Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference (2404.02625v1)

Published 3 Apr 2024 in cs.CL, cs.AI, and cs.LG

Abstract: Integer Linear Programming (ILP) has been proposed as a formalism for encoding precise structural and semantic constraints for Natural Language Inference (NLI). However, traditional ILP frameworks are non-differentiable, posing critical challenges for the integration of continuous language representations based on deep learning. In this paper, we introduce a novel approach, named Diff-Comb Explainer, a neuro-symbolic architecture for explanation-based NLI based on Differentiable BlackBox Combinatorial Solvers (DBCS). Differently from existing neuro-symbolic solvers, Diff-Comb Explainer does not necessitate a continuous relaxation of the semantic constraints, enabling a direct, more precise, and efficient incorporation of neural representations into the ILP formulation. Our experiments demonstrate that Diff-Comb Explainer achieves superior performance when compared to conventional ILP solvers, neuro-symbolic black-box solvers, and Transformer-based encoders. Moreover, a deeper analysis reveals that Diff-Comb Explainer can significantly improve the precision, consistency, and faithfulness of the constructed explanations, opening new opportunities for research on neuro-symbolic architectures for explainable and transparent NLI in complex domains.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (30)
  1. Differentiable convex optimization layers. In Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc.
  2. Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457.
  3. Combining retrieval, statistics, and inference to answer elementary science questions. In AAAI, pages 2580–2586. Citeseer.
  4. Transformers as soft reasoners over language. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pages 3882–3890.
  5. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186.
  6. Worldtree: A corpus of explanation graphs for elementary science questions supporting multi-hop inference. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018).
  7. Billion-scale similarity search with gpus. CoRR, abs/1702.08734.
  8. Question answering via integer programming over semi-structured knowledge. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pages 1145–1152.
  9. Question answering as global reasoning over semantic abstractions. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32.
  10. Unifiedqa: Crossing format boundaries with a single qa system. arXiv preprint arXiv:2005.00700.
  11. Answering complex questions using open information extraction. arXiv preprint arXiv:1704.05572.
  12. Exploiting explicit paths for multi-hop reading comprehension. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2737–2747, Florence, Italy. Association for Computational Linguistics.
  13. L. Lovász and A. Schrijver. 1991. Cones of matrices and set-functions and 0-1 optimization. SIAM JOURNAL ON OPTIMIZATION, 1:166–190.
  14. Learning to attend on essential terms: An enhanced retriever-reader model for open-domain question answering. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 335–344.
  15. Comboptnet: Fit the right np-hard problem by learning integer programming constraints. In International Conference on Machine Learning, pages 8443–8453. PMLR.
  16. Differentiation of blackbox combinatorial solvers. In International Conference on Learning Representations.
  17. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
  18. Prover: Proof generation for interpretable reasoning over rules. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 122–136.
  19. multiprover: Generating multiple proofs for improved interpretability in rule reasoning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3662–3677.
  20. Conceptnet 5.5: An open multilingual graph of general knowledge. In Thirty-first AAAI conference on artificial intelligence.
  21. Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference. Transactions of the Association for Computational Linguistics, 10:1103–1a119.
  22. A survey on explainability in machine reading comprehension. arXiv preprint arXiv:2010.00389.
  23. Explainable inference over grounding-abstract chains for science questions. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1–12.
  24. Hybrid autoregressive inference for scalable multi-hop explanation regeneration. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 11403–11411.
  25. Unification-based reconstruction of multi-hop explanations for science questions. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 200–211.
  26. Huggingface’s transformers: State-of-the-art natural language processing. CoRR, abs/1910.03771.
  27. Worldtree v2: A corpus of science-domain structured explanations and inference patterns supporting multi-hop inference. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 5456–5473.
  28. Alignment over heterogeneous embeddings for question answering. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2681–2691.
  29. Quick and (not so) dirty: Unsupervised selection of justification sentences for multi-hop question answering. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2578–2589, Hong Kong, China. Association for Computational Linguistics.
  30. Kg^ 2: Learning to reason science exam questions with contextual knowledge graph embeddings. arXiv preprint arXiv:1805.12393.

Summary

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