Computation and Language (cs.CL)

Abstract: Commonsense fact verification, as a challenging branch of commonsense question-answering (QA), aims to verify through facts whether a given commonsense claim is correct or not. Answering commonsense questions necessitates a combination of knowledge from various levels. However, existing studies primarily rest on grasping either unstructured evidence or potential reasoning paths from structured knowledge bases, yet failing to exploit the benefits of heterogeneous knowledge simultaneously. In light of this, we propose Decker, a commonsense fact verification model that is capable of bridging heterogeneous knowledge by uncovering latent relationships between structured and unstructured knowledge. Experimental results on two commonsense fact verification benchmark datasets, CSQA2.0 and CREAK demonstrate the effectiveness of our Decker and further analysis verifies its capability to seize more precious information through reasoning.

Abstract: Wikipedia can be edited by anyone and thus contains various quality sentences. Therefore, Wikipedia includes some poor-quality edits, which are often marked up by other editors. While editors' reviews enhance the credibility of Wikipedia, it is hard to check all edited text. Assisting in this process is very important, but a large and comprehensive dataset for studying it does not currently exist. Here, we propose WikiSQE, the first large-scale dataset for sentence quality estimation in Wikipedia. Each sentence is extracted from the entire revision history of Wikipedia, and the target quality labels were carefully investigated and selected. WikiSQE has about 3.4 M sentences with 153 quality labels. In the experiment with automatic classification using competitive machine learning models, sentences that had problems with citation, syntax/semantics, or propositions were found to be more difficult to detect. In addition, we conducted automated essay scoring experiments to evaluate the generalizability of the dataset. We show that the models trained on WikiSQE perform better than the vanilla model, indicating its potential usefulness in other domains. WikiSQE is expected to be a valuable resource for other tasks in NLP.

Abstract: Commonsense question answering (QA) research requires machines to answer questions based on commonsense knowledge. However, this research requires expensive labor costs to annotate data as the basis of research, and models that rely on fine-tuning paradigms only apply to specific tasks, rather than learn a general commonsense reasoning ability. As a more robust method, zero-shot commonsense question answering shows a good prospect. The current zero-shot framework tries to convert triples in commonsense knowledge graphs (KGs) into QA-form samples as the pre-trained data source to incorporate commonsense knowledge into the model. However, this method ignores the multi-hop relationship in the KG, which is also an important central problem in commonsense reasoning. In this paper, we propose a novel multi-hop commonsense knowledge injection framework. Specifically, it explores multi-hop reasoning paradigm in KGs that conform to linguistic logic, and we further propose two multi-hop QA generation methods based on KGs. Then, we utilize contrastive learning to pre-train the model with the synthetic QA dataset to inject multi-hop commonsense knowledge. Extensive experiments on five commonsense question answering benchmarks demonstrate that our framework achieves state-of-art performance.

Abstract: In-context learning (ICL) unfolds as large language models become capable of inferring test labels conditioned on a few labeled samples without any gradient update. ICL-enabled large language models provide a promising step forward toward bypassing recurrent annotation costs in a low-resource setting. Yet, only a handful of past studies have explored ICL in a cross-lingual setting, in which the need for transferring label-knowledge from a high-resource language to a low-resource one is immensely crucial. To bridge the gap, we provide the first in-depth analysis of ICL for cross-lingual text classification. We find that the prevalent mode of selecting random input-label pairs to construct the prompt-context is severely limited in the case of cross-lingual ICL, primarily due to the lack of alignment in the input as well as the output spaces. To mitigate this, we propose a novel prompt construction strategy -- Cross-lingual In-context Source-Target Alignment (X-InSTA). With an injected coherence in the semantics of the input examples and a task-based alignment across the source and target languages, X-InSTA is able to outperform random prompt selection by a large margin across three different tasks using 44 different cross-lingual pairs.

Abstract: Adapting a large language model for multiple-attribute text style transfer via fine-tuning can be challenging due to the significant amount of computational resources and labeled data required for the specific task. In this paper, we address this challenge by introducing AdapterTST, a framework that freezes the pre-trained model's original parameters and enables the development of a multiple-attribute text style transfer model. Using BART as the backbone model, Adapter-TST utilizes different neural adapters to capture different attribute information, like a plug-in connected to BART. Our method allows control over multiple attributes, like sentiment, tense, voice, etc., and configures the adapters' architecture to generate multiple outputs respected to attributes or compositional editing on the same sentence. We evaluate the proposed model on both traditional sentiment transfer and multiple-attribute transfer tasks. The experiment results demonstrate that Adapter-TST outperforms all the state-of-the-art baselines with significantly lesser computational resources. We have also empirically shown that each adapter is able to capture specific stylistic attributes effectively and can be configured to perform compositional editing.

Abstract: For years the model performance in machine learning obeyed a power-law relationship with the model size. For the consideration of parameter efficiency, recent studies focus on increasing model depth rather than width to achieve better performance. In this paper, we study how model width affects the Transformer model through a parameter-efficient multi-path structure. To better fuse features extracted from different paths, we add three additional operations to each sublayer: a normalization at the end of each path, a cheap operation to produce more features, and a learnable weighted mechanism to fuse all features flexibly. Extensive experiments on 12 WMT machine translation tasks show that, with the same number of parameters, the shallower multi-path model can achieve similar or even better performance than the deeper model. It reveals that we should pay more attention to the multi-path structure, and there should be a balance between the model depth and width to train a better large-scale Transformer.

Abstract: Representation forgetting refers to the drift of contextualized representations during continual training. Intuitively, the representation forgetting can influence the general knowledge stored in pre-trained language models (LMs), but the concrete effect is still unclear. In this paper, we study the effect of representation forgetting on the generality of pre-trained language models, i.e. the potential capability for tackling future downstream tasks. Specifically, we design three metrics, including overall generality destruction (GD), syntactic knowledge forgetting (SynF), and semantic knowledge forgetting (SemF), to measure the evolution of general knowledge in continual learning. With extensive experiments, we find that the generality is destructed in various pre-trained LMs, and syntactic and semantic knowledge is forgotten through continual learning. Based on our experiments and analysis, we further get two insights into alleviating general knowledge forgetting: 1) training on general linguistic tasks at first can mitigate general knowledge forgetting; 2) the hybrid continual learning method can mitigate the generality destruction and maintain more general knowledge compared with those only considering rehearsal or regularization.

Abstract: We propose a novel approach for developing privacy-preserving large-scale recommender systems using differentially private (DP) large language models (LLMs) which overcomes certain challenges and limitations in DP training these complex systems. Our method is particularly well suited for the emerging area of LLM-based recommender systems, but can be readily employed for any recommender systems that process representations of natural language inputs. Our approach involves using DP training methods to fine-tune a publicly pre-trained LLM on a query generation task. The resulting model can generate private synthetic queries representative of the original queries which can be freely shared for any downstream non-private recommendation training procedures without incurring any additional privacy cost. We evaluate our method on its ability to securely train effective deep retrieval models, and we observe significant improvements in their retrieval quality without compromising query-level privacy guarantees compared to methods where the retrieval models are directly DP trained.

Abstract: Large language models (LLMs) have been widely studied for their ability to store and utilize positive knowledge. However, negative knowledge, such as "lions don't live in the ocean", is also ubiquitous in the world but rarely mentioned explicitly in the text. What do LLMs know about negative knowledge? This work examines the ability of LLMs to negative commonsense knowledge. We design a constrained keywords-to-sentence generation task (CG) and a Boolean question-answering task (QA) to probe LLMs. Our experiments reveal that LLMs frequently fail to generate valid sentences grounded in negative commonsense knowledge, yet they can correctly answer polar yes-or-no questions. We term this phenomenon the belief conflict of LLMs. Our further analysis shows that statistical shortcuts and negation reporting bias from language modeling pre-training cause this conflict.

Abstract: A medical provider's summary of a patient visit serves several critical purposes, including clinical decision-making, facilitating hand-offs between providers, and as a reference for the patient. An effective summary is required to be coherent and accurately capture all the medically relevant information in the dialogue, despite the complexity of patient-generated language. Even minor inaccuracies in visit summaries (for example, summarizing "patient does not have a fever" when a fever is present) can be detrimental to the outcome of care for the patient. This paper tackles the problem of medical conversation summarization by discretizing the task into several smaller dialogue-understanding tasks that are sequentially built upon. First, we identify medical entities and their affirmations within the conversation to serve as building blocks. We study dynamically constructing few-shot prompts for tasks by conditioning on relevant patient information and use GPT-3 as the backbone for our experiments. We also develop GPT-derived summarization metrics to measure performance against reference summaries quantitatively. Both our human evaluation study and metrics for medical correctness show that summaries generated using this approach are clinically accurate and outperform the baseline approach of summarizing the dialog in a zero-shot, single-prompt setting.

Abstract: Analogical reasoning is a fundamental cognitive ability of humans. However, current language models (LMs) still struggle to achieve human-like performance in analogical reasoning tasks due to a lack of resources for model training. In this work, we address this gap by proposing ANALOGYKB, a million-scale analogy knowledge base (KB) derived from existing knowledge graphs (KGs). ANALOGYKB identifies two types of analogies from the KGs: 1) analogies of the same relations, which can be directly extracted from the KGs, and 2) analogies of analogous relations, which are identified with a selection and filtering pipeline enabled by large LMs (InstructGPT), followed by minor human efforts for data quality control. Evaluations on a series of datasets of two analogical reasoning tasks (analogy recognition and generation) demonstrate that ANALOGYKB successfully enables LMs to achieve much better results than previous state-of-the-art methods.

Abstract: There are two competing approaches for modelling annotator disagreement: distributional soft-labelling approaches (which aim to capture the level of disagreement) or modelling perspectives of individual annotators or groups thereof. We adapt a multi-task architecture -- which has previously shown success in modelling perspectives -- to evaluate its performance on the SEMEVAL Task 11. We do so by combining both approaches, i.e. predicting individual annotator perspectives as an interim step towards predicting annotator disagreement. Despite its previous success, we found that a multi-task approach performed poorly on datasets which contained distinct annotator opinions, suggesting that this approach may not always be suitable when modelling perspectives. Furthermore, our results explain that while strongly perspectivist approaches might not achieve state-of-the-art performance according to evaluation metrics used by distributional approaches, our approach allows for a more nuanced understanding of individual perspectives present in the data. We argue that perspectivist approaches are preferable because they enable decision makers to amplify minority views, and that it is important to re-evaluate metrics to reflect this goal.

Abstract: The MultiCoNER II task aims to detect complex, ambiguous, and fine-grained named entities in low-context situations and noisy scenarios like the presence of spelling mistakes and typos for multiple languages. The task poses significant challenges due to the scarcity of contextual information, the high granularity of the entities(up to 33 classes), and the interference of noisy data. To address these issues, our team {\bf PAI} proposes a universal Named Entity Recognition (NER) system that integrates external entity information to improve performance. Specifically, our system retrieves entities with properties from the knowledge base (i.e. Wikipedia) for a given text, then concatenates entity information with the input sentence and feeds it into Transformer-based models. Finally, our system wins 2 first places, 4 second places, and 1 third place out of 13 tracks. The code is publicly available at \url{https://github.com/diqiuzhuanzhuan/semeval-2023}.

Abstract: Prompt tuning provides an efficient way for users to customize Large Language Models (LLMs) with their private data in the emerging LLM service scenario. However, the sensitive nature of private data brings the need for privacy preservation in LLM service customization. Based on prompt tuning, we propose Privacy-Preserving Prompt Tuning (RAPT), a framework that provides privacy guarantees for LLM services. \textsc{rapt} adopts a local privacy setting, allowing users to privatize their data locally with local differential privacy. As prompt tuning performs poorly when directly trained on privatized data, we introduce a novel privatized token reconstruction task that is trained jointly with the downstream task, allowing LLMs to learn better task-dependent representations. Despite the simplicity of our framework, experiments show that RAPT achieves competitive performance across tasks while providing privacy guarantees against adversaries.

Abstract: To date, most work on text simplification has focused on sentence-level inputs. Early attempts at document simplification merely applied these approaches iteratively over the sentences of a document. However, this fails to coherently preserve the discourse structure, leading to suboptimal output quality. Recently, strategies from controllable simplification have been leveraged to achieve state-of-the-art results on document simplification by first generating a document-level plan (a sequence of sentence-level simplification operations) and using this plan to guide sentence-level simplification downstream. However, this is still limited in that the simplification model has no direct access to the local inter-sentence document context, likely having a negative impact on surface realisation. We explore various systems that use document context within the simplification process itself, either by iterating over larger text units or by extending the system architecture to attend over a high-level representation of document context. In doing so, we achieve state-of-the-art performance on the document simplification task, even when not relying on plan-guidance. Further, we investigate the performance and efficiency tradeoffs of system variants and make suggestions of when each should be preferred.

Abstract: Commonsense knowledge is crucial to many natural language processing tasks. Existing works usually incorporate graph knowledge with conventional graph neural networks (GNNs), leading to the text and graph knowledge encoding processes being separated in a serial pipeline. We argue that these separate representation learning stages may be suboptimal for neural networks to learn the overall context contained in both types of input knowledge. In this paper, we propose a novel context-aware graph-attention model (Context-aware GAT), which can effectively incorporate global features of relevant knowledge graphs based on a context-enhanced knowledge aggregation process. Specifically, our framework leverages a novel representation learning approach to process heterogeneous features - combining flattened graph knowledge with text. To the best of our knowledge, this is the first attempt at hierarchically applying graph knowledge aggregation on a connected subgraph in addition to contextual information to support commonsense dialogue generation. This framework shows superior performance compared to conventional GNN-based language frameworks. Both automatic and human evaluation demonstrates that our proposed model has significant performance uplifts over state-of-the-art baselines.

Abstract: Large language models, particularly GPT-3, are able to produce high quality summaries of general domain news articles in few- and zero-shot settings. However, it is unclear if such models are similarly capable in more specialized, high-stakes domains such as biomedicine. In this paper, we enlist domain experts (individuals with medical training) to evaluate summaries of biomedical articles generated by GPT-3, given zero supervision. We consider both single- and multi-document settings. In the former, GPT-3 is tasked with generating regular and plain-language summaries of articles describing randomized controlled trials; in the latter, we assess the degree to which GPT-3 is able to \emph{synthesize} evidence reported across a collection of articles. We design an annotation scheme for evaluating model outputs, with an emphasis on assessing the factual accuracy of generated summaries. We find that while GPT-3 is able to summarize and simplify single biomedical articles faithfully, it struggles to provide accurate aggregations of findings over multiple documents. We release all data and annotations used in this work.

Abstract: A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support their claims. However, evaluating the attribution, i.e., verifying whether the generated statement is indeed fully supported by the cited reference, remains an open problem. Although human evaluation is common practice, it is costly and time-consuming. In this paper, we investigate the automatic evaluation of attribution by LLMs. We begin by providing a definition of attribution and then explore two approaches for automatic evaluation: prompting LLMs and fine-tuning smaller LMs. The fine-tuning data is repurposed from related tasks, such as question answering, fact-checking, natural language inference, and summarization. To facilitate the evaluation, we manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on the curated test set and simulated test examples from existing benchmark questions highlight both promising signals as well as remaining challenges for the automatic evaluation of attribution. We hope our testbed, modeling methodology, and insights will help lay the foundation for future studies on this important problem.

Abstract: In the paper, we propose a novel way of improving named entity recognition in the Korean language using its language-specific features. While the field of named entity recognition has been studied extensively in recent years, the mechanism of efficiently recognizing named entities in Korean has hardly been explored. This is because the Korean language has distinct linguistic properties that prevent models from achieving their best performances. Therefore, an annotation scheme for {Korean corpora} by adopting the CoNLL-U format, which decomposes Korean words into morphemes and reduces the ambiguity of named entities in the original segmentation that may contain functional morphemes such as postpositions and particles, is proposed herein. We investigate how the named entity tags are best represented in this morpheme-based scheme and implement an algorithm to convert word-based {and syllable-based Korean corpora} with named entities into the proposed morpheme-based format. Analyses of the results of {statistical and neural} models reveal that the proposed morpheme-based format is feasible, and the {varied} performances of the models under the influence of various additional language-specific features are demonstrated. Extrinsic conditions were also considered to observe the variance of the performances of the proposed models, given different types of data, including the original segmentation and different types of tagging formats.

Abstract: We present in this work a new Universal Morphology dataset for Korean. Previously, the Korean language has been underrepresented in the field of morphological paradigms amongst hundreds of diverse world languages. Hence, we propose this Universal Morphological paradigms for the Korean language that preserve its distinct characteristics. For our K-UniMorph dataset, we outline each grammatical criterion in detail for the verbal endings, clarify how to extract inflected forms, and demonstrate how we generate the morphological schemata. This dataset adopts morphological feature schema from Sylak-Glassman et al. (2015) and Sylak-Glassman (2016) for the Korean language as we extract inflected verb forms from the Sejong morphologically analyzed corpus that is one of the largest annotated corpora for Korean. During the data creation, our methodology also includes investigating the correctness of the conversion from the Sejong corpus. Furthermore, we carry out the inflection task using three different Korean word forms: letters, syllables and morphemes. Finally, we discuss and describe future perspectives on Korean morphological paradigms and the dataset.

Abstract: Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered for a particular question, in-context reasoning can be sensitive to distractor facts, additional content that is irrelevant to a question but that may be relevant for a different question (i.e., not necessarily random noise). In these situations, the model fails to distinguish the knowledge that is necessary to answer the question, leading to spurious reasoning and degraded performance. This reasoning failure contrasts with the model's apparent ability to distinguish its contextual knowledge from all the knowledge it has memorized during pre-training. Following this observation, we propose teaching the model to reason more robustly by folding the provided contextual knowledge into the model's parameters before presenting it with a question. Our method, RECKONING, is a bi-level learning algorithm that teaches language models to reason by updating their parametric knowledge through back-propagation, allowing them to then answer questions using the updated parameters. During training, the inner loop rapidly adapts a copy of the model weights to encode contextual knowledge into its parameters. In the outer loop, the model learns to uses the updated weights to reproduce and answer reasoning questions about the memorized knowledge. Our experiments on two multi-hop reasoning datasets show that RECKONING's performance improves over the in-context reasoning baseline (by up to 4.5%). We also find that compared to in-context reasoning, RECKONING generalizes better to longer reasoning chains unseen during training, is more robust to distractors in the context, and is more computationally efficient when multiple questions are asked about the same knowledge.