilize CF do not address the scalability challenges of real-world systems and the problem of cold-start. In this paper, we propose a scalable item-based recommendation system for online job recommendations. Our approach overcomes the major challenges of sparsity and scalability by leveraging a directed graph of jobs connected by multi-edges representing various behavioral and contextual similarity signals. The short lived nature of the items (jobs) in the system and the rapid rate in which new users and jobs enter the system make the cold-start a serious problem hindering CF methods. We address this problem by harnessing the power of deep learning in addition to user behavior to serve hybrid recommendations. Our technique has been leveraged by CareerBuilder.com which is one of the largest job boards in the world to generate high-quality recommendations for millions of users.

Mined Semantic Analysis (MSA) is a novel concept space model which employs unsupervised learning to generate semantic representations of text. MSA represents textual structures (terms, phrases, documents) as a Bag of Concepts (BoC) where concepts are derived from concept rich encyclopedic corpora. Traditional concept space models exploit only target corpus content to construct the concept space. MSA, alternatively, uncovers implicit relations between concepts by mining for their associations (e.g., mining Wikipedia's “See also” link graph). We evaluate MSA's performance on benchmark datasets for measuring semantic relatedness of words and sentences. Empirical results show competitive performance of MSA compared to prior state-of-the-art methods. Additionally, we introduce the first analytical study to examine statistical significance of results reported by different semantic relatedness methods. Our study shows that, the nuances of results across top performing methods could be statistically insignificant. The study positions MSA as one of state-of-the-art methods for measuring semantic relatedness, besides the inherent interpretability and simplicity of the generated semantic representation.

In this demo we present a semantic framework for innovation and patent analytics powered by Mined Semantic Analysis (MSA). Our framework provides cognitive assistance to its users through a Web-based visual and interactive interface. First, we describe building a conceptual knowledge graph by mining user-generated encyclopedic textual corpus for semantic associations. Then, we demonstrate applying the acquired knowledge to support many cognition and knowledge based use cases for innovation analysis including technology exploration and landscaping, competitive analysis, literature and prior art search and others.

Collaborative Filtering (CF) is widely used in large-scale recommendation engines because of its efficiency, accuracy and scalability. However, in practice, the fact that recommendation engines based on CF require interactions between users and items before making recommendations, make it inappropriate for new items which haven't been exposed to the end users to interact with. This is known as the cold-start problem. In this paper we introduce a novel approach which employs deep learning to tackle this problem in any CF based recommendation engine. One of the most important features of the proposed technique is the fact that it can be applied on top of any existing CF based recommendation engine without changing the CF core. We successfully applied this technique to overcome the item cold-start problem in Careerbuilder's CF based recommendation engine. Our experiments show that the proposed technique is very efficient to resolve the cold-start problem while maintaining high accuracy of the CF recommendations.

We present an ensemble approach for categorizing search query entities in the recruitment domain. Understanding the types of entities expressed in a search query (Company, Skill, Job Title, etc.) enables more intelligent information retrieval based upon those entities compared to a traditional keyword-based search. Because search queries are typically very short, leveraging a traditional bag-of-words model to identify entity types would be inappropriate due to the lack of contextual information. Our approach instead combines clues from different sources of varying complexity in order to collect real-world knowledge about query entities. We employ distributional semantic representations of query entities through two models: 1) contextual vectors generated from encyclopedic corpora like Wikipedia, and 2) high dimensional word embedding vectors generated from millions of job postings using word2vec. Additionally, our approach utilizes both entity linguistic properties obtained from WordNet and ontological properties extracted from DBpedia. We evaluate our approach on a data set created at CareerBuilder, the largest job board in the US. The data set contains entities extracted from millions of job seekers/recruiters search queries, job postings, and resume documents. After constructing the distributional vectors of search entities, we use supervised machine learning to infer search entity types. Empirical results show that our approach outperforms the state-of-the-art word2vec distributional semantics model trained on Wikipedia. Moreover, we achieve micro-averaged F1 score of 97% using the proposed distributional representations ensemble.

IBM Watson exemplifies multiple innovations in natural language processing and question answering. In addition, Watson uses most of the known techniques in these two domains as well as many methods from related domains. Hence, there is pedagogical value in a rigorous understanding of its function. The paper provides the description of a text analytics course focused on building a simulator of IBM Watson, conducted in Spring 2014 at UNC Charlotte. We believe this is the first time a simulation containing all the major Watson components was created in a university classroom. The system achieved a respectable (close to) 20% accuracy on Jeopardy! questions, and there remain many known and new avenues of improving performance that can be explored in the future. The code and documentation are available on GitHub. The paper is a joint effort of the teacher and some of the students who were leading teams implementing component technologies, and therefore deeply involved in making the class successful.

In this paper we propose a novel technique for dimensionality reduction using freely available online knowledge bases. The complexity of our method is linearly proportional to the size of the full feature set, making it applicable efficiently to huge and complex datasets. We demonstrate this approach by investigating its effectiveness on patent data, the largest free technical text. We report empirical results on classification of the CLEF-IP 2010 dataset using bigram features supported by mentions in Wikipedia, Wiktionary, and GoogleBooks knowledge bases. We achieve a 13-fold reduction in number of bigrams features and a 1.7% increase in classification accuracy over the unigrams baseline. These results give concrete evidence that significant accuracy improvements and massive reduction in dimensionality could be achieved using our approach, hence help alleviating the tradeoff between task complexity and accuracy.