Papers with unsupervised models
Parallel sentences mining with transfer learning in an unsupervised setting (2021.naacl-srw)
Copied to clipboard
| Challenge: | Existing methods to mine parallel sentences in low-resource environments are not suitable for many low-level language pairs. |
| Approach: | They propose an approach based on transfer learning to mine parallel sentences in an unsupervised setting using bilingual corpora of low-resource language pairs. |
| Outcome: | The proposed model improves the performance of mined parallel sentences at two real-world low-resource language pairs compared with previous methods. |
Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised? (2022.lrec-1)
Copied to clipboard
| Challenge: | Keyword extraction is the task of retrieving words that are essential to the content of a document. |
| Approach: | They propose to use pretrained multilingual language models for zero-shot cross-lingual keyword extraction on low-resource languages with limited or no available labeled training data. |
| Outcome: | The proposed models outperform state-of-the-art unsupervised methods on low-resource languages with limited or no training data. |
Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features (N18-1)
Copied to clipboard
| Challenge: | Currently, unsupervised word embeddings are routinely trained on large amounts of raw text data. |
| Approach: | They propose to use unsupervised word embeddings to train distributed representations of sentences. |
| Outcome: | The proposed method outperforms state-of-the-art models on most benchmark tasks and is robust to the produced general-purpose sentence embeddings. |
USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Standard language generation metrics have been shown to be ineffective for dialog evaluation. |
| Approach: | They propose an unsupervised evaluation metric for dialog that trains unsupervised models to measure several desirable qualities of dialog. |
| Outcome: | The proposed evaluation metric strongly correlates with human judgment on Topical-Chat and PersonaChat. |
Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages (2021.naacl-main)
Copied to clipboard
| Challenge: | Unsupervised translation systems have impressive performance on resource-rich language pairs . however, in more realistic settings, unsupervised systems perform poorly . |
| Approach: | They propose a model for 5 low-resource languages that leverages monolingual and auxiliary parallel data from other high-resourced languages. |
| Outcome: | The proposed model outperforms state-of-the-art models on low-resource languages . it also matches the current state- of-the art model for Nepali-English . |
Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Recent unsupervised sentence compression approaches use custom objectives to guide discrete search, but guided search is expensive at inference time. |
| Approach: | They propose to use reinforcement learning to train effective sentence compression models that are also fast when generating predictions. |
| Outcome: | The proposed model outperforms other unsupervised models while being faster at inference time. |
ArT: All-round Thinker for Unsupervised Commonsense Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work on commonsense QA requires labeled training data for its success . existing work relies on large-scale in-domain or out-of-domain labeles or fails to generate knowledge of high quality in a general way. |
| Approach: | They propose an approach to commonsense question-answering (QA) that takes association during knowledge generation. |
| Outcome: | The proposed model outperforms existing models on commonsense QA benchmarks. |
Unsupervised Question Answering via Answer Diversifying (2022.coling-1)
Copied to clipboard
| Challenge: | Existing extractive question answering methods use labeled data to train QA models. |
| Approach: | They propose an unsupervised method by diversifying answers by using data construction, data augmentation and denoising filter. |
| Outcome: | The proposed method outperforms previous models on five benchmark datasets . it shows strong performance in the few-shot learning setting . |
Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modeling (2023.eacl-main)
Copied to clipboard
| Challenge: | Dropout is a regularization trick used to resolve overfitting in large feedforward neural networks, but there is nil analysis of it for unsupervised models and in particular, VAE-based neural topic models. |
| Approach: | They propose to use dropout to solve overfitting problems in unsupervised neural topic models by stochastically dropping out the activation of neurons to prevent complex co-adaptations of feature vectors. |
| Outcome: | The proposed class of neural topic models can be used to improve the quality and predictive performance of the generated topics. |
(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas (D19-1)
Copied to clipboard
| Challenge: | Despite recent attempts on computational modeling of the variation, the lack of parallel corpora of style language makes it difficult to systematically control the stylistic change and evaluate such models. |
| Approach: | They propose to use a parallel and annotated stylistic language dataset to test the effectiveness of style transfer models. |
| Outcome: | The proposed model outperforms the unsupervised models using nonparallel corpus. |
Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models to summarize texts without ground-truth summaries are extractive, which remove words from texts and thus are less flexible than abstractive models. |
| Approach: | They propose an unsupervised model that extracts words from texts and makes them mutually enhance each other. |
| Outcome: | The proposed model outperforms both abstractive and extractive models, while generating new words not contained in input texts. |
GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation (2020.coling-main)
Copied to clipboard
| Challenge: | a large-scale, general-domain dataset is needed for knowledge graph-to-text generation . data collection is expensive and data-intensive, making it difficult to get good annotation . |
| Approach: | They propose to use a large-scale, general-domain dataset to generate unsupervised text from knowledge graphs. |
| Outcome: | The proposed dataset has 1.3M text and graph examples, and is a benchmark for future research . good annotation is expensive and difficult to get, and it's difficult to check quality . |
Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments (2021.acl-long)
Copied to clipboard
| Challenge: | Current algorithms for AMR parsing suffer from limited coverage and less-than-ideal accuracy . a new algorithm for AML uses unsupervised learning and heuristics to align components of AMR graphs to spans in English sentences . |
| Approach: | They propose algorithms for aligning components of Abstract Meaning Representation graphs to spans in English sentences. |
| Outcome: | The proposed approach covers a wider variety of AMR substructures than previously considered . it achieves higher coverage of nodes and edges, and does so with higher accuracy. |
Reinforcement Learning for Topic Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Topic modeling is a method to extract information from documents by grouping topics into topics and linking them with words describing them. |
| Approach: | They propose to replace the variational autoencoder with a continuous action space reinforcement learning policy and modify the neural network architecture to weight the ELBO loss. |
| Outcome: | The proposed model outperforms all other unsupervised models and performs on par with or better than most models using supervised labeling and contrastive learning. |
A Multilingual View of Unsupervised Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Empirically, we show that our approach results in higher BLEU scores over state-of-the-art unsupervised models on the WMT’14 English-French, WMT'16 English-German, and WMT‘16 English–Romanian datasets in most directions. |
| Approach: | They propose a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. |
| Outcome: | The proposed framework achieves higher BLEU scores than state-of-the-art unsupervised models on the WMT’14 English-French, WMT'16 English-German, and WMT‘16 English–Romanian datasets in most directions. |
EASE: Entity-Aware Contrastive Learning of Sentence Embedding (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for learning sentence embeddings are fine-tuning general-purpose pretrained models with a particular training supervision. |
| Approach: | They propose a method for learning sentence embeddings via contrastive learning between sentences and related entities. |
| Outcome: | The proposed method outperforms baseline methods in multilingual settings on a variety of tasks. |
NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints (2021.naacl-main)
Copied to clipboard
| Challenge: | Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. |
| Approach: | They propose an algorithm that enables neural language models to generate fluent text while satisfying complex lexical constraints. |
| Outcome: | The proposed algorithm outperforms existing methods on four benchmarks and shows that it handles any set of lexical constraints expressible under predicate logic while its asymptotic runtime is equivalent to conventional beam search. |
Improving Unsupervised Question Answering via Summarization-Informed Question Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Question Generation (QG) is the production of meaningful questions given a set of input passages and corresponding answers. |
| Approach: | They propose a method which uses questions generated heuristically from news summaries as a source of training data for a QG system. |
| Outcome: | The proposed method outperforms previous unsupervised models on three in-domain datasets and three out-of-domain ones. |
BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to extractive and abstractive summarization rely on large-scale parallel corpora of input text and output summaries for direct supervision. |
| Approach: | They propose an unsupervised approach to sentence summarization using the Information Bottleneck principle. |
| Outcome: | The proposed method outperforms unsupervised models on automatic metrics and human evaluation along multiple attributes. |
ParaDetox: Detoxification with Parallel Data (2022.acl-long)
Copied to clipboard
Varvara Logacheva, Daryna Dementieva, Sergey Ustyantsev, Daniil Moskovskiy, David Dale, Irina Krotova, Nikita Semenov, Alexander Panchenko
| Challenge: | a pipeline for the collection of parallel data for the detoxification task is available. |
| Approach: | They propose a pipeline for the collection of parallel data for the detoxification task . they collect non-toxic paraphrases for over 10,000 English toxic sentences . |
| Outcome: | The proposed pipeline outperforms state-of-the-art models on both automatic and manual evaluations. |
Attention Is (not) All You Need for Commonsense Reasoning (P19-1)
Copied to clipboard
| Challenge: | Recent language models such as word2vec have produced impressive results on various tasks such as question-answering and natural language inference. |
| Approach: | They propose a simple re-implementation of BERT for commonsense reasoning . they propose to use attention-guided reasoning to solve the Pronoun Disambiguation Problem . |
| Outcome: | The proposed model outperforms the state-of-the-art on several language understanding benchmarks while outperforming the existing models by a margin. |
Unsupervised Summarization Re-ranking (2023.findings-acl)
Copied to clipboard
| Challenge: | Abstractive summarization models have been gaining popularity, but performance of unsupervised models still lags behind supervised models. |
| Approach: | They propose to re-rank summary candidates in an unsupervised manner to close the performance gap between unsupervised and supervised models. |
| Outcome: | The proposed model improves unsupervised models by up to 7.27% and ChatGPT by up 6.86% relative mean ROUGE across four widely-adopted summarization benchmarks. |
Using Human Attention to Extract Keyphrase from Microblog Post (P19-1)
Copied to clipboard
| Challenge: | Existing studies on keyphrase extraction neglect human reading behavior during keyphrase annotating. |
| Approach: | They propose to integrate human attention into keyphrase extraction models by an attention mechanism and combine it with neural network models. |
| Outcome: | The proposed models improve on two Twitter datasets. |
Unsupervised Open-domain Keyphrase Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing models that generate keyphrases without human-labeled data are lacking in this area. |
| Approach: | They propose a model that consists of two modules that can be built in an unsupervised fashion and can perform consistently across domains. |
| Outcome: | The proposed model performs consistently across domains and narrows the gap between supervised and unsupervised models down to about 16%. |
Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining (2022.acl-long)
Copied to clipboard
| Challenge: | a model trained to align only two languages can encode multilingually more aligned representations . a dual-pivot transfer theory is proposed for bilingual training . |
| Approach: | They propose methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. |
| Outcome: | The proposed models reach the state of the art in unsupervised bitext mining and perform better than multilingually supervised models. |