arXiv subjects

Wang-Chiew Tan

Publications and source records attributed to Wang-Chiew Tan.

30 records · Page 2Linked to original sources

arXiv2019

Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization

We present Emu, a system that semantically enhances multilingual sentence embeddings. Our framework fine-tunes pre-trained multilingual sentence embeddings using two main components: a semantic classifier and a language discriminator. The semantic classifier improves the semantic similarity of related sentences, whereas the language discriminator enhances the multilinguality of the embeddings via multilingual adversarial training. Our experimental results based on several language pairs show that our specialized embeddings outperform the state-of-the-art multilingual sentence embedding model on the task of cross-lingual intent classification using only monolingual labeled data.

cs.CL↗

arXiv2019

Essentia: Mining Domain-Specific Paraphrases with Word-Alignment Graphs

Paraphrases are important linguistic resources for a wide variety of NLP applications. Many techniques for automatic paraphrase mining from general corpora have been proposed. While these techniques are successful at discovering generic paraphrases, they often fail to identify domain-specific paraphrases (e.g., {staff, concierge} in the hospitality domain). This is because current techniques are often based on statistical methods, while domain-specific corpora are too small to fit statistical methods. In this paper, we present an unsupervised graph-based technique to mine paraphrases from a small set of sentences that roughly share the same topic or intent. Our system, Essentia, relies on word-alignment techniques to create a word-alignment graph that merges and organizes tokens from input sentences. The resulting graph is then used to generate candidate paraphrases. We demonstrate that our system obtains high-quality paraphrases, as evaluated by crowd workers. We further show that the majority of the identified paraphrases are domain-specific and thus complement existing paraphrase databases.

cs.CL↗

arXiv2019

Subjective Databases

Online users are constantly seeking experiences, such as a hotel with clean rooms and a lively bar, or a restaurant for a romantic rendezvous. However, e-commerce search engines only support queries involving objective attributes such as location, price, and cuisine, and any experiential data is relegated to text reviews. In order to support experiential queries, a database system needs to model subjective data and also be able to process queries where the user can express varied subjective experiences in words chosen by the user, in addition to specifying predicates involving objective attributes. This paper introduces Opine, a subjective database system that addresses these challenges. We introduce a data model for subjective databases. We describe how Opine translates subjective queries against the subjective database schema, which is done by matching the user query phrases to the underlying schema. We also show how the experiential conditions specified by the user can be combined and the results aggregated and ranked. We demonstrate that subjective databases satisfy user needs more effectively and accurately than alternative techniques through experiments with real data of hotel and restaurant reviews.

cs.DB↗

arXiv2019

Happiness Entailment: Automating Suggestions for Well-Being

Understanding what makes people happy is a central topic in psychology. Prior work has mostly focused on developing self-reporting assessment tools for individuals and relies on experts to analyze the periodic reported assessments. One of the goals of the analysis is to understand what actions are necessary to encourage modifications in the behaviors of the individuals to improve their overall well-being. In this paper, we outline a complementary approach; on the assumption that the user journals her happy moments as short texts, a system can analyze these texts and propose sustainable suggestions for the user that may lead to an overall improvement in her well-being. We prototype one necessary component of such a system, the Happiness Entailment Recognition (HER) module, which takes as input a short text describing an event, a candidate suggestion, and outputs a determination about whether the suggestion is more likely to be good for this user based on the event described. This component is implemented as a neural network model with two encoders, one for the user input and one for the candidate actionable suggestion, with additional layers to capture psychologically significant features in the happy moment and suggestion.

cs.CL↗

arXiv2019

Jo: The Smart Journal

We introduce Jo, a mobile application that attempts to improve user's well-being. Jo is a journaling application--users log their important moments via short texts and optionally an attached photo. Unlike a static journal, Jo analyzes these moments and helps users take action towards increased well-being. For example, Jo annotates each moment with a set of values (e.g., family, socialization, mindfulness), thereby giving the user insights about the balance in their lives. In addition, Jo helps the user create reminders that enable them to create additional happy moments. We describe the results of fielding Jo in a study of 39 participants. The results illustrate the promise of a journaling application that provides personalized feedback, and points at further research.

cs.HC↗

arXiv2019

Open Information Extraction from Question-Answer Pairs

Open Information Extraction (OpenIE) extracts meaningful structured tuples from free-form text. Most previous work on OpenIE considers extracting data from one sentence at a time. We describe NeurON, a system for extracting tuples from question-answer pairs. Since real questions and answers often contain precisely the information that users care about, such information is particularly desirable to extend a knowledge base with. NeurON addresses several challenges. First, an answer text is often hard to understand without knowing the question, and second, relevant information can span multiple sentences. To address these, NeurON formulates extraction as a multi-source sequence-to-sequence learning task, wherein it combines distributed representations of a question and an answer to generate knowledge facts. We describe experiments on two real-world datasets that demonstrate that NeurON can find a significant number of new and interesting facts to extend a knowledge base compared to state-of-the-art OpenIE methods.

cs.CL↗

arXiv2019

Voyageur: An Experiential Travel Search Engine

We describe Voyageur, which is an application of experiential search to the domain of travel. Unlike traditional search engines for online services, experiential search focuses on the experiential aspects of the service under consideration. In particular, Voyageur needs to handle queries for subjective aspects of the service (e.g., quiet hotel, friendly staff) and combine these with objective attributes, such as price and location. Voyageur also highlights interesting facts and tips about the services the user is considering to provide them with further insights into their choices.

cs.DB↗

arXiv2018

Scalable Semantic Querying of Text

We present the KOKO system that takes declarative information extraction to a new level by incorporating advances in natural language processing techniques in its extraction language. KOKO is novel in that its extraction language simultaneously supports conditions on the surface of the text and on the structure of the dependency parse tree of sentences, thereby allowing for more refined extractions. KOKO also supports conditions that are forgiving to linguistic variation of expressing concepts and allows to aggregate evidence from the entire document in order to filter extractions. To scale up, KOKO exploits a multi-indexing scheme and heuristics for efficient extractions. We extensively evaluate KOKO over publicly available text corpora. We show that KOKO indices take up the smallest amount of space, are notably faster and more effective than a number of prior indexing schemes. Finally, we demonstrate KOKO's scale up on a corpus of 5 million Wikipedia articles.

cs.DB↗

arXiv2018

HappyDB: A Corpus of 100,000 Crowdsourced Happy Moments

The science of happiness is an area of positive psychology concerned with understanding what behaviors make people happy in a sustainable fashion. Recently, there has been interest in developing technologies that help incorporate the findings of the science of happiness into users' daily lives by steering them towards behaviors that increase happiness. With the goal of building technology that can understand how people express their happy moments in text, we crowd-sourced HappyDB, a corpus of 100,000 happy moments that we make publicly available. This paper describes HappyDB and its properties, and outlines several important NLP problems that can be studied with the help of the corpus. We also apply several state-of-the-art analysis techniques to analyze HappyDB. Our results demonstrate the need for deeper NLP techniques to be developed which makes HappyDB an exciting resource for follow-on research.

cs.CL↗

arXiv2015

High-Level Why-Not Explanations using Ontologies

We propose a novel foundational framework for why-not explanations, that is, explanations for why a tuple is missing from a query result. Our why-not explanations leverage concepts from an ontology to provide high-level and meaningful reasons for why a tuple is missing from the result of a query. A key algorithmic problem in our framework is that of computing a most-general explanation for a why-not question, relative to an ontology, which can either be provided by the user, or it may be automatically derived from the data and/or schema. We study the complexity of this problem and associated problems, and present concrete algorithms for computing why-not explanations. In the case where an external ontology is provided, we first show that the problem of deciding the existence of an explanation to a why-not question is NP-complete in general. However, the problem is solvable in polynomial time for queries of bounded arity, provided that the ontology is specified in a suitable language, such as a member of the DL-Lite family of description logics, which allows for efficient concept subsumption checking. Furthermore, we show that a most-general explanation can be computed in polynomial time in this case. In addition, we propose a method for deriving a suitable (virtual) ontology from a database and/or a data workspace schema, and we present an algorithm for computing a most-general explanation to a why-not question, relative to such ontologies. This algorithm runs in polynomial-time in the case when concepts are defined in a selection-free language, or if the underlying schema is fixed. Finally, we also study the problem of computing short most-general explanations, and we briefly discuss alternative definitions of what it means to be an explanation, and to be most general.

cs.DB↗

arXiv2009

Laconic schema mappings: computing core universal solutions by means of SQL queries

We present a new method for computing core universal solutions in data exchange settings specified by source-to-target dependencies, by means of SQL queries. Unlike previously known algorithms, which are recursive in nature, our method can be implemented directly on top of any DBMS. Our method is based on the new notion of a laconic schema mapping. A laconic schema mapping is a schema mapping for which the canonical universal solution is the core universal solution. We give a procedure by which every schema mapping specified by FO s-t tgds can be turned into a laconic schema mapping specified by FO s-t tgds that may refer to a linear order on the domain of the source instance. We show that our results are optimal, in the sense that the linear order is necessary and the method cannot be extended to schema mapping involving target constraints.

cs.DB↗

arXiv2000

Towards a query language for annotation graphs

The multidimensional, heterogeneous, and temporal nature of speech databases raises interesting challenges for representation and query. Recently, annotation graphs have been proposed as a general-purpose representational framework for speech databases. Typical queries on annotation graphs require path expressions similar to those used in semistructured query languages. However, the underlying model is rather different from the customary graph models for semistructured data: the graph is acyclic and unrooted, and both temporal and inclusion relationships are important. We develop a query language and describe optimization techniques for an underlying relational representation.

cs.CL↗