pith. sign in

arxiv: 1706.04115 · v1 · pith:ZACK35QAnew · submitted 2017-06-13 · 💻 cs.CL · cs.AI· cs.LG

Zero-Shot Relation Extraction via Reading Comprehension

classification 💻 cs.CL cs.AIcs.LG
keywords relationquestionstypeszero-shotaccuracycomprehensionextractionmodels
0
0 comments X
read the original abstract

We show that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot. This reduction has several advantages: we can (1) learn relation-extraction models by extending recent neural reading-comprehension techniques, (2) build very large training sets for those models by combining relation-specific crowd-sourced questions with distant supervision, and even (3) do zero-shot learning by extracting new relation types that are only specified at test-time, for which we have no labeled training examples. Experiments on a Wikipedia slot-filling task demonstrate that the approach can generalize to new questions for known relation types with high accuracy, and that zero-shot generalization to unseen relation types is possible, at lower accuracy levels, setting the bar for future work on this task.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing

    cs.LG 2026-05 unverdicted novelty 6.0

    HoReN achieves stable sequential editing of 50K facts in LLMs by combining a normalized Hopfield codebook with angular retrieval and attractor dynamics.

  2. ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models

    cs.LG 2026-05 unverdicted novelty 5.0

    ZeroUnlearn is a few-shot unlearning method that maps sensitive inputs to neutral states and enforces representational orthogonality through a closed-form multiplicative update, outperforming baselines while preservin...

  3. ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models

    cs.LG 2026-05 unverdicted novelty 5.0

    ZeroUnlearn is a few-shot unlearning method that overwrites sensitive inputs with neutral targets via closed-form multiplicative parameter updates enforcing representational orthogonality in LLMs.

  4. HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing

    cs.LG 2026-05 unverdicted novelty 5.0

    HoReN is a parameter-preserving editor that wraps an MLP with a Hopfield codebook memory and scales to 50K sequential edits on ZsRE while maintaining performance above 0.93.

  5. Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression

    cs.AI 2026-04 unverdicted novelty 5.0

    LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing tr...

  6. EQuANt (Enhanced Question Answer Network)

    cs.CL 2019-06 unverdicted novelty 4.0

    EQuANt extends QANet to SQuAD 2, achieving nearly twice the performance of a lightweight QANet baseline while also improving SQuAD 1.1 results via multi-task learning.

  7. Retrieval-Augmented Generation for Large Language Models: A Survey

    cs.CL 2023-12 unverdicted novelty 3.0

    A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.

  8. Machine Reading Comprehension: a Literature Review

    cs.CL 2019-06 unverdicted novelty 1.0

    A 2019 survey of machine reading comprehension corpora and methods.