cs.CL - 2023-11-04

Can Chat GPT solve a Linguistics Exam?

  • paper_url: http://arxiv.org/abs/2311.02499
  • repo_url: None
  • paper_authors: Patricia Ronan, Gerold Schneider
  • for: 这个研究是用来测试 chatGPT4 是否能成功解决入门语言学考试的。
  • methods: 这个研究使用了 chatGPT4 语言模型,并将过去的考试题 fed 到它中进行测试。
  • results: 研究发现,chatGPT4 在解释复杂和嵌套任务方面非常成功,但在分析 morphemes 和 phrases 方面表现较差。在简单的情况下,它表现 suficiently well,但在缺失一对一对应的情况下,它的结果是混合的。现在,模型还不能处理视觉化任务,如语法树的分析或生成。通过更EXTENSIVE的预处理,将这些任务转换为文本数据,可以使模型也成功地解决这些任务。
    Abstract The present study asks if ChatGPT4, the version of ChatGPT which uses the language model GPT4, can successfully solve introductory linguistic exams. Previous exam questions of an Introduction to Linguistics course at a German university are used to test this. The exam questions were fed into ChatGPT4 with only minimal preprocessing. The results show that the language model is very successful in the interpretation even of complex and nested tasks. It proved surprisingly successful in the task of broad phonetic transcription, but performed less well in the analysis of morphemes and phrases. In simple cases it performs sufficiently well, but rarer cases, particularly with missing one-to-one correspondence, are currently treated with mixed results. The model is not yet able to deal with visualisations, such as the analysis or generation of syntax trees. More extensive preprocessing, which translates these tasks into text data, allow the model to also solve these tasks successfully.
    摘要 本研究问题是否可以使用 ChatGPT4,基于语言模型 GPT4 解决入门语言考试。研究使用了一个德国大学 introductory linguistics 课程的先前考试题,并将其feed into ChatGPT4 中,只进行了最小的处理。结果显示,语言模型在复杂和嵌入的任务中表现非常成功。它在广泛的音素识别任务中表现出色,但在分析 morphemes 和 phrases 方面表现较差。在简单的情况下,它的表现足够好,但在缺少一对一对应的情况下,现在的结果是混合的。模型目前无法处理视觉化任务,如语法树的分析或生成。通过更进一步的处理,将这些任务转化为文本数据后,模型也可以成功解决这些任务。

Citance-Contextualized Summarization of Scientific Papers

  • paper_url: http://arxiv.org/abs/2311.02408
  • repo_url: None
  • paper_authors: Shahbaz Syed, Ahmad Dawar Hakimi, Khalid Al-Khatib, Martin Potthast
  • for: 本研究旨在提供一种新的文本概要方法,可以根据给定的引用句(即“citance”)生成有用的概要。
  • methods: 该方法首先提取并模型了文献中的引用,然后根据引用的位置 retrieve 相关的段落,最后生成基于每个引用的概要。
  • results: 我们使用 $\textbf{Webis-Context-SciSumm-2023}$ 数据集进行评估,发现我们的方法可以生成高质量的概要,并且可以准确地捕捉到文献中的关键信息。
    Abstract Current approaches to automatic summarization of scientific papers generate informative summaries in the form of abstracts. However, abstracts are not intended to show the relationship between a paper and the references cited in it. We propose a new contextualized summarization approach that can generate an informative summary conditioned on a given sentence containing the citation of a reference (a so-called ``citance''). This summary outlines the content of the cited paper relevant to the citation location. Thus, our approach extracts and models the citances of a paper, retrieves relevant passages from cited papers, and generates abstractive summaries tailored to each citance. We evaluate our approach using $\textbf{Webis-Context-SciSumm-2023}$, a new dataset containing 540K~computer science papers and 4.6M~citances therein.
    摘要 现有的自动摘要方法可以生成有用的摘要,但这些摘要不能显示科学论文中引用的文献之间的关系。我们提议一种新的受条件摘要方法,可以根据给定的引用句(即“ citance”)生成相关的摘要。这个摘要将描述引用的文献中与该引用相关的内容。因此,我们的方法可以提取和模型文献中的引用,从引用的文献中检索相关的段落,并生成基于每个引用的摘要。我们使用 $\textbf{Webis-Context-SciSumm-2023}$ dataset,该 dataset包含 540 万个计算机科学论文和 460 万个引用。

TreeSwap: Data Augmentation for Machine Translation via Dependency Subtree Swapping

  • paper_url: http://arxiv.org/abs/2311.02355
  • repo_url: https://github.com/attilanagy234/TreeSwap
  • paper_authors: Attila Nagy, Dorina Lakatos, Botond Barta, Judit Ács
  • for: 该论文主要用于提出一种新的数据扩充方法,用于提高神经机器翻译模型在具有有限训练数据的情况下的性能。
  • methods: 该方法基于 SentenceDependencyGraph,通过将源句子和目标句子中的对象和主语交换来生成新的句子。
  • results: 对4种语言对在限制资源 datasets 上进行了实验,结果显示,TreeSwap 方法可以在多个语言对的两个方向中提供了顺序的改进。
    Abstract Data augmentation methods for neural machine translation are particularly useful when limited amount of training data is available, which is often the case when dealing with low-resource languages. We introduce a novel augmentation method, which generates new sentences by swapping objects and subjects across bisentences. This is performed simultaneously based on the dependency parse trees of the source and target sentences. We name this method TreeSwap. Our results show that TreeSwap achieves consistent improvements over baseline models in 4 language pairs in both directions on resource-constrained datasets. We also explore domain-specific corpora, but find that our method does not make significant improvements on law, medical and IT data. We report the scores of similar augmentation methods and find that TreeSwap performs comparably. We also analyze the generated sentences qualitatively and find that the augmentation produces a correct translation in most cases. Our code is available on Github.
    摘要 � apparatus augmentation methods for neural machine translation are particularly useful when limited amount of training data is available, which is often the case when dealing with low-resource languages. We introduce a novel augmentation method, which generates new sentences by swapping objects and subjects across bisentences. This is performed simultaneously based on the dependency parse trees of the source and target sentences. We name this method TreeSwap. Our results show that TreeSwap achieves consistent improvements over baseline models in 4 language pairs in both directions on resource-constrained datasets. We also explore domain-specific corpora, but find that our method does not make significant improvements on law, medical and IT data. We report the scores of similar augmentation methods and find that TreeSwap performs comparably. We also analyze the generated sentences qualitatively and find that the augmentation produces a correct translation in most cases. Our code is available on Github.Here's a word-for-word translation of the text in Traditional Chinese:� apparatus augmentation methods for neural machine translation are particularly useful when limited amount of training data is available, which is often the case when dealing with low-resource languages. We introduce a novel augmentation method, which generates new sentences by swapping objects and subjects across bisentences. This is performed simultaneously based on the dependency parse trees of the source and target sentences. We name this method TreeSwap. Our results show that TreeSwap achieves consistent improvements over baseline models in 4 language pairs in both directions on resource-constrained datasets. We also explore domain-specific corpora, but find that our method does not make significant improvements on law, medical and IT data. We report the scores of similar augmentation methods and find that TreeSwap performs comparably. We also analyze the generated sentences qualitatively and find that the augmentation produces a correct translation in most cases. Our code is available on Github.

Enhancing English Writing Proficiency in China’s Polytechnic Students An In-Depth Literature Review on the Application of the Input Hypothesis

  • paper_url: http://arxiv.org/abs/2311.02341
  • repo_url: None
  • paper_authors: Wei Zhou
  • for: 这个研究论文的目的是探讨如何使用输入假设(Stephen Krashen)来提高polytechnic学生的英语写作能力。
  • methods: 这个研究使用了实际观察和前期研究的数据,以检验输入假设对polytechnic学生的写作能力的影响。
  • results: 研究发现,通过提供可理解的输入,polytechnic学生的写作能力有所改善,这证明了输入假设的有效性。I hope that helps! Let me know if you have any other questions.
    Abstract Having good English writing skills is extremely important for students in polytechnic institutions. However, a lot of students in technical schools have difficulties in reaching high levels of skill. The Input Hypothesis, created by Stephen Krashen, suggests that people learn languages well when they receive information that's a little harder than what they already know but still understandable. This research paper wants to study how the Input Hypothesis can help polytechnic students improve their English writing skills. The study will include real-life observations and experiments from the previous research. We will look at data from polytechnic students who are receiving special writing instruction to see if the Input Hypothesis actually helps improve their writing skills. The paper can better inform polytechnic students, faculty members, and support staff and even members of the larger community about the attributions, the processes, and the possible outcomes of second language development for polytechnic students. Keywords: English writing skills, Polytechnic students, Input hypothesis, Comprehensible input
    摘要 有良好的英语写作技巧对polytechnic学生非常重要。然而,许多技术学校的学生在达到高水平技巧方面遇到困难。输入假设(Input Hypothesis),由史蒂芬·卡什描述,表明人们在接受可以理解但是一些 harder than what they already know的信息时,会学习语言非常好。这篇研究论文旨在研究如何使用输入假设来帮助polytechnic学生提高英语写作技巧。这篇论文将包括以前的实验和观察数据,以确定输入假设是否确实有助于提高polytechnic学生的写作技巧。这篇论文可以更好地告诉polytechnic学生、教师和支持人员,以及社区成员关于第二语言发展的特点、过程和可能的结果。Keywords: 英语写作技巧, polytechnic学生, 输入假设, 可以理解的输入

Identifying Context-Dependent Translations for Evaluation Set Production

  • paper_url: http://arxiv.org/abs/2311.02321
  • repo_url: None
  • paper_authors: Rachel Wicks, Matt Post
  • for: 本研究的目的是解决Context-aware机器翻译的评估 метри克和测试集的缺失,以便更好地评估Context-aware机器翻译系统的性能。
  • methods: 本研究使用了现代化、扩展和通用的前一代Annotation pipeline,生成了CTXPRO工具,可以正确地翻译五种语言现象:性别、正式度和生物性 для代词、句子间隔融合、和不确定名词变化。
  • results: 研究使用了 seven 种语言对(EN到DE、ES、FR、IT、PL、PT和RU)和两个数据集(OpenSubtitles和WMT测试集),并验证了 CTXPRO 的性能,包括与前一代工作的重叠和分类一个Context-aware机器翻译系统和一个句子基于系统。
    Abstract A major impediment to the transition to context-aware machine translation is the absence of good evaluation metrics and test sets. Sentences that require context to be translated correctly are rare in test sets, reducing the utility of standard corpus-level metrics such as COMET or BLEU. On the other hand, datasets that annotate such sentences are also rare, small in scale, and available for only a few languages. To address this, we modernize, generalize, and extend previous annotation pipelines to produce CTXPRO, a tool that identifies subsets of parallel documents containing sentences that require context to correctly translate five phenomena: gender, formality, and animacy for pronouns, verb phrase ellipsis, and ambiguous noun inflections. The input to the pipeline is a set of hand-crafted, per-language, linguistically-informed rules that select contextual sentence pairs using coreference, part-of-speech, and morphological features provided by state-of-the-art tools. We apply this pipeline to seven languages pairs (EN into and out-of DE, ES, FR, IT, PL, PT, and RU) and two datasets (OpenSubtitles and WMT test sets), and validate its performance using both overlap with previous work and its ability to discriminate a contextual MT system from a sentence-based one. We release the CTXPRO pipeline and data as open source.
    摘要 另一大障碍Context-aware机器翻译的转换是评估 metric 和测试集的缺失。标准的 corpus-level metric 如 COMET 或 BLEU 在测试集中罕见句子需要上下文correctly 翻译,从而减少了其使用的价值。同时,标注这些句子的数据集也很罕见,规模小,并且只有一些语言可用。为了解决这个问题,我们现代化、扩展和改进了之前的注释管道,生成 CTXPRO,它可以在五种现象上翻译上下文需要correctly:性别、正式度和生命力 для pronouns,verb phrase ellipsis,和不确定名词变化。输入管道的是一组手工编写、语言特有的规则,使用核心关系、part-of-speech 和 morphological feature 提供的状态之 искус智能工具。我们对七种语言对(EN到DE、ES、FR、IT、PL、PT和RU)和两个数据集(OpenSubtitles 和 WMT 测试集)进行应用,并验证其性能通过与之前工作的重叠和上下文基础MT 系统与句子基础MT 系统之间的分化能力。我们将 CTXPRO 管道和数据作为开源发布。

Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles

  • paper_url: http://arxiv.org/abs/2311.02310
  • repo_url: None
  • paper_authors: Weiting Tan, Haoran Xu, Lingfeng Shen, Shuyue Stella Li, Kenton Murray, Philipp Koehn, Benjamin Van Durme, Yunmo Chen
  • for: 本研究旨在解释在零shot和几shot示例下大语言模型在翻译中的表现差异,以及如何减少这个差异。
  • methods: 本研究使用了零shot和几shot示例来训练大语言模型,并对其进行了各种改进,如对目标句子风格的调整和不同的损失函数。
  • results: 研究发现,通过调整目标句子风格,可以大幅减少零shot和几shot示例之间的表现差异,并且可以提高翻译 metrics。此外,研究还探讨了不同的改进方法,以及它们对翻译 metrics 的影响。
    Abstract Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning. However, even though zero-shot translations are relatively good, there remains a discernible gap comparing their performance with the few-shot setting. In this paper, we investigate the factors contributing to this gap and find that this gap can largely be closed (for about 70%) by matching the writing styles of the target corpus. Additionally, we explore potential approaches to enhance zero-shot baselines without the need for parallel demonstration examples, providing valuable insights into how these methods contribute to improving translation metrics.
    摘要 大型语言模型在单语言 Setting 中受训练后,表现出在机器翻译中使用零或几个例子进行培训,并且可以通过上下文学习实现一定的泛化能力。然而,即使零shot 翻译结果相对较好,仍然存在一定的差距,比如70%的差距。本文investigate这个差距的原因,发现这个差距可以通过对目标句子批处理的样式匹配来大大减少。此外,我们还探讨了如何通过不需要并行示例来提高零shot 基线,并提供了有价值的发现,这些发现可以帮助改善翻译指标。

LLMs grasp morality in concept

  • paper_url: http://arxiv.org/abs/2311.02294
  • repo_url: None
  • paper_authors: Mark Pock, Andre Ye, Jared Moore
  • for: 本研究旨在探讨语言模型(LLM)是如何具备意义的,以及如何使得LLM具备这种意义。
  • methods: 本研究使用一种普适的意义理论来探讨LLM的意义,并用这种理论来解释LLM作为意义代理人的特性。
  • results: 研究发现,由于LLM已经具备了人类社会中的构造(如道德、性别和种族)的概念,因此在某些伦理框架下,目前流行的模型对适应方法有限制,甚至可能是反产生的。此外,未经适应的模型可能可以帮助我们更好地发展我们的道德和社会哲学。
    Abstract Work in AI ethics and fairness has made much progress in regulating LLMs to reflect certain values, such as fairness, truth, and diversity. However, it has taken the problem of how LLMs might 'mean' anything at all for granted. Without addressing this, it is not clear what imbuing LLMs with such values even means. In response, we provide a general theory of meaning that extends beyond humans. We use this theory to explicate the precise nature of LLMs as meaning-agents. We suggest that the LLM, by virtue of its position as a meaning-agent, already grasps the constructions of human society (e.g. morality, gender, and race) in concept. Consequently, under certain ethical frameworks, currently popular methods for model alignment are limited at best and counterproductive at worst. Moreover, unaligned models may help us better develop our moral and social philosophy.
    摘要 <> traduced the given text into Simplified Chinese.工作在人工智能道德和公平方面有很大的进步,以规范LLMs反映某些价值观,如公平、真实和多样性。然而,它忽略了如何让LLMs有任何意义的问题。不解决这个问题,then it is not clear what imbuing LLMs with such values even means. In response, we provide a general theory of meaning that extends beyond humans. We use this theory to explicate the precise nature of LLMs as meaning-agents. We suggest that the LLM, by virtue of its position as a meaning-agent, already grasps the constructions of human society (e.g. morality, gender, and race) in concept. Consequently, under certain ethical frameworks, currently popular methods for model alignment are limited at best and counterproductive at worst. Moreover, unaligned models may help us better develop our moral and social philosophy.Note: Please note that the translation is in Simplified Chinese, which is the standard form of Chinese used in mainland China and Singapore. If you need Traditional Chinese, please let me know.