NAACL 2018 Papers

Coding EMRs with diagnosis and procedure codes is an indispensable task for billing, secondary data analyses, and monitoring health trends. Both speed and accuracy of coding are critical. While coding errors could lead to more patient-side financial burden and misinterpretation of a patient’s well-being, timely coding is also needed to avoid backlogs and additional costs for the healthcare facility. In this paper, we present a new neural network architecture that combines ideas from few-shot learning matching networks, multi-label loss functions, and convolutional neural networks for text classification to significantly outperform other state-of-the-art models. Our evaluations are conducted using a well known de-identified EMR dataset (MIMIC) with a variety of multi-label performance measures.

It has been proven that automatic conversational agents can be built up using the Endto-End Neural Response Generation (NRG) framework, and such a data-driven methodology requires a large number of dialog pairs for model training and reasonable evaluation metrics for testing. This paper proposes a Large Scale Domain-Specific Conversational Corpus (LSDSCC) composed of high-quality queryresponse pairs extracted from the domainspecific online forum, with thorough preprocessing and cleansing procedures. Also, a testing set, including multiple diverse responses annotated for each query, is constructed, and on this basis, the metrics for measuring the diversity of generated results are further presented. We evaluate the performances of neural dialog models with the widely applied diversity boosting strategies on the proposed dataset. The experimental results have shown that our proposed corpus can be taken as a new benchmark dataset for the NRG task, and the presented metrics are promising to guide the optimization of NRG models by quantifying the diversity of the generated responses reasonably.

In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction with users by learning from human teaching and feedback. We design a neural network based task-oriented dialogue agent that can be optimized end-to-end with the proposed learning method. Experimental results show that our end-to-end dialogue agent can learn effectively from the mistake it makes via imitation learning from user teaching. Applying reinforcement learning with user feedback after the imitation learning stage further improves the agent’s capability in successfully completing a task.

In this paper, we propose a generalizable dialog generation approach that adapts multi-turn reasoning, one recent advancement in the field of document comprehension, to generate responses (“answers”) by taking current conversation session context as a “document” and current query as a “question”. The major idea is to represent a conversation session into memories upon which attention-based memory reading mechanism can be performed multiple times, so that (1) user’s query is properly extended by contextual clues and (2) optimal responses are step-by-step generated. Considering that the speakers of one conversation are not limited to be one, we separate the single memory used for document comprehension into different groups for speaker-specific topic and opinion embedding. Namely, we utilize the queries’ memory, the responses’ memory, and their unified memory, following the time sequence of the conversation session. Experiments on Japanese 10-sentence (5-round) conversation modeling show impressive results on how multi-turn reasoning can produce more diverse and acceptable responses than state-of-the-art single-turn and non-reasoning baselines.

This paper presents a new corpus and a robust deep learning architecture for a task in reading comprehension, passage completion, on multiparty dialog. Given a dialog in text and a passage containing factual descriptions about the dialog where mentions of the characters are replaced by blanks, the task is to fill the blanks with the most appropriate character names that reflect the contexts in the dialog. Since there is no dataset that challenges the task of passage completion in this genre, we create a corpus by selecting transcripts from a TV show that comprise 1,681 dialogs, generating passages for each dialog through crowdsourcing, and annotating mentions of characters in both the dialog and the passages. Given this dataset, we build a deep neural model that integrates rich feature extraction from convolutional neural networks into sequence modeling in recurrent neural networks, optimized by utterance and dialog level attentions. Our model outperforms the previous state-of-the-art model on this task in a different genre using bidirectional LSTM, showing a 13.0+% improvement for longer dialogs. Our analysis shows the effectiveness of the attention mechanisms and suggests a direction to machine comprehension on multiparty dialog.

When learning POS taggers and syntactic chunkers for low-resource languages, different resources may be available, and often all we have is a small tag dictionary, motivating type-constrained unsupervised induction. Even small dictionaries can improve the performance of unsupervised induction algorithms. This paper shows that performance can be further improved by including data that is readily available or can be easily obtained for most languages, i.e., eye-tracking, speech, or keystroke logs (or any combination thereof). We project information from all these data sources into shared spaces, in which the union of words is represented. For English unsupervised POS induction, the additional information, which is not required at test time, leads to an average error reduction on Ontonotes domains of 1.5% over systems augmented with state-of-the-art word embeddings. On Penn Treebank the best model achieves 5.4% error reduction over a word embeddings baseline. We also achieve significant improvements for syntactic chunk induction. Our analysis shows that improvements are even bigger when the available tag dictionaries are smaller.

This paper explores the time course of lexical memory retrieval by modeling fluent language production. The duration of retrievals is predicted using the ACT-R cognitive architecture. In a large-scale observational study of a spoken corpus, we find that language production at a time point preceding a word is sped up or slowed down depending on activation of that word. This computational analysis has consequences for the theoretical model of language production. The results point to interference between lexical and phonological stages as well as a quantifiable buffer for lexical information that opens up the possibility of non-sequential retrievals.

Automatic identification of spurious instances (those with potentially wrong labels in datasets) can improve the quality of existing language resources, especially when annotations are obtained through crowdsourcing or automatically generated based on coded rankings. In this paper, we present effective approaches inspired by queueing theory and psychology of learning to automatically identify spurious instances in datasets. Our approaches discriminate instances based on their “difficulty to learn,” determined by a downstream learner. Our methods can be applied to any dataset assuming the existence of a neural network model for the target task of the dataset. Our best approach outperforms competing state-of-the-art baselines and has a MAP of 0.85 and 0.22 in identifying spurious instances in synthetic and carefully-crowdsourced real-world datasets respectively.

Speakers often have more than one way to express the same meaning. What general principles govern speaker choice in the face of optionality when near semantically invariant alternation exists? Studies have shown that optional reduction in language is sensitive to contextual predictability, such that more predictable a linguistic unit is, the more likely it is to get reduced. Yet it is unclear whether these cases of speaker choice are driven by audience design versus toward facilitating production. Here we argue that for a different optionality phenomenon, namely classifier choice in Mandarin Chinese, Uniform Information Density and at least one plausible variant of availability-based production make opposite predictions regarding the relationship between the predictability of the upcoming material and speaker choices. In a corpus analysis of Mandarin Chinese, we show that the distribution of speaker choices supports the availability-based production account and not the Uniform Information Density.

We present a novel approach for determining learners’ second language proficiency which utilizes behavioral traces of eye movements during reading. Our approach provides stand-alone eyetracking based English proficiency scores which reflect the extent to which the learner’s gaze patterns in reading are similar to those of native English speakers. We show that our scores correlate strongly with standardized English proficiency tests. We also demonstrate that gaze information can be used to accurately predict the outcomes of such tests. Our approach yields the strongest performance when the test taker is presented with a suite of sentences for which we have eyetracking data from other readers. However, it remains effective even using eyetracking with sentences for which eye movement data have not been previously collected. By deriving proficiency as an automatic byproduct of eye movements during ordinary reading, our approach offers a potentially valuable new tool for second language proficiency assessment. More broadly, our results open the door to future methods for inferring reader characteristics from the behavioral traces of reading.

Natural Language Inference is a challenging task that has received substantial attention, and state-of-the-art models now achieve impressive test set performance in the form of accuracy scores. Here, we go beyond this single evaluation metric to examine robustness to semantically-valid alterations to the input data. We identify three factors - insensitivity, polarity and unseen pairs - and compare their impact on three SNLI models under a variety of conditions. Our results demonstrate a number of strengths and weaknesses in the models’ ability to generalise to new in-domain instances. In particular, while strong performance is possible on unseen hypernyms, unseen antonyms are more challenging for all the models. More generally, the models suffer from an insensitivity to certain small but semantically significant alterations, and are also often influenced by simple statistical correlations between words and training labels. Overall, we show that evaluations of NLI models can benefit from studying the influence of factors intrinsic to the models or found in the dataset used.

Election manifestos document the intentions, motives, and views of political parties. They are often used for analysing a party’s fine-grained position on a particular issue, as well as for coarse-grained positioning of a party on the left–right spectrum. In this paper we propose a two-stage model for automatically performing both levels of analysis over manifestos. In the first step we employ a hierarchical multi-task structured deep model to predict fine- and coarse-grained positions, and in the second step we perform post-hoc calibration of coarse-grained positions using probabilistic soft logic. We empirically show that the proposed model outperforms state-of-art approaches at both granularities using manifestos from twelve countries, written in ten different languages.

We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reason about why speakers produce certain instructions, and about how listeners will react upon hearing them. Like previous pragmatic models, we use learned base listener and speaker models to build a pragmatic speaker that uses the base listener to simulate the interpretation of candidate descriptions, and a pragmatic listener that reasons counterfactually about alternative descriptions. We extend these models to tasks with sequential structure. Evaluation of language generation and interpretation shows that pragmatic inference improves state-of-the-art listener models (at correctly interpreting human instructions) and speaker models (at producing instructions correctly interpreted by humans) in diverse settings.

We explore deception detection in interview dialogues. We analyze a set of linguistic features in both truthful and deceptive responses to interview questions. We also study the perception of deception, identifying characteristics of statements that are perceived as truthful or deceptive by interviewers. Our analysis show significant differences between truthful and deceptive question responses, as well as variations in deception patterns across gender and native language. This analysis motivated our selection of features for machine learning experiments aimed at classifying globally deceptive speech. Our best classification performance is 72.74% F1-Score (about 17% better than human performance), which is achieved using a combination of linguistic features and individual traits.

Reasoning is a crucial part of natural language argumentation. To comprehend an argument, one must analyze its warrant, which explains why its claim follows from its premises. As arguments are highly contextualized, warrants are usually presupposed and left implicit. Thus, the comprehension does not only require language understanding and logic skills, but also depends on common sense. In this paper we develop a methodology for reconstructing warrants systematically. We operationalize it in a scalable crowdsourcing process, resulting in a freely licensed dataset with warrants for 2k authentic arguments from news comments. On this basis, we present a new challenging task, the argument reasoning comprehension task. Given an argument with a claim and a premise, the goal is to choose the correct implicit warrant from two options. Both warrants are plausible and lexically close, but lead to contradicting claims. A solution to this task will define a substantial step towards automatic warrant reconstruction. However, experiments with several neural attention and language models reveal that current approaches do not suffice.

We often talk about events that impact us positively or negatively. For example “I got a job” is good news, but “I lost my job” is bad news. When we discuss an event, we not only understand its affective polarity but also the reason why the event is beneficial or detrimental. For example, getting or losing a job has affective polarity primarily because it impacts us financially. Our work aims to categorize affective events based upon human need categories that often explain people’s motivations and desires: PHYSIOLOGICAL, HEALTH, LEISURE, SOCIAL, FINANCIAL, COGNITION, and FREEDOM. We create classification models based on event expressions as well as models that use contexts surrounding event mentions. We also design a co-training model that learns from unlabeled data by simultaneously training event expression and event context classifiers in an iterative learning process. Our results show that co-training performs well, producing substantially better results than the individual classifiers.

Predicting the emotional value of lexical items is a well-known problem in sentiment analysis. While research has focused on polarity for quite a long time, meanwhile this early focus has been shifted to more expressive emotion representation models (such as Basic Emotions or Valence-Arousal-Dominance). This change resulted in a proliferation of heterogeneous formats and, in parallel, often small-sized, non-interoperable resources (lexicons and corpus annotations). In particular, the limitations in size hampered the application of deep learning methods in this area because they typically require large amounts of input data. We here present a solution to get around this language data bottleneck by rephrasing word emotion induction as a multi-task learning problem. In this approach, the prediction of each independent emotion dimension is considered as an individual task and hidden layers are shared between these dimensions. We investigate whether multi-task learning is more advantageous than single-task learning for emotion prediction by comparing our model against a wide range of alternative emotion and polarity induction methods featuring 9 typologically diverse languages and a total of 15 conditions. Our model turns out to outperform each one of them. Against all odds, the proposed deep learning approach yields the largest gain on the smallest data sets, merely composed of one thousand samples.

We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of tasks with disparate label spaces. We outperform strong single and multi-task baselines and achieve a new state of the art for aspect-based and topic-based sentiment analysis.

Sentiment analysis is used as a proxy to measure human emotion, where the objective is to categorize text according to some predefined notion of sentiment. Sentiment analysis datasets are typically constructed with gold-standard sentiment labels, assigned based on the results of manual annotations. When working with such annotations, it is common for dataset constructors to discard “noisy” or “controversial” data where there is significant disagreement on the proper label. In datasets constructed for the purpose of Twitter sentiment analysis (TSA), these controversial examples can compose over 30% of the originally annotated data. We argue that the removal of such data is a problematic trend because, when performing real-time sentiment classification of short-text, an automated system cannot know a priori which samples would fall into this category of disputed sentiment. We therefore propose the notion of a “complicated” class of sentiment to categorize such text, and argue that its inclusion in the short-text sentiment analysis framework will improve the quality of automated sentiment analysis systems as they are implemented in real-world settings. We motivate this argument by building and analyzing a new publicly available TSA dataset of over 7,000 tweets annotated with 5x coverage, named MTSA. Our analysis of classifier performance over our dataset offers insights into sentiment analysis dataset and model design, how current techniques would perform in the real world, and how researchers should handle difficult data.