Generating free-text rationales is among the emergent capabilities of Large Language Models (LLMs). These rationales have been found to enhance LLM performance across various NLP tasks. Recently, there has been growing interest in using these rationales to provide insights for various important downstream tasks. In this paper, we analyze generated free-text rationales in tasks with subjective answers, emphasizing the importance of rationalization in such scenarios. We focus on pairwise argument ranking, a highly subjective task with significant potential for real-world applications, such as debate assistance. We evaluate the persuasiveness of rationales generated by nine LLMs to support their subjective choices. Our findings suggest that open-source LLMs, particularly Llama2-70B-chat, are capable of providing highly persuasive rationalizations, surpassing even GPT models. Additionally, our experiments demonstrate that the persuasiveness of the generated rationales can be enhanced by guiding their persuasive elements through prompting or self-refinement techniques.

Human evaluation remains the gold standard for assessing abstractive summarization. However, current practices often prioritize constructing evaluation guidelines for fluency, coherence, and factual accuracy, overlooking other critical dimensions. In this paper, we investigate argument coverage in abstractive summarization by focusing on long legal opinions, where summaries must effectively encapsulate the document’s argumentative nature. We introduce a set of human-evaluation guidelines to evaluate generated summaries based on argumentative coverage. These guidelines enable us to assess three distinct summarization models, studying the influence of including argument roles in summarization. Furthermore, we utilize these evaluation scores to benchmark automatic summarization metrics against argument coverage, providing insights into the effectiveness of automated evaluation methods.

This paper introduces ReflectSumm, a novel summarization dataset specifically designed for summarizing students’ reflective writing. The goal of ReflectSumm is to facilitate developing and evaluating novel summarization techniques tailored to real-world scenarios with little training data, with potential implications in the opinion summarization domain in general and the educational domain in particular. The dataset encompasses a diverse range of summarization tasks and includes comprehensive metadata, enabling the exploration of various research questions and supporting different applications. To showcase its utility, we conducted extensive evaluations using multiple state-of-the-art baselines. The results provide benchmarks for facilitating further research in this area.

We propose a simple approach for the abstractive summarization of long legal opinions that takes into account the argument structure of the document. Legal opinions often contain complex and nuanced argumentation, making it challenging to generate a concise summary that accurately captures the main points of the legal opinion. Our approach involves using argument role information to generate multiple candidate summaries, then reranking these candidates based on alignment with the document’s argument structure. We demonstrate the effectiveness of our approach on a dataset of long legal opinions and show that it outperforms several strong baselines.

This paper presents an overview of the ImageArg shared task, the first multimodal Argument Mining shared task co-located with the 10th Workshop on Argument Mining at EMNLP 2023. The shared task comprises two classification subtasks - (1) Subtask-A: Argument Stance Classification; (2) Subtask-B: Image Persuasiveness Classification. The former determines the stance of a tweet containing an image and a piece of text toward a controversial topic (e.g., gun control and abortion). The latter determines whether the image makes the tweet text more persuasive. The shared task received 31 submissions for Subtask-A and 21 submissions for Subtask-B from 9 different teams across 6 countries. The top submission in Subtask-A achieved an F1-score of 0.8647 while the best submission in Subtask-B achieved an F1-score of 0.5561.

A challenging task when generating summaries of legal documents is the ability to address their argumentative nature. We introduce a simple technique to capture the argumentative structure of legal documents by integrating argument role labeling into the summarization process. Experiments with pretrained language models show that our proposed approach improves performance over strong baselines.

Argument role labeling is a fundamental task in Argument Mining research. However, such research often suffers from a lack of large-scale datasets labeled for argument roles such as evidence, which is crucial for neural model training. While large pretrained language models have somewhat alleviated the need for massive manually labeled datasets, how much these models can further benefit from self-training techniques hasn’t been widely explored in the literature in general and in Argument Mining specifically. In this work, we focus on self-trained language models (particularly BERT) for evidence detection. We provide a thorough investigation on how to utilize pseudo labels effectively in the self-training scheme. We also assess whether adding pseudo labels from an out-of-domain source can be beneficial. Experiments on sentence level evidence detection show that self-training can complement pretrained language models to provide performance improvements.

This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language modeling, concept detection, and paraphrase detection) both individually and in combination, with the goal of enhancing the target task of abstractive summarization via multitask learning. We show that for many task combinations, a model trained in a multitask setting outperforms a model trained only for abstractive summarization, with no additional summarization data introduced. Additionally, we do a comprehensive search and find that certain tasks (e.g. paraphrase detection) consistently benefit abstractive summarization, not only when combined with other tasks but also when using different architectures and training corpora.

In this paper, we describe CU-RAISA teamcontribution to the 2019Madar shared task2, which focused on Twitter User fine-grained dialect identification. Among par-ticipating teams, our system ranked the4th(with 61.54%) F1-Macro measure. Our sys-tem is trained using a character level convo-lutional bidirectional long-short-term memorynetwork trained on 2k users’ data. We showthat training on concatenated user tweets asinput is further superior to training on usertweets separately and assign user’s label on themode of user’s tweets’ predictions.

The Arabic Online Commentary (AOC) (Zaidan and Callison-Burch, 2011) is a large-scale repos-itory of Arabic dialects with manual labels for4varieties of the language. Existing dialect iden-tification models exploiting the dataset pre-date the recent boost deep learning brought to NLPand hence the data are not benchmarked for use with deep learning, nor is it clear how much neural networks can help tease the categories in the data apart. We treat these two limitations:We (1) benchmark the data, and (2) empirically test6different deep learning methods on thetask, comparing peformance to several classical machine learning models under different condi-tions (i.e., both binary and multi-way classification). Our experimental results show that variantsof (attention-based) bidirectional recurrent neural networks achieve best accuracy (acc) on thetask, significantly outperforming all competitive baselines. On blind test data, our models reach87.65%acc on the binary task (MSA vs. dialects),87.4%acc on the 3-way dialect task (Egyptianvs. Gulf vs. Levantine), and82.45%acc on the 4-way variants task (MSA vs. Egyptian vs. Gulfvs. Levantine). We release our benchmark for future work on the dataset

We describe UBC-NLP contribution to IEST-2018, focused at learning implicit emotion in Twitter data. Among the 30 participating teams, our system ranked the 4th (with 69.3% F-score). Post competition, we were able to score slightly higher than the 3rd ranking system (reaching 70.7%). Our system is trained on top of a pre-trained language model (LM), fine-tuned on the data provided by the task organizers. Our best results are acquired by an average of an ensemble of language models. We also offer an analysis of system performance and the impact of training data size on the task. For example, we show that training our best model for only one epoch with < 40% of the data enables better performance than the baseline reported by Klinger et al. (2018) for the task.

In this paper, we introduce an enhancement for speech recognition systems using an unsupervised speaker clustering technique. The proposed technique is mainly based on I-vectors and Self-Organizing Map Neural Network(SOM).The input to the proposed algorithm is a set of speech utterances. For each utterance, we extract 100-dimensional I-vector and then SOM is used to group the utterances to different speakers. In our experiments, we compared our technique with Normalized Cross Likelihood ratio Clustering (NCLR). Results show that the proposed technique reduces the speaker error rate in comparison with NCLR. Finally, we have experimented the effect of speaker clustering on Speaker Adaptive Training (SAT) in a speech recognition system implemented to test the performance of the proposed technique. It was noted that the proposed technique reduced the WER over clustering speakers with NCLR.