Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Faithful Temporal Question Answering over Heterogeneous Sources (2402.15400v1)

Published 23 Feb 2024 in cs.IR and cs.CL

Abstract: Temporal question answering (QA) involves time constraints, with phrases such as "... in 2019" or "... before COVID". In the former, time is an explicit condition, in the latter it is implicit. State-of-the-art methods have limitations along three dimensions. First, with neural inference, time constraints are merely soft-matched, giving room to invalid or inexplicable answers. Second, questions with implicit time are poorly supported. Third, answers come from a single source: either a knowledge base (KB) or a text corpus. We propose a temporal QA system that addresses these shortcomings. First, it enforces temporal constraints for faithful answering with tangible evidence. Second, it properly handles implicit questions. Third, it operates over heterogeneous sources, covering KB, text and web tables in a unified manner. The method has three stages: (i) understanding the question and its temporal conditions, (ii) retrieving evidence from all sources, and (iii) faithfully answering the question. As implicit questions are sparse in prior benchmarks, we introduce a principled method for generating diverse questions. Experiments show superior performance over a suite of baselines.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (65)
  1. Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering. In arXiv.
  2. Semantic Parsing on Freebase from Question-Answer Pairs. In EMNLP.
  3. Language Models are Few-Shot Learners. In NeurIPS.
  4. Temporal Knowledge Graph Completion: A Survey. In arXiv.
  5. Survey of Temporal Information Retrieval and Related Applications. ACM Computing Surveys (CSUR) (2014).
  6. Angel X. Chang and Christopher D. Manning. 2012. SUTime: A Library for Recognizing and Normalizing Time Expressions. In LREC.
  7. Reading Wikipedia to Answer Open-Domain Questions. In ACL.
  8. Open Question Answering over Tables and Text. In ICLR.
  9. A Dataset for Answering Time-Sensitive Questions. In NeurIPS.
  10. Temporal Knowledge Graph Question Qnswering via Subgraph Reasoning. Knowledge-Based Systems (2022).
  11. Beyond NED: Fast and Effective Search Space Reduction for Complex Question Answering over Knowledge Bases. In WSDM.
  12. Conversational Question Answering on Heterogeneous Sources. In SIGIR.
  13. Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks. In SIGIR.
  14. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL.
  15. Time-Aware Language Models as Temporal Knowledge Bases. In TACL.
  16. Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs. In EMNLP.
  17. Paolo Ferragina and Ugo Scaiella. 2010. TAGME: On-the-fly Annotation of Short Text Fragments (by Wikipedia Entities). In CIKM.
  18. David A. Ferrucci. 2012. Introduction to ”This is Watson”. IBM Journal of Research and Development (2012).
  19. Learning Sequence Encoders for Temporal Knowledge Graph Completion. In EMNLP.
  20. Qsearch: Answering Quantity Queries from Text. In ISWC.
  21. Gautier Izacard and Édouard Grave. 2021. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. In EACL.
  22. TempQuestions: A Benchmark for Temporal Question Answering. In HQA@WWW.
  23. TEQUILA: Temporal Question Answering over Knowledge Bases. In CIKM.
  24. Complex Temporal Question Answering on Knowledge Graphs. In CIKM.
  25. An Improving Reasoning Network for Complex Question Answering over Temporal Knowledge Graphs. In Applied Intelligence. Springer.
  26. Julien Leblay and Melisachew Wudage Chekol. 2018. Deriving Validity Time in Knowledge Graph. In TempWeb@WWW.
  27. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL.
  28. Complex Question Answering Over Temporal Knowledge Graphs. In WISE.
  29. Open Domain Question Answering with A Unified Knowledge Interface. In ACL.
  30. When not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories. In ACL.
  31. TempoQR: Temporal Question Reasoning over Knowledge Graphs. In AAAI.
  32. Temporal Knowledge Graph Completion Using Box Embeddings. In AAAI.
  33. FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation. In EMNLP.
  34. SYGMA: System for Generalizable Modular Question Answering over Knowledge Bases. In Findings of the Association for Computational Linguistics: EMNLP.
  35. TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions. In EMNLP.
  36. Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. In arXiv.
  37. OpenAI. 2023. GPT-4 Technical Report. In arXiv.
  38. UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering. In NAACL-HLT.
  39. Training Language Models to Follow Instructions with Human Feedback. In NeurIPS.
  40. Evokg: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphs. In WSDM.
  41. Language Models as Knowledge Bases?. In EMNLP-IJCNLP.
  42. UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text. In arXiv.
  43. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. In JMLR.
  44. SQuAD: 100,000+ Questions for Machine Comprehension of Text. In EMNLP.
  45. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In EMNLP.
  46. Rishiraj Saha Roy and Avishek Anand. 2022. Question Answering for the Curated Web: Tasks and Methods in QA over Knowledge Bases and Text Collections. Springer.
  47. Denis Savenkov and Eugene Agichtein. 2016. When a Knowledge Base Is Not Enough: Question Answering over Knowledge Bases with External Text Data. In SIGIR.
  48. Question Answering Over Temporal Knowledge Graphs. In ACL.
  49. Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs. In ACL.
  50. TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs. In EACL.
  51. PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text. In EMNLP-IJCNLP.
  52. Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text. In EMNLP.
  53. Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models. In ACL.
  54. Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks. In arXiv.
  55. Denny Vrandečić and Markus Krötzsch. 2014. Wikidata: A Free Collaborative Knowledgebase. CACM (2014).
  56. TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion. In EMNLP.
  57. Introducing External Knowledge to Answer Questions with Implicit Temporal Constraints over Knowledge Base. Future Internet (2020).
  58. Modeling Temporal-Sensitive Information for Complex Question Answering over Knowledge Graphs. In NLPCC.
  59. Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings. In NAACL.
  60. Hybrid Question Answering over Knowledge Base and Free Text. In COLING.
  61. Question Answering on Freebase via Relation Extraction and Textual Evidence. In ACL.
  62. Natural Language Questions for the Web of Data. In EMNLP.
  63. TERQA: Question Answering over Knowledge Graph Considering Precise Dependencies of Temporal Information on Vectors. Displays (2022).
  64. Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base. In ACL-IJCNLP.
  65. Learning Recurrent Event Queries for Web Search. In EMNLP.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Zhen Jia (34 papers)
  2. Philipp Christmann (9 papers)
  3. Gerhard Weikum (75 papers)
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now