Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism. As most of the research focus on probing tasks or hidden states, previous works have found some primitive patterns of attention head behavior by heuristic analytical methods, but a more systematic analysis specific on the attention patterns still remains primitive. In this work, we clearly cluster the attention heatmaps into significantly different patterns through unsupervised clustering on top of a set of proposed features, which corroborates with previous observations. We further study their corresponding functions through analytical study. In addition, our proposed features can be used to explain and calibrate different attention heads in Transformer models.
Homonym identification is important for WSD that require coarse-grained partitions of senses. The goal of this project is to determine whether contextual information is sufficient for identifying a homonymous word. To capture the context, BERT embeddings are used as opposed to Word2Vec, which conflates senses into one vector. SemCor is leveraged to retrieve the embeddings. Various clustering algorithms are applied to the embeddings. Finally, the embeddings are visualized in a lower-dimensional space to understand the feasibility of the clustering process.
Lexical semantic change detection (also known as semantic shift tracing) is a task of identifying words that have changed their meaning over time. Unsupervised semantic shift tracing, focal point of SemEval2020, is particularly challenging. Given the unsupervised setup, in this work, we propose to identify clusters among different occurrences of each target word, considering these as representatives of different word meanings. As such, disagreements in obtained clusters naturally allow to quantify the level of semantic shift per each target word in four target languages. To leverage this idea,…
Contrastive learning is a promising approach to unsupervised learning, as it inherits the advantages of well-studied deep models without a dedicated and complex model design. In this paper, based on bidirectional encoder representations from transformers, we propose self-supervised contrastive learning (SCL) as well as few-shot contrastive learning (FCL) with unsupervised data augmentation (UDA) for text clustering. SCL outperforms state-of-the-art unsupervised clustering approaches for short texts and those for long texts in terms of several clustering evaluation measures. FCL achieves perfor…
In recent years, summarizers that incorporate domain knowledge into the process of text summarization have outperformed generic methods, especially for summarization of biomedical texts. However, construction and maintenance of domain knowledge bases are resource-intense tasks requiring significant manual annotation. In this paper, we demonstrate that contextualized representations extracted from the pre-trained deep language model BERT, can be effectively used to measure the similarity between sentences and to quantify the informative content. The results show that our BERT-based summarizer c…
Deakin University（迪肯大学）；University of Technology Sydney（悉尼科技大学）
Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the expressiveness for short text representations with more condensed, low-dimensional and continuous features compared to the traditional Bag-of-Words (BoW) model. However, these models are trained for general purposes and thus are suboptimal for the short text clustering task. In this paper, we propose two methods to exploit the unsupervised autoencoder (AE) framework …
We investigate how well BERT performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions. Although BERT obtains a strong performance on most datasets, it does so by exploiting common surface patterns that correlate with certain factuality labels, and it fails on instances where pragmatic reasoning is necessary. Contrary to what the high performance suggests, we are still far from having a robust system for factuality prediction.
While attention is all you need may be proving true, we do not know why: attention-based transformer models such as BERT are superior but how information flows from input tokens to output predictions are unclear. We introduce influence patterns, abstractions of sets of paths through a transformer model. Patterns quantify and localize the flow of information to paths passing through a sequence of model nodes. Experimentally, we find that significant portion of information flow in BERT goes through skip connections instead of attention heads. We further show that consistency of patterns across i…
ShareChat；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；ETH Zurich（苏黎世联邦理工学院）
We explore deep clustering of text representations for unsupervised model interpretation and induction of syntax. As these representations are high-dimensional, out-of-the-box methods like KMeans do not work well. Thus, our approach jointly transforms the representations into a lower-dimensional cluster-friendly space and clusters them. We consider two notions of syntax: Part of speech Induction (POSI) and constituency labelling (CoLab) in this work. Interestingly, we find that Multilingual BERT (mBERT) contains surprising amount of syntactic knowledge of English; possibly even as much as Engl…
Several pre-training objectives, such as masked language modeling (MLM), have been proposed to pre-train language models (e.g. BERT) with the aim of learning better language representations. However, to the best of our knowledge, no previous work so far has investigated how different pre-training objectives affect what BERT learns about linguistics properties. We hypothesize that linguistically motivated objectives such as MLM should help BERT to acquire better linguistic knowledge compared to other non-linguistically motivated objectives that are not intuitive or hard for humans to guess the …
In this work we provide new insights into the transformer architecture, and in particular, its best-known variant, BERT. First, we propose a method to measure the degree of non-linearity of different elements of transformers. Next, we focus our investigation on the feed-forward networks (FFN) inside transformers, which contain 2/3 of the model parameters and have so far not received much attention. We find that FFNs are an inefficient yet important architectural element and that they cannot simply be replaced by attention blocks without a degradation in performance. Moreover, we study the inte…
Islamic Azad University（伊斯兰阿扎德大学）；Iran University of Science and Technology（伊朗科技大学）
This paper is a comparison study in the context of Topic Detection on COVID-19 data. There are various approaches for Topic Detection, among which the Clustering approach is selected in this paper. Clustering requires distance and calculating distance needs embedding. The aim of this research is to simultaneously study the three factors of embedding methods, distance metrics and clustering methods and their interaction. A dataset including one-month tweets collected with COVID-19-related hashtags is used for this study. Five methods, from earlier to new methods, are selected among the embeddin…
East China Normal University（华东师范大学）；Shandong University（山东大学）；Tsinghua University（清华大学）；Jiangsu Normal University（江苏师范大学）
Short text clustering has far-reaching effects on semantic analysis, showing its importance for multiple applications such as corpus summarization and information retrieval. However, it inevitably encounters the severe sparsity of short text representations, making the previous clustering approaches still far from satisfactory. In this paper, we present a novel attentive representation learning model for shot text clustering, wherein cluster-level attention is proposed to capture the correlations between text representations and cluster representations. Relying on this, the representation lear…
Georgetown University（乔治城大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. In this work, we investigate how two pretrained contextualized language models (ELMo and BERT) can be utilized for ad-hoc document ranking. Through experiments on TREC benchmarks, we find that several existing neural ranking architectures can benefit from the additional context provided by contextualized language models. Furthermore, we propose a joint approach that incorporates BERT's classification vector…
Many natural language processing and information retrieval problems can be formalized as the task of semantic matching. Existing work in this area has been largely focused on matching between short texts (e.g., question answering), or between a short and a long text (e.g., ad-hoc retrieval). Semantic matching between long-form documents, which has many important applications like news recommendation, related article recommendation and document clustering, is relatively less explored and needs more research effort. In recent years, self-attention based models like Transformers and BERT have ach…
