Abstract:We introduce a novel benchmark for evaluating the role-playing capabilities of language models. Our approach leverages language models themselves to emulate users in dynamic, multi-turn conversations and to assess the resulting dialogues. The framework consists of three main components: a player model assuming a specific character role, an interrogator model simulating user behavior, and a judge model evaluating conversation quality. We conducted experiments comparing automated evaluations with human annotations to validate our approach, demonstrating strong correlations across multiple criteria. This work provides a foundation for a robust and dynamic evaluation of model capabilities in interactive scenarios.
Abstract:Text style transfer techniques are gaining popularity in natural language processing allowing paraphrasing text in the required form: from toxic to neural, from formal to informal, from old to the modern English language, etc. Solving the task is not sufficient to generate some neural/informal/modern text, but it is important to preserve the original content unchanged. This requirement becomes even more critical in some applications such as style transfer of goal-oriented dialogues where the factual information shall be kept to preserve the original message, e.g. ordering a certain type of pizza to a certain address at a certain time. The aspect of content preservation is critical for real-world applications of style transfer studies, but it has received little attention. To bridge this gap we perform a comparison of various style transfer models on the example of the formality transfer domain. To perform a study of the content preservation abilities of various style transfer methods we create a parallel dataset of formal vs. informal task-oriented dialogues. The key difference between our dataset and the existing ones like GYAFC [17] is the presence of goal-oriented dialogues with predefined semantic slots essential to be kept during paraphrasing, e.g. named entities. This additional annotation allowed us to conduct a precise comparative study of several state-of-the-art techniques for style transfer. Another result of our study is a modification of the unsupervised method LEWIS [19] which yields a substantial improvement over the original method and all evaluated baselines on the proposed task.
Abstract:Text detoxification is a style transfer task of creating neutral versions of toxic texts. In this paper, we use the concept of text editing to build a two-step tagging-based detoxification model using a parallel corpus of Russian texts. With this model, we achieved the best style transfer accuracy among all models in the RUSSE Detox shared task, surpassing larger sequence-to-sequence models.
Abstract:Detecting implicit causal relations in texts is a task that requires both common sense and world knowledge. Existing datasets are focused either on commonsense causal reasoning or explicit causal relations. In this work, we present HeadlineCause, a dataset for detecting implicit causal relations between pairs of news headlines. The dataset includes over 5000 headline pairs from English news and over 9000 headline pairs from Russian news labeled through crowdsourcing. The pairs vary from totally unrelated or belonging to the same general topic to the ones including causation and refutation relations. We also present a set of models and experiments that demonstrates the dataset validity, including a multilingual XLM-RoBERTa based model for causality detection and a GPT-2 based model for possible effects prediction.
Abstract:This paper presents the results of the Russian News Clustering and Headline Selection shared task. As a part of it, we propose the tasks of Russian news event detection, headline selection, and headline generation. These tasks are accompanied by datasets and baselines. The presented datasets for event detection and headline selection are the first public Russian datasets for their tasks. The headline generation dataset is based on clustering and provides multiple reference headlines for every cluster, unlike the previous datasets. Finally, the approaches proposed by the shared task participants are reported and analyzed.
Abstract:Automatic text summarization has been studied in a variety of domains and languages. However, this does not hold for the Russian language. To overcome this issue, we present Gazeta, the first dataset for summarization of Russian news. We describe the properties of this dataset and benchmark several extractive and abstractive models. We demonstrate that the dataset is a valid task for methods of text summarization for Russian. Additionally, we prove the pretrained mBART model to be useful for Russian text summarization.
Abstract:Pretrained language models based on Transformer architecture are the reason for recent breakthroughs in many areas of NLP, including sentiment analysis, question answering, named entity recognition. Headline generation is a special kind of text summarization task. Models need to have strong natural language understanding that goes beyond the meaning of individual words and sentences and an ability to distinguish essential information to succeed in it. In this paper, we fine-tune two pretrained Transformer-based models (mBART and BertSumAbs) for that task and achieve new state-of-the-art results on the RIA and Lenta datasets of Russian news. BertSumAbs increases ROUGE on average by 4.6 and 5.9 points respectively over previous best score achieved by Pointer-Generator network.
Abstract:News headline generation is an essential problem of text summarization because it is constrained, well-defined, and is still hard to solve. Models with a limited vocabulary can not solve it well, as new named entities can appear regularly in the news and these entities often should be in the headline. News articles in morphologically rich languages such as Russian require model modifications due to a large number of possible word forms. This study aims to validate that models with a possibility of copying words from the original article performs better than models without such an option. The proposed model achieves a mean ROUGE score of 23 on the provided test dataset, which is 8 points greater than the result of a similar model without a copying mechanism. Moreover, the resulting model performs better than any known model on the new dataset of Russian news.
Abstract:In this paper, we explore the ways to improve POS-tagging using various types of auxiliary losses and different word representations. As a baseline, we utilized a BiLSTM tagger, which is able to achieve state-of-the-art results on the sequence labelling tasks. We developed a new method for character-level word representation using feedforward neural network. Such representation gave us better results in terms of speed and performance of the model. We also applied a novel technique of pretraining such word representations with existing word vectors. Finally, we designed a new variant of auxiliary loss for sequence labelling tasks: an additional prediction of the neighbour labels. Such loss forces a model to learn the dependencies in-side a sequence of labels and accelerates the process of training. We test these methods on English and Russian languages.