arXiv subjects

Jinho D. Choi

Publications and source records attributed to Jinho D. Choi.

82 records · Page 5Linked to original sources

arXiv2018

Analysis of Wikipedia-based Corpora for Question Answering

This paper gives comprehensive analyses of corpora based on Wikipedia for several tasks in question answering. Four recent corpora are collected,WikiQA, SelQA, SQuAD, and InfoQA, and first analyzed intrinsically by contextual similarities, question types, and answer categories. These corpora are then analyzed extrinsically by three question answering tasks, answer retrieval, selection, and triggering. An indexing-based method for the creation of a silver-standard dataset for answer retrieval using the entire Wikipedia is also presented. Our analysis shows the uniqueness of these corpora and suggests a better use of them for statistical question answering learning.

cs.CL↗

arXiv2017

Lexicon Integrated CNN Models with Attention for Sentiment Analysis

With the advent of word embeddings, lexicons are no longer fully utilized for sentiment analysis although they still provide important features in the traditional setting. This paper introduces a novel approach to sentiment analysis that integrates lexicon embeddings and an attention mechanism into Convolutional Neural Networks. Our approach performs separate convolutions for word and lexicon embeddings and provides a global view of the document using attention. Our models are experimented on both the SemEval'16 Task 4 dataset and the Stanford Sentiment Treebank, and show comparative or better results against the existing state-of-the-art systems. Our analysis shows that lexicon embeddings allow to build high-performing models with much smaller word embeddings, and the attention mechanism effectively dims out noisy words for sentiment analysis.

cs.CL↗

arXiv2017

Classification of Radiology Reports Using Neural Attention Models

The electronic health record (EHR) contains a large amount of multi-dimensional and unstructured clinical data of significant operational and research value. Distinguished from previous studies, our approach embraces a double-annotated dataset and strays away from obscure "black-box" models to comprehensive deep learning models. In this paper, we present a novel neural attention mechanism that not only classifies clinically important findings. Specifically, convolutional neural networks (CNN) with attention analysis are used to classify radiology head computed tomography reports based on five categories that radiologists would account for in assessing acute and communicable findings in daily practice. The experiments show that our CNN attention models outperform non-neural models, especially when trained on a larger dataset. Our attention analysis demonstrates the intuition behind the classifier's decision by generating a heatmap that highlights attended terms used by the CNN model; this is valuable when potential downstream medical decisions are to be performed by human experts or the classifier information is to be used in cohort construction such as for epidemiological studies.

cs.CL↗

arXiv2017

Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks

While there have been significant advances in detecting emotions from speech and image recognition, emotion detection on text is still under-explored and remained as an active research field. This paper introduces a corpus for text-based emotion detection on multiparty dialogue as well as deep neural models that outperform the existing approaches for document classification. We first present a new corpus that provides annotation of seven emotions on consecutive utterances in dialogues extracted from the show, Friends. We then suggest four types of sequence-based convolutional neural network models with attention that leverage the sequence information encapsulated in dialogue. Our best model shows the accuracies of 37.9% and 54% for fine- and coarse-grained emotions, respectively. Given the difficulty of this task, this is promising.

cs.CL↗

arXiv2017

Cross-genre Document Retrieval: Matching between Conversational and Formal Writings

This paper challenges a cross-genre document retrieval task, where the queries are in formal writing and the target documents are in conversational writing. In this task, a query, is a sentence extracted from either a summary or a plot of an episode in a TV show, and the target document consists of transcripts from the corresponding episode. To establish a strong baseline, we employ the current state-of-the-art search engine to perform document retrieval on the dataset collected for this work. We then introduce a structure reranking approach to improve the initial ranking by utilizing syntactic and semantic structures generated by NLP tools. Our evaluation shows an improvement of more than 4% when the structure reranking is applied, which is very promising.

cs.CL↗

arXiv2017

Improving Document Clustering by Eliminating Unnatural Language

Technical documents contain a fair amount of unnatural language, such as tables, formulas, pseudo-codes, etc. Unnatural language can be an important factor of confusing existing NLP tools. This paper presents an effective method of distinguishing unnatural language from natural language, and evaluates the impact of unnatural language detection on NLP tasks such as document clustering. We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories. First, we create a new annotated corpus by collecting slides and papers in various formats, PPT, PDF, and HTML, where unnatural language components are annotated into four categories. We then explore features available from plain text to build a statistical model that can handle any format as long as it is converted into plain text. Our experiments show that removing unnatural language components gives an absolute improvement in document clustering up to 15%. Our corpus and tool are publicly available.

cs.IR↗

arXiv2016

SelQA: A New Benchmark for Selection-based Question Answering

This paper presents a new selection-based question answering dataset, SelQA. The dataset consists of questions generated through crowdsourcing and sentence length answers that are drawn from the ten most prevalent topics in the English Wikipedia. We introduce a corpus annotation scheme that enhances the generation of large, diverse, and challenging datasets by explicitly aiming to reduce word co-occurrences between the question and answers. Our annotation scheme is composed of a series of crowdsourcing tasks with a view to more effectively utilize crowdsourcing in the creation of question answering datasets in various domains. Several systems are compared on the tasks of answer sentence selection and answer triggering, providing strong baseline results for future work to improve upon.

cs.CL↗

arXiv2016

Multi-Field Structural Decomposition for Question Answering

This paper presents a precursory yet novel approach to the question answering task using structural decomposition. Our system first generates linguistic structures such as syntactic and semantic trees from text, decomposes them into multiple fields, then indexes the terms in each field. For each question, it decomposes the question into multiple fields, measures the relevance score of each field to the indexed ones, then ranks all documents by their relevance scores and weights associated with the fields, where the weights are learned through statistical modeling. Our final model gives an absolute improvement of over 40% to the baseline approach using simple search for detecting documents containing answers.

cs.CL↗

arXiv2014

Targetable Named Entity Recognition in Social Media

We present a novel approach for recognizing what we call targetable named entities; that is, named entities in a targeted set (e.g, movies, books, TV shows). Unlike many other NER systems that need to retrain their statistical models as new entities arrive, our approach does not require such retraining, which makes it more adaptable for types of entities that are frequently updated. For this preliminary study, we focus on one entity type, movie title, using data collected from Twitter. Our system is tested on two evaluation sets, one including only entities corresponding to movies in our training set, and the other excluding any of those entities. Our final model shows F1-scores of 76.19% and 78.70% on these evaluation sets, which gives strong evidence that our approach is completely unbiased to any par- ticular set of entities found during training.

cs.CL↗

arXiv2013

Preparing Korean Data for the Shared Task on Parsing Morphologically Rich Languages

This document gives a brief description of Korean data prepared for the SPMRL 2013 shared task. A total of 27,363 sentences with 350,090 tokens are used for the shared task. All constituent trees are collected from the KAIST Treebank and transformed to the Penn Treebank style. All dependency trees are converted from the transformed constituent trees using heuristics and labeling rules de- signed specifically for the KAIST Treebank. In addition to the gold-standard morphological analysis provided by the KAIST Treebank, two sets of automatic morphological analysis are provided for the shared task, one is generated by the HanNanum morphological analyzer, and the other is generated by the Sejong morphological analyzer.

cs.CL↗