arXiv subjects

Yashar Mehdad

Publications and source records attributed to Yashar Mehdad.

42 records · Page 3Linked to original sources

arXiv2020

Conversational Semantic Parsing

The structured representation for semantic parsing in task-oriented assistant systems is geared towards simple understanding of one-turn queries. Due to the limitations of the representation, the session-based properties such as co-reference resolution and context carryover are processed downstream in a pipelined system. In this paper, we propose a semantic representation for such task-oriented conversational systems that can represent concepts such as co-reference and context carryover, enabling comprehensive understanding of queries in a session. We release a new session-based, compositional task-oriented parsing dataset of 20k sessions consisting of 60k utterances. Unlike Dialog State Tracking Challenges, the queries in the dataset have compositional forms. We propose a new family of Seq2Seq models for the session-based parsing above, which achieve better or comparable performance to the current state-of-the-art on ATIS, SNIPS, TOP and DSTC2. Notably, we improve the best known results on DSTC2 by up to 5 points for slot-carryover.

cs.CL↗

arXiv2017

DocTag2Vec: An Embedding Based Multi-label Learning Approach for Document Tagging

Tagging news articles or blog posts with relevant tags from a collection of predefined ones is coined as document tagging in this work. Accurate tagging of articles can benefit several downstream applications such as recommendation and search. In this work, we propose a novel yet simple approach called DocTag2Vec to accomplish this task. We substantially extend Word2Vec and Doc2Vec---two popular models for learning distributed representation of words and documents. In DocTag2Vec, we simultaneously learn the representation of words, documents, and tags in a joint vector space during training, and employ the simple $k$-nearest neighbor search to predict tags for unseen documents. In contrast to previous multi-label learning methods, DocTag2Vec directly deals with raw text instead of provided feature vector, and in addition, enjoys advantages like the learning of tag representation, and the ability of handling newly created tags. To demonstrate the effectiveness of our approach, we conduct experiments on several datasets and show promising results against state-of-the-art methods.

cs.CL↗

arXiv2017

Online Article Ranking as a Constrained, Dynamic, Multi-Objective Optimization Problem

The content ranking problem in a social news website, is typically a function that maximizes a scalar metric of interest like dwell-time. However, like in most real-world applications we are interested in more than one metric---for instance simultaneously maximizing click-through rate, monetization metrics, dwell-time---and also satisfy the traffic requirements promised to different publishers. All this needs to be done on online data and under the settings where the objective function and the constraints can dynamically change; this could happen if for instance new publishers are added, some contracts are adjusted, or if some contracts are over. In this paper, we formulate this problem as a constrained, dynamic, multi-objective optimization problem. We propose a novel framework that extends a successful genetic optimization algorithm, NSGA-II, to solve this online, data-driven problem. We design the modules of NSGA-II to suit our problem. We evaluate optimization performance using Hypervolume and introduce a confidence interval metric for assessing the practicality of a solution. We demonstrate the application of this framework on a real-world Article Ranking problem. We observe that we make considerable improvements in both time and performance over a brute-force baseline technique that is currently in production.

cs.AI↗

arXiv2017

Rank-to-engage: New Listwise Approaches to Maximize Engagement

For many internet businesses, presenting a given list of items in an order that maximizes a certain metric of interest (e.g., click-through-rate, average engagement time etc.) is crucial. We approach the aforementioned task from a learning-to-rank perspective which reveals a new problem setup. In traditional learning-to-rank literature, it is implicitly assumed that during the training data generation one has access to the \emph{best or desired} order for the given list of items. In this work, we consider a problem setup where we do not observe the desired ranking. We present two novel solutions: the first solution is an extension of already existing listwise learning-to-rank technique--Listwise maximum likelihood estimation (ListMLE)--while the second one is a generic machine learning based framework that tackles the problem in its entire generality. We discuss several challenges associated with this generic framework, and propose a simple \emph{item-payoff} and \emph{positional-gain} model that addresses these challenges. We provide training algorithms, inference procedures, and demonstrate the effectiveness of the two approaches over traditional ListMLE on synthetic as well as on real-life setting of ranking news articles for increased dwell time.

stat.ML↗

arXiv2017

RIPML: A Restricted Isometry Property based Approach to Multilabel Learning

The multilabel learning problem with large number of labels, features, and data-points has generated a tremendous interest recently. A recurring theme of these problems is that only a few labels are active in any given datapoint as compared to the total number of labels. However, only a small number of existing work take direct advantage of this inherent extreme sparsity in the label space. By the virtue of Restricted Isometry Property (RIP), satisfied by many random ensembles, we propose a novel procedure for multilabel learning known as RIPML. During the training phase, in RIPML, labels are projected onto a random low-dimensional subspace followed by solving a least-square problem in this subspace. Inference is done by a k-nearest neighbor (kNN) based approach. We demonstrate the effectiveness of RIPML by conducting extensive simulations and comparing results with the state-of-the-art linear dimensionality reduction based approaches.

cs.IR↗

arXiv2016

Domain Adaptation for Named Entity Recognition in Online Media with Word Embeddings

Content on the Internet is heterogeneous and arises from various domains like News, Entertainment, Finance and Technology. Understanding such content requires identifying named entities (persons, places and organizations) as one of the key steps. Traditionally Named Entity Recognition (NER) systems have been built using available annotated datasets (like CoNLL, MUC) and demonstrate excellent performance. However, these models fail to generalize onto other domains like Sports and Finance where conventions and language use can differ significantly. Furthermore, several domains do not have large amounts of annotated labeled data for training robust Named Entity Recognition models. A key step towards this challenge is to adapt models learned on domains where large amounts of annotated training data are available to domains with scarce annotated data. In this paper, we propose methods to effectively adapt models learned on one domain onto other domains using distributed word representations. First we analyze the linguistic variation present across domains to identify key linguistic insights that can boost performance across domains. We propose methods to capture domain specific semantics of word usage in addition to global semantics. We then demonstrate how to effectively use such domain specific knowledge to learn NER models that outperform previous baselines in the domain adaptation setting.

cs.CL↗