The state-of-the-art pre-trained language representation models, such as Bidirectional Encoder Representations from Transformers (BERT), rarely incorporate commonsense knowledge or other knowledge explicitly. We propose a pre-training approach for incorporating commonsense knowledge into language representation models. We construct a commonsense-related multi-choice question answering dataset for pre-training a neural language representation model. The dataset is created automatically by our proposed "align, mask, and select" (AMS) method. We also investigate different pre-training tasks. Experimental results demonstrate that pre-training models using the proposed approach followed by fine-tuning achieve significant improvements over previous state-of-the-art models on two commonsense-related benchmarks, including CommonsenseQA and Winograd Schema Challenge. We also observe that fine-tuned models after the proposed pre-training approach maintain comparable performance on other NLP tasks, such as sentence classification and natural language inference tasks, compared to the original BERT models. These results verify that the proposed approach, while significantly improving commonsense-related NLP tasks, does not degrade the general language representation capabilities.
Most existing approaches to disfluency detection heavily rely on human-annotated data, which is expensive to obtain in practice. To tackle the training data bottleneck, we investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled news data, and propose two self-supervised pre-training tasks: (i) tagging task to detect the added noisy words. (ii) sentence classification to distinguish original sentences from grammatically-incorrect sentences. We then combine these two tasks to jointly train a network. The pre-trained network is then fine-tuned using human-annotated disfluency detection training data. Experimental results on the commonly used English Switchboard test set show that our approach can achieve competitive performance compared to the previous systems (trained using the full dataset) by using less than 1% (1000 sentences) of the training data. Our method trained on the full dataset significantly outperforms previous methods, reducing the error by 21% on English Switchboard.
In this work\footnote {This work was supported in part by the National Science Foundation under grant IIS-1212948.}, we present a method to represent a video with a sequence of words, and learn the temporal sequencing of such words as the key information for predicting and recognizing human actions. We leverage core concepts from the Natural Language Processing (NLP) literature used in sentence classification to solve the problems of action prediction and action recognition. Each frame is converted into a word that is represented as a vector using the Bag of Visual Words (BoW) encoding method. The words are then combined into a sentence to represent the video, as a sentence. The sequence of words in different actions are learned with a simple but effective Temporal Convolutional Neural Network (T-CNN) that captures the temporal sequencing of information in a video sentence. We demonstrate that a key characteristic of the proposed method is its low-latency, i.e. its ability to predict an action accurately with a partial sequence (sentence). Experiments on two datasets, \textit{UCF101} and \textit{HMDB51} show that the method on average reaches 95\% of its accuracy within half the video frames. Results, also demonstrate that our method achieves compatible state-of-the-art performance in action recognition (i.e. at the completion of the sentence) in addition to action prediction.
Process model extraction (PME) is a recently emerged interdiscipline between natural language processing (NLP) and business process management (BPM), which aims to extract process models from textual descriptions. Previous process extractors heavily depend on manual features and ignore the potential relations between clues of different text granularities. In this paper, we formalize the PME task into the multi-grained text classification problem, and propose a hierarchical neural network to effectively model and extract multi-grained information without manually-defined procedural features. Under this structure, we accordingly propose the coarse-to-fine (grained) learning mechanism, training multi-grained tasks in coarse-to-fine grained order to share the high-level knowledge for the low-level tasks. To evaluate our approach, we construct two multi-grained datasets from two different domains and conduct extensive experiments from different dimensions. The experimental results demonstrate that our approach outperforms the state-of-the-art methods with statistical significance and further investigations demonstrate its effectiveness.
Different from the writing systems of many Romance and Germanic languages, some languages or language families show complex conjunct forms in character composition. For such cases where the conjuncts consist of the components representing consonant(s) and vowel, various character encoding schemes can be adopted beyond merely making up a one-hot vector. However, there has been little work done on intra-language comparison regarding performances using each representation. In this study, utilizing the Korean language which is character-rich and agglutinative, we investigate an encoding scheme that is the most effective among Jamo-level one-hot, character-level one-hot, character-level dense, and character-level multi-hot. Classification performance with each scheme is evaluated on two corpora: one on binary sentiment analysis of movie reviews, and the other on multi-class identification of intention types. The result displays that the character-level features show higher performance in general, although the Jamo-level features may show compatibility with the attention-based models if guaranteed adequate parameter set size.
Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in [0,1] through a sigmoid function. However, due to the graduality of the sigmoid function, the sigmoid gate is not flexible in representing multi-modality or skewness. Besides, the previous models lack modeling on the correlation between the gates, which would be a new method to adopt inductive bias for a relationship between previous and current input. This paper proposes a new gate structure with the bivariate Beta distribution. The proposed gate structure enables probabilistic modeling on the gates within the LSTM cell so that the modelers can customize the cell state flow with priors and distributions. Moreover, we theoretically show the higher upper bound of the gradient compared to the sigmoid function, and we empirically observed that the bivariate Beta distribution gate structure provides higher gradient values in training. We demonstrate the effectiveness of bivariate Beta gate structure on the sentence classification, image classification, polyphonic music modeling, and image caption generation.
The GLUE benchmark (Wang et al., 2019b) is a suite of language understanding tasks which has seen dramatic progress in the past year, with average performance moving from 70.0 at launch to 83.9, state of the art at the time of writing (May 24, 2019). Here, we measure human performance on the benchmark, in order to learn whether significant headroom remains for further progress. We provide a conservative estimate of human performance on the benchmark through crowdsourcing: Our annotators are non-experts who must learn each task from a brief set of instructions and 20 examples. In spite of limited training, these annotators robustly outperform the state of the art on six of the nine GLUE tasks and achieve an average score of 87.1. Given the fast pace of progress however, the headroom we observe is quite limited. To reproduce the data-poor setting that our annotators must learn in, we also train the BERT model (Devlin et al., 2019) in limited-data regimes, and conclude that low-resource sentence classification remains a challenge for modern neural network approaches to text understanding.
Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the state-of-the-art networks for image classification. However, how this technique can be applied to and what is its effectiveness on natural language processing (NLP) tasks have not been investigated. In this paper, we propose two strategies for the adaption of Mixup on sentence classification: one performs interpolation on word embeddings and another on sentence embeddings. We conduct experiments to evaluate our methods using several benchmark datasets. Our studies show that such interpolation strategies serve as an effective, domain independent data augmentation approach for sentence classification, and can result in significant accuracy improvement for both CNN and LSTM models.
We consider the extreme multi-label text classification (XMC) problem: given an input text, return the most relevant labels from a large label collection. For example, the input text could be a product description on Amazon.com and the labels could be product categories. XMC is an important yet challenging problem in the NLP community. Recently, deep pretrained transformer models have achieved state-of-the-art performance on many NLP tasks including sentence classification, albeit with small label sets. However, naively applying deep transformer models to the XMC problem leads to sub-optimal performance due to the large output space and the label sparsity issue. In this paper, we propose X-Transformer, the first scalable approach to fine-tuning deep transformer models for the XMC problem. The proposed method achieves new state-of-the-art results on four XMC benchmark datasets. In particular, on a Wiki dataset with around 0.5 million labels, the prec@1 of X-Transformer is 77.28%, a substantial improvement over state-of-the-art XMC approaches Parabel (linear) and AttentionXML (neural), which achieve 68.70% and 76.95% precision@1, respectively. We further apply X-Transformer to a product2query dataset from Amazon and gained 10.7% relative improvement on prec@1 over Parabel.
Identifying the intent of a citation in scientific papers (e.g., background information, use of methods, comparing results) is critical for machine reading of individual publications and automated analysis of the scientific literature. We propose structural scaffolds, a multitask model to incorporate structural information of scientific papers into citations for effective classification of citation intents. Our model achieves a new state-of-the-art on an existing ACL anthology dataset (ACL-ARC) with a 13.3% absolute increase in F1 score, without relying on external linguistic resources or hand-engineered features as done in existing methods. In addition, we introduce a new dataset of citation intents (SciCite) which is more than five times larger and covers multiple scientific domains compared with existing datasets. Our code and data are available at: https://github.com/allenai/scicite.
Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et al., 2018) to address the lack of high-quality, large-scale labeled scientific data. SciBERT leverages unsupervised pretraining on a large multi-domain corpus of scientific publications to improve performance on downstream scientific NLP tasks. We evaluate on a suite of tasks including sequence tagging, sentence classification and dependency parsing, with datasets from a variety of scientific domains. We demonstrate statistically significant improvements over BERT and achieve new state-of-the-art results on several of these tasks. The code and pretrained models are available at https://github.com/allenai/scibert/.
Tracking developments in the highly dynamic data-technology landscape are vital to keeping up with novel technologies and tools, in the various areas of Artificial Intelligence (AI). However, It is difficult to keep track of all the relevant technology keywords. In this paper, we propose a novel system that addresses this problem. This tool is used to automatically detect the existence of new technologies and tools in text, and extract terms used to describe these new technologies. The extracted new terms can be logged as new AI technologies as they are found on-the-fly in the web. It can be subsequently classified into the relevant semantic labels and AI domains. Our proposed tool is based on a two-stage cascading model -- the first stage classifies if the sentence contains a technology term or not; and the second stage identifies the technology keyword in the sentence. We obtain a competitive accuracy for both tasks of sentence classification and text identification.
This paper describes our submission for the SemEval-2019 Suggestion Mining task. A simple Convolutional Neural Network (CNN) classifier with contextual word representations from a pre-trained language model was used for sentence classification. The model is trained using tri-training, a semi-supervised bootstrapping mechanism for labelling unseen data. Tri-training proved to be an effective technique to accommodate domain shift for cross-domain suggestion mining (Subtask B) where there is no hand labelled training data. For in-domain evaluation (Subtask A), we use the same technique to augment the training set. Our system ranks thirteenth in Subtask A with an $F_1$-score of 68.07 and third in Subtask B with an $F_1$-score of 81.94.
Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network (RNN), represents the sequential information transfer. RNN uses a chain of repeating cells to model the sequence data. However, previous studies of neural network based transfer learning simply represents the whole sentence by a single vector, which is unfeasible for seq2seq and sequence labeling. Meanwhile, such layer-wise transfer learning mechanisms lose the fine-grained cell-level information from the source domain. In this paper, we proposed the aligned recurrent transfer, ART, to achieve cell-level information transfer. ART is under the pre-training framework. Each cell attentively accepts transferred information from a set of positions in the source domain. Therefore, ART learns the cross-domain word collocations in a more flexible way. We conducted extensive experiments on both sequence labeling tasks (POS tagging, NER) and sentence classification (sentiment analysis). ART outperforms the state-of-the-arts over all experiments.
We explore various methods for computing sentence representations from pre-trained word embeddings without any training, i.e., using nothing but random parameterizations. Our aim is to put sentence embeddings on more solid footing by 1) looking at how much modern sentence embeddings gain over random methods---as it turns out, surprisingly little; and by 2) providing the field with more appropriate baselines going forward---which are, as it turns out, quite strong. We also make important observations about proper experimental protocol for sentence classification evaluation, together with recommendations for future research.
It is intuitive that NLP tasks for logographic languages like Chinese should benefit from the use of the glyph information in those languages. However, due to the lack of rich pictographic evidence in glyphs and the weak generalization ability of standard computer vision models on character data, an effective way to utilize the glyph information remains to be found. In this paper, we address this gap by presenting Glyce, the glyph-vectors for Chinese character representations. We make three major innovations: (1) We use historical Chinese scripts (e.g., bronzeware script, seal script, traditional Chinese, etc) to enrich the pictographic evidence in characters; (2) We design CNN structures (called tianzege-CNN) tailored to Chinese character image processing; and (3) We use image-classification as an auxiliary task in a multi-task learning setup to increase the model's ability to generalize. We show that glyph-based models are able to consistently outperform word/char ID-based models in a wide range of Chinese NLP tasks. We are able to set new state-of-the-art results for a variety of Chinese NLP tasks, including tagging (NER, CWS, POS), sentence pair classification, single sentence classification tasks, dependency parsing, and semantic role labeling. For example, the proposed model achieves an F1 score of 80.6 on the OntoNotes dataset of NER, +1.5 over BERT; it achieves an almost perfect accuracy of 99.8\% on the Fudan corpus for text classification. Code found at https://github.com/ShannonAI/glyce.
Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows. With the progress in natural language processing (NLP), extracting valuable information from biomedical literature has gained popularity among researchers, and deep learning has boosted the development of effective biomedical text mining models. However, directly applying the advancements in NLP to biomedical text mining often yields unsatisfactory results due to a word distribution shift from general domain corpora to biomedical corpora. In this article, we investigate how the recently introduced pre-trained language model BERT can be adapted for biomedical corpora. We introduce BioBERT (Bidirectional Encoder Representations from Transformers for Biomedical Text Mining), which is a domain-specific language representation model pre-trained on large-scale biomedical corpora. With almost the same architecture across tasks, BioBERT largely outperforms BERT and previous state-of-the-art models in a variety of biomedical text mining tasks when pre-trained on biomedical corpora. While BERT obtains performance comparable to that of previous state-of-the-art models, BioBERT significantly outperforms them on the following three representative biomedical text mining tasks: biomedical named entity recognition (0.62% F1 score improvement), biomedical relation extraction (2.80% F1 score improvement) and biomedical question answering (12.24% MRR improvement). Our analysis results show that pre-training BERT on biomedical corpora helps it to understand complex biomedical texts. We make the pre-trained weights of BioBERT freely available at https://github.com/naver/biobert-pretrained, and the source code for fine-tuning BioBERT available at https://github.com/dmis-lab/biobert.
Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in various NLP tasks such as sentence classification and document summarization. Therefore, various sentence embedding models based on supervised and unsupervised learning have been proposed after the advent of researches regarding the distributed representation of words. They were evaluated through semantic textual similarity (STS) tasks, which measure the degree of semantic preservation of a sentence and neural network-based supervised embedding models generally yielded state-of-the-art performance. However, these models have a limitation in that they have multiple parameters to update, thereby requiring a tremendous amount of labeled training data. In this study, we propose an efficient approach that learns a transition matrix that refines a sentence embedding vector to reflect the latent semantic meaning of a sentence. The proposed method has two practical advantages; (1) it can be applied to any sentence embedding method, and (2) it can achieve robust performance in STS tasks irrespective of the number of training examples.
Automatic text classification (TC) research can be used for real-world problems such as the classification of in-patient discharge summaries and medical text reports, which is beneficial to make medical documents more understandable to doctors. However, in electronic medical records (EMR), the texts containing sentences are shorter than that in general domain, which leads to the lack of semantic features and the ambiguity of semantic. To tackle this challenge, we propose to add word-cluster embedding to deep neural network for improving short text classification. Concretely, we first use hierarchical agglomerative clustering to cluster the word vectors in the semantic space. Then we calculate the cluster center vector which represents the implicit topic information of words in the cluster. Finally, we expand word vector with cluster center vector, and implement classifiers using CNN and LSTM respectively. To evaluate the performance of our proposed method, we conduct experiments on public data sets TREC and the medical short sentences data sets which is constructed and released by us. The experimental results demonstrate that our proposed method outperforms state-of-the-art baselines in short sentence classification on both medical domain and general domain.
The meaning of a sentence is a function of the relations that hold between its words. We instantiate this relational view of semantics in a series of neural models based on variants of relation networks (RNs) which represent a set of objects (for us, words forming a sentence) in terms of representations of pairs of objects. We propose two extensions to the basic RN model for natural language. First, building on the intuition that not all word pairs are equally informative about the meaning of a sentence, we use constraints based on both supervised and unsupervised dependency syntax to control which relations influence the representation. Second, since higher-order relations are poorly captured by a sum of pairwise relations, we use a recurrent extension of RNs to propagate information so as to form representations of higher order relations. Experiments on sentence classification, sentence pair classification, and machine translation reveal that, while basic RNs are only modestly effective for sentence representation, recurrent RNs with latent syntax are a reliably powerful representational device.