Pub Date : 2022-11-23DOI: 10.48550/arXiv.2211.12835
K. Shridhar, Jakub Macina, Mennatallah El-Assady, Tanmay Sinha, Manu Kapur, Mrinmaya Sachan
Socratic questioning is an educational method that allows students to discover answers to complex problems by asking them a series of thoughtful questions. Generation of didactically sound questions is challenging, requiring understanding of the reasoning process involved in the problem. We hypothesize that such questioning strategy can not only enhance the human performance, but also assist the math word problem (MWP) solvers.In this work, we explore the ability of large language models (LMs) in generating sequential questions for guiding math word problem-solving. We propose various guided question generation schemes based on input conditioning and reinforcement learning.On both automatic and human quality evaluations, we find that LMs constrained with desirable question properties generate superior questions and improve the overall performance of a math word problem solver. We conduct a preliminary user study to examine the potential value of such question generation models in the education domain. Results suggest that the difficulty level of problems plays an important role in determining whether questioning improves or hinders human performance. We discuss the future of using such questioning strategies in education.
{"title":"Automatic Generation of Socratic Subquestions for Teaching Math Word Problems","authors":"K. Shridhar, Jakub Macina, Mennatallah El-Assady, Tanmay Sinha, Manu Kapur, Mrinmaya Sachan","doi":"10.48550/arXiv.2211.12835","DOIUrl":"https://doi.org/10.48550/arXiv.2211.12835","url":null,"abstract":"Socratic questioning is an educational method that allows students to discover answers to complex problems by asking them a series of thoughtful questions. Generation of didactically sound questions is challenging, requiring understanding of the reasoning process involved in the problem. We hypothesize that such questioning strategy can not only enhance the human performance, but also assist the math word problem (MWP) solvers.In this work, we explore the ability of large language models (LMs) in generating sequential questions for guiding math word problem-solving. We propose various guided question generation schemes based on input conditioning and reinforcement learning.On both automatic and human quality evaluations, we find that LMs constrained with desirable question properties generate superior questions and improve the overall performance of a math word problem solver. We conduct a preliminary user study to examine the potential value of such question generation models in the education domain. Results suggest that the difficulty level of problems plays an important role in determining whether questioning improves or hinders human performance. We discuss the future of using such questioning strategies in education.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"83 1","pages":"4136-4149"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89884272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-23DOI: 10.48550/arXiv.2211.12641
Aashna Jena, Vivek Gupta, Manish Shrivastava, Julian Martin Eisenschlos
Creating challenging tabular inference data is essential for learning complex reasoning. Prior work has mostly relied on two data generation strategies. The first is human annotation, which yields linguistically diverse data but is difficult to scale. The second category for creation is synthetic generation, which is scalable and cost effective but lacks inventiveness. In this research, we present a framework for semi-automatically recasting existing tabular data to make use of the benefits of both approaches. We utilize our framework to build tabular NLI instances from five datasets that were initially intended for tasks like table2text creation, tabular Q/A, and semantic parsing. We demonstrate that recasted data could be used as evaluation benchmarks as well as augmentation data to enhance performance on tabular NLI tasks. Furthermore, we investigate the effectiveness of models trained on recasted data in the zero-shot scenario, and analyse trends in performance across different recasted datasets types.
{"title":"Leveraging Data Recasting to Enhance Tabular Reasoning","authors":"Aashna Jena, Vivek Gupta, Manish Shrivastava, Julian Martin Eisenschlos","doi":"10.48550/arXiv.2211.12641","DOIUrl":"https://doi.org/10.48550/arXiv.2211.12641","url":null,"abstract":"Creating challenging tabular inference data is essential for learning complex reasoning. Prior work has mostly relied on two data generation strategies. The first is human annotation, which yields linguistically diverse data but is difficult to scale. The second category for creation is synthetic generation, which is scalable and cost effective but lacks inventiveness. In this research, we present a framework for semi-automatically recasting existing tabular data to make use of the benefits of both approaches. We utilize our framework to build tabular NLI instances from five datasets that were initially intended for tasks like table2text creation, tabular Q/A, and semantic parsing. We demonstrate that recasted data could be used as evaluation benchmarks as well as augmentation data to enhance performance on tabular NLI tasks. Furthermore, we investigate the effectiveness of models trained on recasted data in the zero-shot scenario, and analyse trends in performance across different recasted datasets types.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"54 1","pages":"4483-4496"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86057949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-23DOI: 10.48550/arXiv.2211.13252
Kai Shen, Yichong Leng, Xuejiao Tan, Si-Qi Tang, Yuan Zhang, Wenjie Liu, Ed Lin
Text error correction aims to correct the errors in text sequences such as those typed by humans or generated by speech recognition models.Previous error correction methods usually take the source (incorrect) sentence as encoder input and generate the target (correct) sentence through the decoder. Since the error rate of the incorrect sentence is usually low (e.g., 10%), the correction model can only learn to correct on limited error tokens but trivially copy on most tokens (correct tokens), which harms the effective training of error correction. In this paper, we argue that the correct tokens should be better utilized to facilitate effective training and then propose a simple yet effective masking strategy to achieve this goal.Specifically, we randomly mask out a part of the correct tokens in the source sentence and let the model learn to not only correct the original error tokens but also predict the masked tokens based on their context information. Our method enjoys several advantages: 1) it alleviates trivial copy; 2) it leverages effective training signals from correct tokens; 3) it is a plug-and-play module and can be applied to different models and tasks. Experiments on spelling error correction and speech recognition error correction on Mandarin datasets and grammar error correction on English datasets with both autoregressive and non-autoregressive generation models show that our method improves the correctionaccuracy consistently.
{"title":"Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction","authors":"Kai Shen, Yichong Leng, Xuejiao Tan, Si-Qi Tang, Yuan Zhang, Wenjie Liu, Ed Lin","doi":"10.48550/arXiv.2211.13252","DOIUrl":"https://doi.org/10.48550/arXiv.2211.13252","url":null,"abstract":"Text error correction aims to correct the errors in text sequences such as those typed by humans or generated by speech recognition models.Previous error correction methods usually take the source (incorrect) sentence as encoder input and generate the target (correct) sentence through the decoder. Since the error rate of the incorrect sentence is usually low (e.g., 10%), the correction model can only learn to correct on limited error tokens but trivially copy on most tokens (correct tokens), which harms the effective training of error correction. In this paper, we argue that the correct tokens should be better utilized to facilitate effective training and then propose a simple yet effective masking strategy to achieve this goal.Specifically, we randomly mask out a part of the correct tokens in the source sentence and let the model learn to not only correct the original error tokens but also predict the masked tokens based on their context information. Our method enjoys several advantages: 1) it alleviates trivial copy; 2) it leverages effective training signals from correct tokens; 3) it is a plug-and-play module and can be applied to different models and tasks. Experiments on spelling error correction and speech recognition error correction on Mandarin datasets and grammar error correction on English datasets with both autoregressive and non-autoregressive generation models show that our method improves the correctionaccuracy consistently.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"17 1","pages":"10367-10380"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82015323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-21DOI: 10.48550/arXiv.2211.11875
E. Mitchell, Joseph J. Noh, Siyan Li, William S. Armstrong, Ananth Agarwal, Patrick Liu, Chelsea Finn, Christopher D. Manning
While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs. For example, a state-of-the-art Macaw question-answering (QA) model answers Yes to Is a sparrow a bird? and Does a bird have feet? but answers No to Does a sparrow have feet?. To address this failure mode, we propose a framework, Consistency Correction through Relation Detection, or ConCoRD, for boosting the consistency and accuracy of pre-trained NLP models using pre-trained natural language inference (NLI) models without fine-tuning or re-training. Given a batch of test inputs, ConCoRD samples several candidate outputs for each input and instantiates a factor graph that accounts for both the model’s belief about the likelihood of each answer choice in isolation and the NLI model’s beliefs about pair-wise answer choice compatibility. We show that a weighted MaxSAT solver can efficiently compute high-quality answer choices under this factor graph, improving over the raw model’s predictions. Our experiments demonstrate that ConCoRD consistently boosts accuracy and consistency of off-the-shelf closed-book QA and VQA models using off-the-shelf NLI models, notably increasing accuracy of LXMERT on ConVQA by 5% absolute. See the project website (https://ericmitchell.ai/emnlp-2022-concord/) for code and data.
{"title":"Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference","authors":"E. Mitchell, Joseph J. Noh, Siyan Li, William S. Armstrong, Ananth Agarwal, Patrick Liu, Chelsea Finn, Christopher D. Manning","doi":"10.48550/arXiv.2211.11875","DOIUrl":"https://doi.org/10.48550/arXiv.2211.11875","url":null,"abstract":"While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs. For example, a state-of-the-art Macaw question-answering (QA) model answers Yes to Is a sparrow a bird? and Does a bird have feet? but answers No to Does a sparrow have feet?. To address this failure mode, we propose a framework, Consistency Correction through Relation Detection, or ConCoRD, for boosting the consistency and accuracy of pre-trained NLP models using pre-trained natural language inference (NLI) models without fine-tuning or re-training. Given a batch of test inputs, ConCoRD samples several candidate outputs for each input and instantiates a factor graph that accounts for both the model’s belief about the likelihood of each answer choice in isolation and the NLI model’s beliefs about pair-wise answer choice compatibility. We show that a weighted MaxSAT solver can efficiently compute high-quality answer choices under this factor graph, improving over the raw model’s predictions. Our experiments demonstrate that ConCoRD consistently boosts accuracy and consistency of off-the-shelf closed-book QA and VQA models using off-the-shelf NLI models, notably increasing accuracy of LXMERT on ConVQA by 5% absolute. See the project website (https://ericmitchell.ai/emnlp-2022-concord/) for code and data.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"10 1","pages":"1754-1768"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79094445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-21DOI: 10.48550/arXiv.2211.11256
Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, Yongbin Li
Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors. From a psychological perspective, emotions are the expression of affect or feelings during a short period, while sentiments are formed and held for a longer period. However, most existing works study sentiment and emotion separately and do not fully exploit the complementary knowledge behind the two. In this paper, we propose a multimodal sentiment knowledge-sharing framework (UniMSE) that unifies MSA and ERC tasks from features, labels, and models. We perform modality fusion at the syntactic and semantic levels and introduce contrastive learning between modalities and samples to better capture the difference and consistency between sentiments and emotions. Experiments on four public benchmark datasets, MOSI, MOSEI, MELD, and IEMOCAP, demonstrate the effectiveness of the proposed method and achieve consistent improvements compared with state-of-the-art methods.
{"title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","authors":"Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, Yongbin Li","doi":"10.48550/arXiv.2211.11256","DOIUrl":"https://doi.org/10.48550/arXiv.2211.11256","url":null,"abstract":"Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors. From a psychological perspective, emotions are the expression of affect or feelings during a short period, while sentiments are formed and held for a longer period. However, most existing works study sentiment and emotion separately and do not fully exploit the complementary knowledge behind the two. In this paper, we propose a multimodal sentiment knowledge-sharing framework (UniMSE) that unifies MSA and ERC tasks from features, labels, and models. We perform modality fusion at the syntactic and semantic levels and introduce contrastive learning between modalities and samples to better capture the difference and consistency between sentiments and emotions. Experiments on four public benchmark datasets, MOSI, MOSEI, MELD, and IEMOCAP, demonstrate the effectiveness of the proposed method and achieve consistent improvements compared with state-of-the-art methods.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"44 21","pages":"7837-7851"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91402216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-21DOI: 10.48550/arXiv.2211.11902
Hyeongdon Moon, Yoonseok Yang, Jamin Shin, Hangyeol Yu, Seunghyun Lee, Myeongho Jeong, Juneyoung Park, Minsam Kim, Seungtaek Choi
The automatic generation of Multiple Choice Questions (MCQ) has the potential to reduce the time educators spend on student assessment significantly. However, existing evaluation metrics for MCQ generation, such as BLEU, ROUGE, and METEOR, focus on the n-gram based similarity of the generated MCQ to the gold sample in the dataset and disregard their educational value.They fail to evaluate the MCQ’s ability to assess the student’s knowledge of the corresponding target fact. To tackle this issue, we propose a novel automatic evaluation metric, coined Knowledge Dependent Answerability (KDA), which measures the MCQ’s answerability given knowledge of the target fact. Specifically, we first show how to measure KDA based on student responses from a human survey.Then, we propose two automatic evaluation metrics, KDA_disc and KDA_cont, that approximate KDA by leveraging pre-trained language models to imitate students’ problem-solving behavior.Through our human studies, we show that KDA_disc and KDA_soft have strong correlations with both (1) KDA and (2) usability in an actual classroom setting, labeled by experts. Furthermore, when combined with n-gram based similarity metrics, KDA_disc and KDA_cont are shown to have a strong predictive power for various expert-labeled MCQ quality measures.
{"title":"Evaluating the Knowledge Dependency of Questions","authors":"Hyeongdon Moon, Yoonseok Yang, Jamin Shin, Hangyeol Yu, Seunghyun Lee, Myeongho Jeong, Juneyoung Park, Minsam Kim, Seungtaek Choi","doi":"10.48550/arXiv.2211.11902","DOIUrl":"https://doi.org/10.48550/arXiv.2211.11902","url":null,"abstract":"The automatic generation of Multiple Choice Questions (MCQ) has the potential to reduce the time educators spend on student assessment significantly. However, existing evaluation metrics for MCQ generation, such as BLEU, ROUGE, and METEOR, focus on the n-gram based similarity of the generated MCQ to the gold sample in the dataset and disregard their educational value.They fail to evaluate the MCQ’s ability to assess the student’s knowledge of the corresponding target fact. To tackle this issue, we propose a novel automatic evaluation metric, coined Knowledge Dependent Answerability (KDA), which measures the MCQ’s answerability given knowledge of the target fact. Specifically, we first show how to measure KDA based on student responses from a human survey.Then, we propose two automatic evaluation metrics, KDA_disc and KDA_cont, that approximate KDA by leveraging pre-trained language models to imitate students’ problem-solving behavior.Through our human studies, we show that KDA_disc and KDA_soft have strong correlations with both (1) KDA and (2) usability in an actual classroom setting, labeled by experts. Furthermore, when combined with n-gram based similarity metrics, KDA_disc and KDA_cont are shown to have a strong predictive power for various expert-labeled MCQ quality measures.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"19 1","pages":"10512-10526"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82754187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-21DOI: 10.48550/arXiv.2211.11617
Yinpei Dai, Wanwei He, Bowen Li, Yuchuan Wu, Zhen Cao, Zhongqi An, Jian Sun, Yongbin Li
Practical dialog systems need to deal with various knowledge sources, noisy user expressions, and the shortage of annotated data. To better solve the above problems, we propose CGoDial, a new challenging and comprehensive Chinese benchmark for multi-domain Goal-oriented Dialog evaluation. It contains 96,763 dialog sessions, and 574,949 dialog turns totally, covering three datasets with different knowledge sources: 1) a slot-based dialog (SBD) dataset with table-formed knowledge, 2) a flow-based dialog (FBD) dataset with tree-formed knowledge, and a retrieval-based dialog (RBD) dataset with candidate-formed knowledge. To bridge the gap between academic benchmarks and spoken dialog scenarios, we either collect data from real conversations or add spoken features to existing datasets via crowd-sourcing. The proposed experimental settings include the combinations of training with either the entire training set or a few-shot training set, and testing with either the standard test set or a hard test subset, which can assess model capabilities in terms of general prediction, fast adaptability and reliable robustness.
{"title":"CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation","authors":"Yinpei Dai, Wanwei He, Bowen Li, Yuchuan Wu, Zhen Cao, Zhongqi An, Jian Sun, Yongbin Li","doi":"10.48550/arXiv.2211.11617","DOIUrl":"https://doi.org/10.48550/arXiv.2211.11617","url":null,"abstract":"Practical dialog systems need to deal with various knowledge sources, noisy user expressions, and the shortage of annotated data. To better solve the above problems, we propose CGoDial, a new challenging and comprehensive Chinese benchmark for multi-domain Goal-oriented Dialog evaluation. It contains 96,763 dialog sessions, and 574,949 dialog turns totally, covering three datasets with different knowledge sources: 1) a slot-based dialog (SBD) dataset with table-formed knowledge, 2) a flow-based dialog (FBD) dataset with tree-formed knowledge, and a retrieval-based dialog (RBD) dataset with candidate-formed knowledge. To bridge the gap between academic benchmarks and spoken dialog scenarios, we either collect data from real conversations or add spoken features to existing datasets via crowd-sourcing. The proposed experimental settings include the combinations of training with either the entire training set or a few-shot training set, and testing with either the standard test set or a hard test subset, which can assess model capabilities in terms of general prediction, fast adaptability and reliable robustness.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"182 1","pages":"4097-4111"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82689420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-18DOI: 10.48550/arXiv.2211.10243
Zhihao Du, Shiliang Zhang, Siqi Zheng, Zhijie Yan
Recently, hybrid systems of clustering and neural diarization models have been successfully applied in multi-party meeting analysis. However, current models always treat overlapped speaker diarization as a multi-label classification problem, where speaker dependency and overlaps are not well considered. To overcome the disadvantages, we reformulate overlapped speaker diarization task as a single-label prediction problem via the proposed power set encoding (PSE). Through this formulation, speaker dependency and overlaps can be explicitly modeled. To fully leverage this formulation, we further propose the speaker overlap-aware neural diarization (SOND) model, which consists of a context-independent (CI) scorer to model global speaker discriminability, a context-dependent scorer (CD) to model local discriminability, and a speaker combining network (SCN) to combine and reassign speaker activities. Experimental results show that using the proposed formulation can outperform the state-of-the-art methods based on target speaker voice activity detection, and the performance can be further improved with SOND, resulting in a 6.30% relative diarization error reduction.
{"title":"Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis","authors":"Zhihao Du, Shiliang Zhang, Siqi Zheng, Zhijie Yan","doi":"10.48550/arXiv.2211.10243","DOIUrl":"https://doi.org/10.48550/arXiv.2211.10243","url":null,"abstract":"Recently, hybrid systems of clustering and neural diarization models have been successfully applied in multi-party meeting analysis. However, current models always treat overlapped speaker diarization as a multi-label classification problem, where speaker dependency and overlaps are not well considered. To overcome the disadvantages, we reformulate overlapped speaker diarization task as a single-label prediction problem via the proposed power set encoding (PSE). Through this formulation, speaker dependency and overlaps can be explicitly modeled. To fully leverage this formulation, we further propose the speaker overlap-aware neural diarization (SOND) model, which consists of a context-independent (CI) scorer to model global speaker discriminability, a context-dependent scorer (CD) to model local discriminability, and a speaker combining network (SCN) to combine and reassign speaker activities. Experimental results show that using the proposed formulation can outperform the state-of-the-art methods based on target speaker voice activity detection, and the performance can be further improved with SOND, resulting in a 6.30% relative diarization error reduction.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"112 1","pages":"7458-7469"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80173916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-18DOI: 10.48550/arXiv.2211.10018
Yew Ken Chia, Lidong Bing, Sharifah Mahani Aljunied, Luo Si, Soujanya Poria
Relation extraction has the potential for large-scale knowledge graph construction, but current methods do not consider the qualifier attributes for each relation triplet, such as time, quantity or location. The qualifiers form hyper-relational facts which better capture the rich and complex knowledge graph structure. For example, the relation triplet (Leonard Parker, Educated At, Harvard University) can be factually enriched by including the qualifier (End Time, 1967). Hence, we propose the task of hyper-relational extraction to extract more specific and complete facts from text. To support the task, we construct HyperRED, a large-scale and general-purpose dataset. Existing models cannot perform hyper-relational extraction as it requires a model to consider the interaction between three entities. Hence, we propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers. To improve model scalability and reduce negative class imbalance, we further propose a cube-pruning method. Our experiments show that CubeRE outperforms strong baselines and reveal possible directions for future research. Our code and data are available at github.com/declare-lab/HyperRED.
关系提取具有构建大规模知识图谱的潜力，但目前的方法没有考虑每个关系三元组的限定词属性，如时间、数量或位置。限定词形成超关系事实，可以更好地捕获丰富而复杂的知识图谱结构。例如，关系三元组(Leonard Parker, educate At, Harvard University)可以通过包含限定词(End Time, 1967)来丰富事实。因此，我们提出了超关系提取的任务，以从文本中提取更具体和完整的事实。为了支持这项任务，我们构建了HyperRED，一个大规模的通用数据集。现有模型不能执行超关系提取，因为它需要一个模型来考虑三个实体之间的交互。因此，我们提出了CubeRE，这是一个受表填充方法启发的立方体填充模型，明确地考虑了关系三元组和限定符之间的相互作用。为了提高模型的可扩展性和减少负类不平衡，我们进一步提出了一种立方体剪枝方法。我们的实验表明，CubeRE优于强基线，并为未来的研究揭示了可能的方向。我们的代码和数据可在github.com/declare-lab/HyperRED上获得。
{"title":"A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach","authors":"Yew Ken Chia, Lidong Bing, Sharifah Mahani Aljunied, Luo Si, Soujanya Poria","doi":"10.48550/arXiv.2211.10018","DOIUrl":"https://doi.org/10.48550/arXiv.2211.10018","url":null,"abstract":"Relation extraction has the potential for large-scale knowledge graph construction, but current methods do not consider the qualifier attributes for each relation triplet, such as time, quantity or location. The qualifiers form hyper-relational facts which better capture the rich and complex knowledge graph structure. For example, the relation triplet (Leonard Parker, Educated At, Harvard University) can be factually enriched by including the qualifier (End Time, 1967). Hence, we propose the task of hyper-relational extraction to extract more specific and complete facts from text. To support the task, we construct HyperRED, a large-scale and general-purpose dataset. Existing models cannot perform hyper-relational extraction as it requires a model to consider the interaction between three entities. Hence, we propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers. To improve model scalability and reduce negative class imbalance, we further propose a cube-pruning method. Our experiments show that CubeRE outperforms strong baselines and reveal possible directions for future research. Our code and data are available at github.com/declare-lab/HyperRED.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"9 1","pages":"10114-10133"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81819812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-17DOI: 10.48550/arXiv.2211.09455
Aleksandar Savkov, Francesco Moramarco, Alex Papadopoulos Korfiatis, Mark Perera, Anya Belz, E. Reiter
Evaluating automatically generated text is generally hard due to the inherently subjective nature of many aspects of the output quality. This difficulty is compounded in automatic consultation note generation by differing opinions between medical experts both about which patient statements should be included in generated notes and about their respective importance in arriving at a diagnosis. Previous real-world evaluations of note-generation systems saw substantial disagreement between expert evaluators. In this paper we propose a protocol that aims to increase objectivity by grounding evaluations in Consultation Checklists, which are created in a preliminary step and then used as a common point of reference during quality assessment. We observed good levels of inter-annotator agreement in a first evaluation study using the protocol; further, using Consultation Checklists produced in the study as reference for automatic metrics such as ROUGE or BERTScore improves their correlation with human judgements compared to using the original human note.
{"title":"Consultation Checklists: Standardising the Human Evaluation of Medical Note Generation","authors":"Aleksandar Savkov, Francesco Moramarco, Alex Papadopoulos Korfiatis, Mark Perera, Anya Belz, E. Reiter","doi":"10.48550/arXiv.2211.09455","DOIUrl":"https://doi.org/10.48550/arXiv.2211.09455","url":null,"abstract":"Evaluating automatically generated text is generally hard due to the inherently subjective nature of many aspects of the output quality. This difficulty is compounded in automatic consultation note generation by differing opinions between medical experts both about which patient statements should be included in generated notes and about their respective importance in arriving at a diagnosis. Previous real-world evaluations of note-generation systems saw substantial disagreement between expert evaluators. In this paper we propose a protocol that aims to increase objectivity by grounding evaluations in Consultation Checklists, which are created in a preliminary step and then used as a common point of reference during quality assessment. We observed good levels of inter-annotator agreement in a first evaluation study using the protocol; further, using Consultation Checklists produced in the study as reference for automatic metrics such as ROUGE or BERTScore improves their correlation with human judgements compared to using the original human note.","PeriodicalId":74540,"journal":{"name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","volume":"19 1","pages":"111-120"},"PeriodicalIF":0.0,"publicationDate":"2022-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76622153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：