Previous works related to automatic personality recognition focus on using traditional classification models with linguistic features. However, attentive neural networks with contextual embeddings, which have achieved huge success in text classification, are rarely explored for this task. In this project, we have two major contributions. First, we create the first dialogue-based personality dataset, FriendsPersona, by annotating 5 personality traits of speakers from Friends TV Show through crowdsourcing. Second, we present a novel approach to automatic personality recognition using pre-trained contextual embeddings (BERT and RoBERTa) and attentive neural networks. Our models largely improve the state-of-art results on the monologue Essays dataset by 2.49%, and establish a solid benchmark on our FriendsPersona. By comparing results in two datasets, we demonstrate the challenges of modeling personality in multi-party dialogue.
We present a novel online algorithm that learns the essence of each dimension in word embeddings by minimizing the within-group distance of contextualized embedding groups. Three state-of-the-art neural-based language models are used, Flair, ELMo, and BERT, to generate contextualized word embeddings such that different embeddings are generated for the same word type, which are grouped by their senses manually annotated in the SemCor dataset. We hypothesize that not all dimensions are equally important for downstream tasks so that our algorithm can detect unessential dimensions and discard them without hurting the performance. To verify this hypothesis, we first mask dimensions determined unessential by our algorithm, apply the masked word embeddings to a word sense disambiguation task (WSD), and compare its performance against the one achieved by the original embeddings. Several KNN approaches are experimented to establish strong baselines for WSD. Our results show that the masked word embeddings do not hurt the performance and can improve it by 3%. Our work can be used to conduct future research on the interpretability of contextualized embeddings.
This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT. For each task, we first replicate and simplify the current state-of-the-art approach to enhance its model efficiency. We then evaluate our simplified approaches on those three tasks using token embeddings generated by BERT. 12 datasets in both English and Chinese are used for our experiments. The BERT models outperform the previously best-performing models by 2.5% on average (7.5% for the most significant case). Moreover, an in-depth analysis on the impact of BERT embeddings is provided using self-attention, which helps understanding in this rich yet representation. All models and source codes are available in public so that researchers can improve upon and utilize them to establish strong baselines for the next decade.
Recent advances in deep learning have facilitated the demand of neural models for real applications. In practice, these applications often need to be deployed with limited resources while keeping high accuracy. This paper touches the core of neural models in NLP, word embeddings, and presents a new embedding distillation framework that remarkably reduces the dimension of word embeddings without compromising accuracy. A novel distillation ensemble approach is also proposed that trains a high-efficient student model using multiple teacher models. In our approach, the teacher models play roles only during training such that the student model operates on its own without getting supports from the teacher models during decoding, which makes it eighty times faster and lighter than other typical ensemble methods. All models are evaluated on seven document classification datasets and show a significant advantage over the teacher models for most cases. Our analysis depicts insightful transformation of word embeddings from distillation and suggests a future direction to ensemble approaches using neural models.
Electronic Health Records (EHRs) have been heavily used to predict various downstream clinical tasks such as readmission or mortality. One of the modalities in EHRs, clinical notes, has not been fully explored for these tasks due to its unstructured and inexplicable nature. Although recent advances in deep learning (DL) enables models to extract interpretable features from unstructured data, they often require a large amount of training data. However, many tasks in medical domains inherently consist of small sample data with lengthy documents; for a kidney transplant as an example, data from only a few thousand of patients are available and each patient's document consists of a couple of millions of words in major hospitals. Thus, complex DL methods cannot be applied to these kinds of domains. In this paper, we present a comprehensive ensemble model using vector space modeling and topic modeling. Our proposed model is evaluated on the readmission task of kidney transplant patients and improves 0.0211 in terms of c-statistics from the previous state-of-the-art approach using structured data, while typical DL methods fail to beat this approach. The proposed architecture provides the interpretable score for each feature from both modalities, structured and unstructured data, which is shown to be meaningful through a physician's evaluation.
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.
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.
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.
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.
Transferring knowledge from a source domain to another domain is useful, especially when gathering new data is very expensive and time-consuming. Deep networks have been well-studied for question answering tasks in recent years; however, no prominent research for transfer learning through deep neural networks exists in the question answering field. In this paper, two main methods (INIT and MULT) in this field are examined. Then, a new method named Intelligent sample selection (ISS-MULT) is proposed to improve the MULT method for question answering tasks. Different datasets, specificay SQuAD, SelQA, WikiQA, NewWikiQA and InforBoxQA, are used for evaluation. Moreover, two different tasks of question answering - answer selection and answer triggering - are evaluated to examine the effectiveness of transfer learning. The results show that using transfer learning generally improves the performance if the corpora are related and are based on the same policy. In addition, using ISS-MULT could finely improve the MULT method for question answering tasks, and these improvements prove more significant in the answer triggering task.