# Reasoning over Logically Interacted Conditions for Question Answering

arXiv: https://arxiv.org/abs/2205.12898 · HTML: https://mlsanity.com/paper/2205.12898/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 25 May 2022.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings](https://mlsanity.com/paper/2002.05969/) (2020)
- [A Dataset for Answering Time-Sensitive Questions](https://mlsanity.com/paper/2108.06314/) (2021)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs](https://mlsanity.com/paper/2010.11465/) (2020)
- [Interpretation of Natural Language Rules in Conversational Machine Reading](https://mlsanity.com/paper/1809.01494/) (2018)
- [ETC: Encoding Long and Structured Inputs in Transformers](https://mlsanity.com/paper/2004.08483/) (2020)
- [Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading](https://mlsanity.com/paper/2010.01838/) (2020)
- [Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base](https://mlsanity.com/paper/2002.06115/) (2020)
- [TensorLog: A Differentiable Deductive Database](https://mlsanity.com/paper/1605.06523/) (2016)
- [ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers](https://mlsanity.com/paper/2110.06884/) (2021)
- [Dialogue Graph Modeling for Conversational Machine Reading](https://mlsanity.com/paper/2012.14827/) (2020)
- [RuleBert: Teaching Soft Rules to Pre-trained Language Models](https://mlsanity.com/paper/2109.13006/) (2021)
- [E3: Entailment-driven Extracting and Editing for Conversational Machine Reading](https://mlsanity.com/paper/1906.05373/) (2019)
- [Attending to Future Tokens For Bidirectional Sequence Generation](https://mlsanity.com/paper/1908.05915/) (2019)
- [Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading](https://mlsanity.com/paper/2005.12484/) (2020)

## Built on by (most cited first, 3 of 3)

- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [Neuro-symbolic Training for Reasoning over Spatial Language](https://mlsanity.com/paper/2406.13828/) (2024)
- [Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering](https://mlsanity.com/paper/2408.05442/) (2024)

## Abstract (arXiv)

Some questions have multiple answers that are not equally correct, i.e. answers are different under different conditions. Conditions are used to distinguish answers as well as to provide additional information to support them. In this paper, we study a more challenging task where answers are constrained by a list of conditions that logically interact, which requires performing logical reasoning over the conditions to determine the correctness of the answers. Even more challenging, we only provide evidences for a subset of the conditions, so some questions may not have deterministic answers. In such cases, models are asked to find probable answers and identify conditions that need to be satisfied to make the answers correct. We propose a new model, TReasoner, for this challenging reasoning task. TReasoner consists of an entailment module, a reasoning module, and a generation module (if the answers are free-form text spans). TReasoner achieves state-of-the-art performance on two benchmark conditional QA datasets, outperforming the previous state-of-the-art by 3-10 points.