Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks. However, their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks (e.g., knowledge acquisition tasks). In this paper, we seek to assess and enhance LLMs' contextual faithfulness in two aspects: knowledge conflict and prediction with abstention. We demonstrate that LLMs' faithfulness can be significantly improved using carefully designed prompting strategies. In particular, we identify opinion-based prompts and counterfactual demonstrations as the most effective methods. Opinion-based prompts reframe the context as a narrator's statement and inquire about the narrator's opinions, while counterfactual demonstrations use instances containing false facts to improve faithfulness in knowledge conflict situations. Neither technique requires additional training. We conduct experiments on three datasets of two standard NLP tasks, machine reading comprehension and relation extraction, and the results demonstrate significant improvement in faithfulness to contexts. Code and data are released at https://github.com/wzhouad/context-faithful-llm.
Objective: To develop a natural language processing system that solves both clinical concept extraction and relation extraction in a unified prompt-based machine reading comprehension (MRC) architecture with good generalizability for cross-institution applications. Methods: We formulate both clinical concept extraction and relation extraction using a unified prompt-based MRC architecture and explore state-of-the-art transformer models. We compare our MRC models with existing deep learning models for concept extraction and end-to-end relation extraction using two benchmark datasets developed by the 2018 National NLP Clinical Challenges (n2c2) challenge (medications and adverse drug events) and the 2022 n2c2 challenge (relations of social determinants of health [SDoH]). We also evaluate the transfer learning ability of the proposed MRC models in a cross-institution setting. We perform error analyses and examine how different prompting strategies affect the performance of MRC models. Results and Conclusion: The proposed MRC models achieve state-of-the-art performance for clinical concept and relation extraction on the two benchmark datasets, outperforming previous non-MRC transformer models. GatorTron-MRC achieves the best strict and lenient F1-scores for concept extraction, outperforming previous deep learning models on the two datasets by 1%~3% and 0.7%~1.3%, respectively. For end-to-end relation extraction, GatorTron-MRC and BERT-MIMIC-MRC achieve the best F1-scores, outperforming previous deep learning models by 0.9%~2.4% and 10%-11%, respectively. For cross-institution evaluation, GatorTron-MRC outperforms traditional GatorTron by 6.4% and 16% for the two datasets, respectively. The proposed method is better at handling nested/overlapped concepts, extracting relations, and has good portability for cross-institute applications.
Incorporating prior knowledge can improve existing pre-training models in cloze-style machine reading and has become a new trend in recent studies. Notably, most of the existing models have integrated external knowledge graphs (KG) and transformer-based models, such as BERT into a unified data structure. However, selecting the most relevant ambiguous entities in KG and extracting the best subgraph remains a challenge. In this paper, we propose the LUKE-Graph, a model that builds a heterogeneous graph based on the intuitive relationships between entities in a document without using any external KG. We then use a Relational Graph Attention (RGAT) network to fuse the graph's reasoning information and the contextual representation encoded by the pre-trained LUKE model. In this way, we can take advantage of LUKE, to derive an entity-aware representation; and a graph model - to exploit relation-aware representation. Moreover, we propose Gated-RGAT by augmenting RGAT with a gating mechanism that regulates the question information for the graph convolution operation. This is very similar to human reasoning processing because they always choose the best entity candidate based on the question information. Experimental results demonstrate that the LUKE-Graph achieves state-of-the-art performance on the ReCoRD dataset with commonsense reasoning.
Although many large-scale knowledge bases (KBs) claim to contain multilingual information, their support for many non-English languages is often incomplete. This incompleteness gives birth to the task of cross-lingual question answering over knowledge base (xKBQA), which aims to answer questions in languages different from that of the provided KB. One of the major challenges facing xKBQA is the high cost of data annotation, leading to limited resources available for further exploration. Another challenge is mapping KB schemas and natural language expressions in the questions under cross-lingual settings. In this paper, we propose a novel approach for xKBQA in a reading comprehension paradigm. We convert KB subgraphs into passages to narrow the gap between KB schemas and questions, which enables our model to benefit from recent advances in multilingual pre-trained language models (MPLMs) and cross-lingual machine reading comprehension (xMRC). Specifically, we use MPLMs, with considerable knowledge of cross-lingual mappings, for cross-lingual reading comprehension. Existing high-quality xMRC datasets can be further utilized to finetune our model, greatly alleviating the data scarcity issue in xKBQA. Extensive experiments on two xKBQA datasets in 12 languages show that our approach outperforms various baselines and achieves strong few-shot and zero-shot performance. Our dataset and code are released for further research.
The conversational machine reading comprehension (CMRC) task aims to answer questions in conversations, which has been a hot research topic in recent years because of its wide applications. However, existing CMRC benchmarks in which each conversation is assigned a static passage are inconsistent with real scenarios. Thus, model's comprehension ability towards real scenarios are hard to evaluate reasonably. To this end, we propose the first Chinese CMRC benchmark Orca and further provide zero-shot/few-shot settings to evaluate model's generalization ability towards diverse domains. We collect 831 hot-topic driven conversations with 4,742 turns in total. Each turn of a conversation is assigned with a response-related passage, aiming to evaluate model's comprehension ability more reasonably. The topics of conversations are collected from social media platform and cover 33 domains, trying to be consistent with real scenarios. Importantly, answers in Orca are all well-annotated natural responses rather than the specific spans or short phrase in previous datasets. Besides, we implement three strong baselines to tackle the challenge in Orca. The results indicate the great challenge of our CMRC benchmark. Our datatset and checkpoints are available at https://github.com/nuochenpku/Orca.
Machine reading comprehension (MRC) is an important area of conversation agents and draws a lot of attention. However, there is a notable limitation to current MRC benchmarks: The labeled answers are mostly either spans extracted from the target corpus or the choices of the given candidates, ignoring the natural aspect of high-quality responses. As a result, MRC models trained on these datasets can not generate human-like responses in real QA scenarios. To this end, we construct a new dataset called Penguin to promote the research of MRC, providing a training and test bed for natural response generation to real scenarios. Concretely, Penguin consists of 200k training data with high-quality fluent, and well-informed responses. Penguin is the first benchmark towards natural response generation in Chinese MRC on a relatively large scale. To address the challenges in Penguin, we develop two strong baselines: end-to-end and two-stage frameworks. Following that, we further design Prompt-BART: fine-tuning the pre-trained generative language models with a mixture of prefix prompts in Penguin. Extensive experiments validated the effectiveness of this design.
Pretrained language models have achieved super-human performances on many Machine Reading Comprehension (MRC) benchmarks. Nevertheless, their relative inability to defend against adversarial attacks has spurred skepticism about their natural language understanding. In this paper, we ask whether training with unanswerable questions in SQuAD 2.0 can help improve the robustness of MRC models against adversarial attacks. To explore that question, we fine-tune three state-of-the-art language models on either SQuAD 1.1 or SQuAD 2.0 and then evaluate their robustness under adversarial attacks. Our experiments reveal that current models fine-tuned on SQuAD 2.0 do not initially appear to be any more robust than ones fine-tuned on SQuAD 1.1, yet they reveal a measure of hidden robustness that can be leveraged to realize actual performance gains. Furthermore, we find that the robustness of models fine-tuned on SQuAD 2.0 extends to additional out-of-domain datasets. Finally, we introduce a new adversarial attack to reveal artifacts of SQuAD 2.0 that current MRC models are learning.
Dialogue State Tracking (DST) is core research in dialogue systems and has received much attention. In addition, it is necessary to define a new problem that can deal with dialogue between users as a step toward the conversational AI that extracts and recommends information from the dialogue between users. So, we introduce a new task - DST from dialogue between users about scheduling an event (DST-USERS). The DST-USERS task is much more challenging since it requires the model to understand and track dialogue states in the dialogue between users and to understand who suggested the schedule and who agreed to the proposed schedule. To facilitate DST-USERS research, we develop dialogue datasets between users that plan a schedule. The annotated slot values which need to be extracted in the dialogue are date, time, and location. Previous approaches, such as Machine Reading Comprehension (MRC) and traditional DST techniques, have not achieved good results in our extensive evaluations. By adopting the knowledge-integrated learning method, we achieve exceptional results. The proposed model architecture combines gazetteer features and speaker information efficiently. Our evaluations of the dialogue datasets between users that plan a schedule show that our model outperforms the baseline model.
Machine Reading Comprehension has become one of the most advanced and popular research topics in the fields of Natural Language Processing in recent years. The classification of answerability questions is a relatively significant sub-task in machine reading comprehension; however, there haven't been many studies. Retro-Reader is one of the studies that has solved this problem effectively. However, the encoders of most traditional machine reading comprehension models in general and Retro-Reader, in particular, have not been able to exploit the contextual semantic information of the context completely. Inspired by SemBERT, we use semantic role labels from the SRL task to add semantics to pre-trained language models such as mBERT, XLM-R, PhoBERT. This experiment was conducted to compare the influence of semantics on the classification of answerability for the Vietnamese machine reading comprehension. Additionally, we hope this experiment will enhance the encoder for the Retro-Reader model's Sketchy Reading Module. The improved Retro-Reader model's encoder with semantics was first applied to the Vietnamese Machine Reading Comprehension task and obtained positive results.
Multi-Hop Question Answering (MHQA) is a significant area in question answering, requiring multiple reasoning components, including document retrieval, supporting sentence prediction, and answer span extraction. In this work, we analyze the primary factors limiting the performance of multi-hop reasoning and introduce label smoothing into the MHQA task. This is aimed at enhancing the generalization capabilities of MHQA systems and mitigating overfitting of answer spans and reasoning paths in training set. We propose a novel label smoothing technique, F1 Smoothing, which incorporates uncertainty into the learning process and is specifically tailored for Machine Reading Comprehension (MRC) tasks. Inspired by the principles of curriculum learning, we introduce the Linear Decay Label Smoothing Algorithm (LDLA), which progressively reduces uncertainty throughout the training process. Experiment on the HotpotQA dataset demonstrates the effectiveness of our methods in enhancing performance and generalizability in multi-hop reasoning, achieving new state-of-the-art results on the leaderboard.
Drug-drug interaction prediction is a crucial issue in molecular biology. Traditional methods of observing drug-drug interactions through medical experiments require significant resources and labor. This paper presents a medical knowledge graph question answering model, dubbed MedKGQA, that predicts drug-drug interaction by employing machine reading comprehension from closed-domain literature and constructing a knowledge graph of drug-protein triplets from open-domain documents. The model vectorizes the drug-protein target attributes in the graph using entity embeddings and establishes directed connections between drug and protein entities based on the metabolic interaction pathways of protein targets in the human body. This aligns multiple external knowledge and applies it to learn the graph neural network. Without bells and whistles, the proposed model achieved a 4.5% improvement in terms of drug-drug interaction prediction accuracy compared to previous state-of-the-art models on the Qangaroo MedHop dataset. Experimental results demonstrate the efficiency and effectiveness of the model and verify the feasibility of integrating external knowledge in machine reading comprehension tasks.
Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes. Machines are required to make a decision of "Yes/No/Inquire" or generate a follow-up question when the decision is "Inquire" based on retrieved rule texts, user scenario, user question, and dialogue history. Recent studies explored the methods to reduce the information gap between decision-making and question generation and thus improve the performance of generation. However, the information gap still exists because these pipeline structures are still limited in decision-making, span extraction, and question rephrasing three stages. Decision-making and generation are reasoning separately, and the entailment reasoning utilized in decision-making is hard to share through all stages. To tackle the above problem, we proposed a novel one-stage end-to-end framework, called Entailment Fused-T5 (EFT), to bridge the information gap between decision-making and generation in a global understanding manner. The extensive experimental results demonstrate that our proposed framework achieves new state-of-the-art performance on the OR-ShARC benchmark.
We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. PMR can resolve the discrepancy between model pre-training and downstream fine-tuning of existing MLMs. To build the proposed PMR, we constructed a large volume of general-purpose and high-quality MRC-style training data by using Wikipedia hyperlinks and designed a Wiki Anchor Extraction task to guide the MRC-style pre-training. Apart from its simplicity, PMR effectively solves extraction tasks, such as Extractive Question Answering and Named Entity Recognition. PMR shows tremendous improvements over existing approaches, especially in low-resource scenarios. When applied to the sequence classification task in the MRC formulation, PMR enables the extraction of high-quality rationales to explain the classification process, thereby providing greater prediction explainability. PMR also has the potential to serve as a unified model for tackling various extraction and classification tasks in the MRC formulation.
Machine reading comprehension (MRC) is a long-standing topic in natural language processing (NLP). The MRC task aims to answer a question based on the given context. Recently studies focus on multi-hop MRC which is a more challenging extension of MRC, which to answer a question some disjoint pieces of information across the context are required. Due to the complexity and importance of multi-hop MRC, a large number of studies have been focused on this topic in recent years, therefore, it is necessary and worth reviewing the related literature. This study aims to investigate recent advances in the multi-hop MRC approaches based on 31 studies from 2018 to 2022. In this regard, first, the multi-hop MRC problem definition will be introduced, then 31 models will be reviewed in detail with a strong focus on their multi-hop aspects. They also will be categorized based on their main techniques. Finally, a fine-grain comprehensive comparison of the models and techniques will be presented.
Multi-hop Machine reading comprehension is a challenging task with aim of answering a question based on disjoint pieces of information across the different passages. The evaluation metrics and datasets are a vital part of multi-hop MRC because it is not possible to train and evaluate models without them, also, the proposed challenges by datasets often are an important motivation for improving the existing models. Due to increasing attention to this field, it is necessary and worth reviewing them in detail. This study aims to present a comprehensive survey on recent advances in multi-hop MRC evaluation metrics and datasets. In this regard, first, the multi-hop MRC problem definition will be presented, then the evaluation metrics based on their multi-hop aspect will be investigated. Also, 15 multi-hop datasets have been reviewed in detail from 2017 to 2022, and a comprehensive analysis has been prepared at the end. Finally, open issues in this field have been discussed.
We introduce GENIUS: a conditional text generation model using sketches as input, which can fill in the missing contexts for a given sketch (key information consisting of textual spans, phrases, or words, concatenated by mask tokens). GENIUS is pre-trained on a large-scale textual corpus with a novel reconstruction from sketch objective using an extreme and selective masking strategy, enabling it to generate diverse and high-quality texts given sketches. Comparison with other competitive conditional language models (CLMs) reveals the superiority of GENIUS's text generation quality. We further show that GENIUS can be used as a strong and ready-to-use data augmentation tool for various natural language processing (NLP) tasks. Most existing textual data augmentation methods are either too conservative, by making small changes to the original text, or too aggressive, by creating entirely new samples. With GENIUS, we propose GeniusAug, which first extracts the target-aware sketches from the original training set and then generates new samples based on the sketches. Empirical experiments on 6 text classification datasets show that GeniusAug significantly improves the models' performance in both in-distribution (ID) and out-of-distribution (OOD) settings. We also demonstrate the effectiveness of GeniusAug on named entity recognition (NER) and machine reading comprehension (MRC) tasks. (Code and models are publicly available at https://github.com/microsoft/SCGLab and https://github.com/beyondguo/genius)
While most successful approaches for machine reading comprehension rely on single training objective, it is assumed that the encoder layer can learn great representation through the loss function we define in the predict layer, which is cross entropy in most of time, in the case that we first use neural networks to encode the question and paragraph, then directly fuse the encoding result of them. However, due to the distantly loss backpropagating in reading comprehension, the encoder layer cannot learn effectively and be directly supervised. Thus, the encoder layer can not learn the representation well at any time. Base on this, we propose to inject multi granularity information to the encoding layer. Experiments demonstrate the effect of adding multi granularity information to the encoding layer can boost the performance of machine reading comprehension system. Finally, empirical study shows that our approach can be applied to many existing MRC models.
Machine Reading Comprehension (MRC) has become one of the essential tasks in Natural Language Understanding (NLU) as it is often included in several NLU benchmarks (Liang et al., 2020; Wilie et al., 2020). However, most MRC datasets only have answerable question type, overlooking the importance of unanswerable questions. MRC models trained only on answerable questions will select the span that is most likely to be the answer, even when the answer does not actually exist in the given passage (Rajpurkar et al., 2018). This problem especially remains in medium- to low-resource languages like Indonesian. Existing Indonesian MRC datasets (Purwarianti et al., 2007; Clark et al., 2020) are still inadequate because of the small size and limited question types, i.e., they only cover answerable questions. To fill this gap, we build a new Indonesian MRC dataset called I(n)don'tKnow- MRC (IDK-MRC) by combining the automatic and manual unanswerable question generation to minimize the cost of manual dataset construction while maintaining the dataset quality. Combined with the existing answerable questions, IDK-MRC consists of more than 10K questions in total. Our analysis shows that our dataset significantly improves the performance of Indonesian MRC models, showing a large improvement for unanswerable questions.
This paper describes NEREL-BIO -- an annotation scheme and corpus of PubMed abstracts in Russian and smaller number of abstracts in English. NEREL-BIO extends the general domain dataset NEREL by introducing domain-specific entity types. NEREL-BIO annotation scheme covers both general and biomedical domains making it suitable for domain transfer experiments. NEREL-BIO provides annotation for nested named entities as an extension of the scheme employed for NEREL. Nested named entities may cross entity boundaries to connect to shorter entities nested within longer entities, making them harder to detect. NEREL-BIO contains annotations for 700+ Russian and 100+ English abstracts. All English PubMed annotations have corresponding Russian counterparts. Thus, NEREL-BIO comprises the following specific features: annotation of nested named entities, it can be used as a benchmark for cross-domain (NEREL -> NEREL-BIO) and cross-language (English -> Russian) transfer. We experiment with both transformer-based sequence models and machine reading comprehension (MRC) models and report their results. The dataset is freely available at https://github.com/nerel-ds/NEREL-BIO.
Prompt tuning is a parameter-efficient approach to adapting pre-trained language models to downstream tasks. Although prompt tuning has been shown to match the performance of full model tuning when training data is sufficient, it tends to struggle in few-shot learning settings. In this paper, we present Multi-task Pre-trained Modular Prompt (MP2) to boost prompt tuning for few-shot learning. MP2 is a set of combinable prompts pre-trained on 38 Chinese tasks. On downstream tasks, the pre-trained prompts are selectively activated and combined, leading to strong compositional generalization to unseen tasks. To bridge the gap between pre-training and fine-tuning, we formulate upstream and downstream tasks into a unified machine reading comprehension task. Extensive experiments under two learning paradigms, i.e., gradient descent and black-box tuning, show that MP2 significantly outperforms prompt tuning, full model tuning, and prior prompt pre-training methods in few-shot settings. In addition, we demonstrate that MP2 can achieve surprisingly fast and strong adaptation to downstream tasks by merely learning 8 parameters to combine the pre-trained modular prompts.