This paper explores an empirical approach to learn more discriminantive sentence representations in an unsupervised fashion. Leveraging semantic graph smoothing, we enhance sentence embeddings obtained from pretrained models to improve results for the text clustering and classification tasks. Our method, validated on eight benchmarks, demonstrates consistent improvements, showcasing the potential of semantic graph smoothing in improving sentence embeddings for the supervised and unsupervised document categorization tasks.
Text document clustering can play a vital role in organizing and handling the everincreasing number of text documents. Uninformative and redundant features included in large text documents reduce the effectiveness of the clustering algorithm. Feature selection (FS) is a well-known technique for removing these features. Since FS can be formulated as an optimization problem, various meta-heuristic algorithms have been employed to solve it. Teaching-Learning-Based Optimization (TLBO) is a novel meta-heuristic algorithm that benefits from the low number of parameters and fast convergence. A hybrid method can simultaneously benefit from the advantages of TLBO and tackle the possible entrapment in the local optimum. By proposing a hybrid of TLBO, Grey Wolf Optimizer (GWO), and Genetic Algorithm (GA) operators, this paper suggests a filter-based FS algorithm (TLBO-GWO). Six benchmark datasets are selected, and TLBO-GWO is compared with three recently proposed FS algorithms with similar approaches, the main TLBO and GWO. The comparison is conducted based on clustering evaluation measures, convergence behavior, and dimension reduction, and is validated using statistical tests. The results reveal that TLBO-GWO can significantly enhance the effectiveness of the text clustering technique (K-means).
In the information age we are living in today, not only are we interested in accessing multimedia objects such as documents, videos, etc. but also in searching for professional experts, people or celebrities, possibly for professional needs or just for fun. Information access systems need to be able to extract and exploit various sources of information (usually in text format) about such individuals, and to represent them in a suitable way usually in the form of a profile. In this article, we tackle the problems of profile-based expert recommendation and document filtering from a machine learning perspective by clustering expert textual sources to build profiles and capture the different hidden topics in which the experts are interested. The experts will then be represented by means of multi-faceted profiles. Our experiments show that this is a valid technique to improve the performance of expert finding and document filtering.
The growth in Internet usage has contributed to a large volume of continuously available data, and has created the need for automatic and efficient organization of the data. In this context, text clustering techniques are significant because they aim to organize documents according to their characteristics. More specifically, hierarchical and incremental clustering techniques can organize dynamic data in a hierarchical form, thus guaranteeing that this organization is updated and its exploration is facilitated. Based on the relevance and contemporary nature of the field, this study aims to analyze various hierarchical and incremental clustering techniques; the main contribution of this research is the organization and comparison of the techniques used by studies published between 2010 and 2018 that aimed to texts documents clustering. We describe the principal concepts related to the challenge and the different characteristics of these published works in order to provide a better understanding of the research in this field.
Short text clustering has been popularly studied for its significance in mining valuable insights from many short texts. In this paper, we focus on the federated short text clustering (FSTC) problem, i.e., clustering short texts that are distributed in different clients, which is a realistic problem under privacy requirements. Compared with the centralized short text clustering problem that short texts are stored on a central server, the FSTC problem has not been explored yet. To fill this gap, we propose a Federated Robust Short Text Clustering (FSTC) framework. FSTC includes two main modules, i.e., robust short text clustering module and federated cluster center aggregation module. The robust short text clustering module aims to train an effective short text clustering model with local data in each client. We innovatively combine optimal transport to generate pseudo-labels with Gaussian-uniform mixture model to ensure the reliability of the pseudo-supervised data. The federated cluster center aggregation module aims to exchange knowledge across clients without sharing local raw data in an efficient way. The server aggregates the local cluster centers from different clients and then sends the global centers back to all clients in each communication round. Our empirical studies on three short text clustering datasets demonstrate that FSTC significantly outperforms the federated short text clustering baselines.
Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user's intent. Existing approaches to semi-supervised clustering require a significant amount of feedback from an expert to improve the clusters. In this paper, we ask whether a large language model can amplify an expert's guidance to enable query-efficient, few-shot semi-supervised text clustering. We show that LLMs are surprisingly effective at improving clustering. We explore three stages where LLMs can be incorporated into clustering: before clustering (improving input features), during clustering (by providing constraints to the clusterer), and after clustering (using LLMs post-correction). We find incorporating LLMs in the first two stages can routinely provide significant improvements in cluster quality, and that LLMs enable a user to make trade-offs between cost and accuracy to produce desired clusters. We release our code and LLM prompts for the public to use.
Short text clustering is challenging since it takes imbalanced and noisy data as inputs. Existing approaches cannot solve this problem well, since (1) they are prone to obtain degenerate solutions especially on heavy imbalanced datasets, and (2) they are vulnerable to noises. To tackle the above issues, we propose a Robust Short Text Clustering (RSTC) model to improve robustness against imbalanced and noisy data. RSTC includes two modules, i.e., pseudo-label generation module and robust representation learning module. The former generates pseudo-labels to provide supervision for the later, which contributes to more robust representations and correctly separated clusters. To provide robustness against the imbalance in data, we propose self-adaptive optimal transport in the pseudo-label generation module. To improve robustness against the noise in data, we further introduce both class-wise and instance-wise contrastive learning in the robust representation learning module. Our empirical studies on eight short text clustering datasets demonstrate that RSTC significantly outperforms the state-of-the-art models. The code is available at: https://github.com/hmllmh/RSTC.
We introduce ClusterLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupervised methods that builds upon "small" embedders, ClusterLLM exhibits two intriguing advantages: (1) it enjoys the emergent capability of LLM even if its embeddings are inaccessible; and (2) it understands the user's preference on clustering through textual instruction and/or a few annotated data. First, we prompt ChatGPT for insights on clustering perspective by constructing hard triplet questions <does A better correspond to B than C>, where A, B and C are similar data points that belong to different clusters according to small embedder. We empirically show that this strategy is both effective for fine-tuning small embedder and cost-efficient to query ChatGPT. Second, we prompt ChatGPT for helps on clustering granularity by carefully designed pairwise questions <do A and B belong to the same category>, and tune the granularity from cluster hierarchies that is the most consistent with the ChatGPT answers. Extensive experiments on 14 datasets show that ClusterLLM consistently improves clustering quality, at an average cost of ~$0.6 per dataset. The code will be available at https://github.com/zhang-yu-wei/ClusterLLM.
Text embeddings are useful features for several NLP applications, such as sentence similarity, text clustering, and semantic search. In this paper, we present a Low-rank Adaptation with a Contrastive objective on top of 8-bit Siamese-BLOOM, a multilingual large language model optimized to produce semantically meaningful word embeddings. The innovation is threefold. First, we cast BLOOM weights to 8-bit values. Second, we fine-tune BLOOM with a scalable adapter (LoRA) and 8-bit Adam optimizer for sentence similarity classification. Third, we apply a Siamese architecture on BLOOM model with a contrastive objective to ease the multi-lingual labeled data scarcity. The experiment results show the quality of learned embeddings from LACoS-BLOOM is proportional to the number of model parameters and the amount of unlabeled training data. With the parameter efficient fine-tuning design, we are able to run BLOOM 7.1 billion parameters end-to-end on a single GPU machine with 32GB memory. Compared to previous solution Sentence-BERT, we achieve significant improvement on both English and multi-lingual STS tasks.
With the advent of e-commerce platforms, reviews are crucial for customers to assess the credibility of a product. The star ratings do not always match the review text written by the customer. For example, a three star rating (out of five) may be incongruous with the review text, which may be more suitable for a five star review. A clustering approach can be used to relabel the correct star ratings by grouping the text reviews into individual groups. In this work, we explore the task of choosing different text embeddings to represent these reviews and also explore the impact the embedding choice has on the performance of various classes of clustering algorithms. We use contextual (BERT) and non-contextual (Word2Vec) text embeddings to represent the text and measure their impact of three classes on clustering algorithms - partitioning based (KMeans), single linkage agglomerative hierarchical, and density based (DBSCAN and HDBSCAN), each with various experimental settings. We use the silhouette score, adjusted rand index score, and cluster purity score metrics to evaluate the performance of the algorithms and discuss the impact of different embeddings on the clustering performance. Our results indicate that the type of embedding chosen drastically affects the performance of the algorithm, the performance varies greatly across different types of clustering algorithms, no embedding type is better than the other, and DBSCAN outperforms KMeans and single linkage agglomerative clustering but also labels more data points as outliers. We provide a thorough comparison of the performances of different algorithms and provide numerous ideas to foster further research in the domain of text clustering.
Text clustering, as one of the most fundamental challenges in unsupervised learning, aims at grouping semantically similar text segments without relying on human annotations. With the rapid development of deep learning, deep clustering has achieved significant advantages over traditional clustering methods. Despite the effectiveness, most existing deep text clustering methods rely heavily on representations pre-trained in general domains, which may not be the most suitable solution for clustering in specific target domains. To address this issue, we propose CEIL, a novel Classification-Enhanced Iterative Learning framework for short text clustering, which aims at generally promoting the clustering performance by introducing a classification objective to iteratively improve feature representations. In each iteration, we first adopt a language model to retrieve the initial text representations, from which the clustering results are collected using our proposed Category Disentangled Contrastive Clustering (CDCC) algorithm. After strict data filtering and aggregation processes, samples with clean category labels are retrieved, which serve as supervision information to update the language model with the classification objective via a prompt learning approach. Finally, the updated language model with improved representation ability is used to enhance clustering in the next iteration. Extensive experiments demonstrate that the CEIL framework significantly improves the clustering performance over iterations, and is generally effective on various clustering algorithms. Moreover, by incorporating CEIL on CDCC, we achieve the state-of-the-art clustering performance on a wide range of short text clustering benchmarks outperforming other strong baseline methods.
Machine Learning (ML) has been widely used in Natural Language Processing (NLP) applications. A fundamental assumption in ML is that training data and real-world data should follow a similar distribution. However, a deployed ML model may suffer from out-of-distribution (OOD) issues due to distribution shifts in the real-world data. Though many algorithms have been proposed to detect OOD data from text corpora, there is still a lack of interactive tool support for ML developers. In this work, we propose DeepLens, an interactive system that helps users detect and explore OOD issues in massive text corpora. Users can efficiently explore different OOD types in DeepLens with the help of a text clustering method. Users can also dig into a specific text by inspecting salient words highlighted through neuron activation analysis. In a within-subjects user study with 24 participants, participants using DeepLens were able to find nearly twice more types of OOD issues accurately with 22% more confidence compared with a variant of DeepLens that has no interaction or visualization support.
Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A parameter-efficient adaptation method suggests training an adapter for each domain on the task of language modeling. This leads to good in-domain scores but can be impractical for domain- or resource-restricted settings. A solution is to use a related-domain adapter for the novel domain at test time. In this paper, we introduce AdapterSoup, an approach that performs weight-space averaging of adapters trained on different domains. Our approach is embarrassingly parallel: first, we train a set of domain-specific adapters; then, for each novel domain, we determine which adapters should be averaged at test time. We present extensive experiments showing that AdapterSoup consistently improves performance to new domains without extra training. We also explore weight averaging of adapters trained on the same domain with different hyper-parameters, and show that it preserves the performance of a PLM on new domains while obtaining strong in-domain results. We explore various approaches for choosing which adapters to combine, such as text clustering and semantic similarity. We find that using clustering leads to the most competitive results on novel domains.
Text clustering and topic extraction are two important tasks in text mining. Usually, these two tasks are performed separately. For topic extraction to facilitate clustering, we can first project texts into a topic space and then perform a clustering algorithm to obtain clusters. To promote topic extraction by clustering, we can first obtain clusters with a clustering algorithm and then extract cluster-specific topics. However, this naive strategy ignores the fact that text clustering and topic extraction are strongly correlated and follow a chicken-and-egg relationship. Performing them separately fails to make them mutually benefit each other to achieve the best overall performance. In this paper, we propose an unsupervised text clustering and topic extraction framework (ClusTop) which integrates text clustering and topic extraction into a unified framework and can achieve high-quality clustering result and extract topics from each cluster simultaneously. Our framework includes four components: enhanced language model training, dimensionality reduction, clustering and topic extraction, where the enhanced language model can be viewed as a bridge between clustering and topic extraction. On one hand, it provides text embeddings with a strong cluster structure which facilitates effective text clustering; on the other hand, it pays high attention on the topic related words for topic extraction because of its self-attention architecture. Moreover, the training of enhanced language model is unsupervised. Experiments on two datasets demonstrate the effectiveness of our framework and provide benchmarks for different model combinations in this framework.
Text data mining is the process of deriving essential information from language text. Typical text mining tasks include text categorization, text clustering, topic modeling, information extraction, and text summarization. Various data sets are collected and various algorithms are designed for the different types of tasks. In this paper, I present a blue sky idea that very large language model (VLLM) will become an effective unified methodology of text mining. I discuss at least three advantages of this new methodology against conventional methods. Finally I discuss the challenges in the design and development of VLLM techniques for text mining.
Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be equally well applied to other tasks like clustering or reranking. This makes progress in the field difficult to track, as various models are constantly being proposed without proper evaluation. To solve this problem, we introduce the Massive Text Embedding Benchmark (MTEB). MTEB spans 8 embedding tasks covering a total of 58 datasets and 112 languages. Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks. This suggests that the field has yet to converge on a universal text embedding method and scale it up sufficiently to provide state-of-the-art results on all embedding tasks. MTEB comes with open-source code and a public leaderboard at https://github.com/embeddings-benchmark/mteb.
The target of image-text clustering (ITC) is to find correct clusters by integrating complementary and consistent information of multi-modalities for these heterogeneous samples. However, the majority of current studies analyse ITC on the ideal premise that the samples in every modality are complete. This presumption, however, is not always valid in real-world situations. The missing data issue degenerates the image-text feature learning performance and will finally affect the generalization abilities in ITC tasks. Although a series of methods have been proposed to address this incomplete image text clustering issue (IITC), the following problems still exist: 1) most existing methods hardly consider the distinct gap between heterogeneous feature domains. 2) For missing data, the representations generated by existing methods are rarely guaranteed to suit clustering tasks. 3) Existing methods do not tap into the latent connections both inter and intra modalities. In this paper, we propose a Clustering-Induced Generative Incomplete Image-Text Clustering(CIGIT-C) network to address the challenges above. More specifically, we first use modality-specific encoders to map original features to more distinctive subspaces. The latent connections between intra and inter-modalities are thoroughly explored by using the adversarial generating network to produce one modality conditional on the other modality. Finally, we update the corresponding modalityspecific encoders using two KL divergence losses. Experiment results on public image-text datasets demonstrated that the suggested method outperforms and is more effective in the IITC job.
Extracting knowledge from unlabeled texts using machine learning algorithms can be complex. Document categorization and information retrieval are two applications that may benefit from unsupervised learning (e.g., text clustering and topic modeling), including exploratory data analysis. However, the unsupervised learning paradigm poses reproducibility issues. The initialization can lead to variability depending on the machine learning algorithm. Furthermore, the distortions can be misleading when regarding cluster geometry. Amongst the causes, the presence of outliers and anomalies can be a determining factor. Despite the relevance of initialization and outlier issues for text clustering and topic modeling, the authors did not find an in-depth analysis of them. This survey provides a systematic literature review (2011-2022) of these subareas and proposes a common terminology since similar procedures have different terms. The authors describe research opportunities, trends, and open issues. The appendices summarize the theoretical background of the text vectorization, the factorization, and the clustering algorithms that are directly or indirectly related to the reviewed works.
Sentence embeddings are commonly used in text clustering and semantic retrieval tasks. State-of-the-art sentence representation methods are based on artificial neural networks fine-tuned on large collections of manually labeled sentence pairs. Sufficient amount of annotated data is available for high-resource languages such as English or Chinese. In less popular languages, multilingual models have to be used, which offer lower performance. In this publication, we address this problem by proposing a method for training effective language-specific sentence encoders without manually labeled data. Our approach is to automatically construct a dataset of paraphrase pairs from sentence-aligned bilingual text corpora. We then use the collected data to fine-tune a Transformer language model with an additional recurrent pooling layer. Our sentence encoder can be trained in less than a day on a single graphics card, achieving high performance on a diverse set of sentence-level tasks. We evaluate our method on eight linguistic tasks in Polish, comparing it with the best available multilingual sentence encoders.
Most existing scene text detectors focus on detecting characters or words that only capture partial text messages due to missing contextual information. For a better understanding of text in scenes, it is more desired to detect contextual text blocks (CTBs) which consist of one or multiple integral text units (e.g., characters, words, or phrases) in natural reading order and transmit certain complete text messages. This paper presents contextual text detection, a new setup that detects CTBs for better understanding of texts in scenes. We formulate the new setup by a dual detection task which first detects integral text units and then groups them into a CTB. To this end, we design a novel scene text clustering technique that treats integral text units as tokens and groups them (belonging to the same CTB) into an ordered token sequence. In addition, we create two datasets SCUT-CTW-Context and ReCTS-Context to facilitate future research, where each CTB is well annotated by an ordered sequence of integral text units. Further, we introduce three metrics that measure contextual text detection in local accuracy, continuity, and global accuracy. Extensive experiments show that our method accurately detects CTBs which effectively facilitates downstream tasks such as text classification and translation. The project is available at https://sg-vilab.github.io/publication/xue2022contextual/.