---
title: 'QDMR: Structured Question Decomposition'
url: https://www.emergentmind.com/topics/question-decomposition-meaning-representation-qdmr
type: topic
---

# QDMR: Structured Question Decomposition

Question Decomposition Meaning Representation (QDMR) is a structured formalism for compositional natural-language question understanding and reasoning, enabling the decomposition of complex questions into interpretable sequences of atomic reasoning steps. Each QDMR instance provides a sequence of explicit operations—such as select, filter, project, group, and aggregate—whose compositional execution yields the final answer. QDMR serves as an intermediary semantic layer between open-domain question answering and both formal (e.g., SQL) and semi-formal (e.g., chain-of-thought) reasoning systems, supporting robust training, evaluation, and interpretability of multi-step reasoning models [2104.08647][2305.14901][2205.12496][2112.06311].

## 1. Formal Structure and Semantics of QDMR

A QDMR is defined as an ordered sequence of reasoning steps for a question $q$, where each step is either a basic operation over the text or a transformation grounded in the answer to a prior step. Formally, given $q = \langle q_1, \ldots, q_n \rangle$ (the tokenized input question), a QDMR decomposition is
$$
S = \langle q;\;s^1, \ldots, s^m \rangle,
$$
where each $s^i$ is a short, human-readable "atomic question," each with an operator $o^i$ from a finite set $O = \{\texttt{SELECT}, \texttt{FILTER}, \texttt{PROJECT}, \ldots\}$, operator-specific properties $\rho^i \in \text{PROP}(o^i)$, and arguments $A^i: A(o^i) \to \{\text{token-spans from } q \text{ or prior steps}\}$ [2104.08647].

Semantically, QDMR decompositions encode directed acyclic computation graphs: each reasoning step's output can be referenced via a variable (e.g., "#2"), forming explicit data flow and dependency structure [2205.12496][2112.06311]. The compositionality of QDMR is foundational for constraining QA models to exhibit interpretable, stepwise reasoning.

## 2. QDMR Representations and Conversion to Programs

QDMR steps are typically linearized as tuples $(o^i, \rho^i, A^i)$, but can equivalently be represented as dependency graphs $G=(V,E)$ over tokens, where each edge encodes logical or argument relations defined by QDMR operators and step structure [2104.08647]. QDMRs can also be programmatically mapped to "typed programs" $\langle f_1, ..., f_n \rangle$ of primitive functions, each with explicit input/output types such as \texttt{List[Entity]}, \texttt{Int}, or \texttt{Bool} [2205.12496]. For example:

- QDMR step: "project yard_line of #1 $\rightarrow$ #2"
- Program: \texttt{#2 = project(input=#1, field="yard_line")}

Typed program conversions enable direct grounding of QDMRs into executable logical forms for downstream applications, such as synthesis of SQL queries or numerical computation pipelines [2112.06311][2205.12496].

## 3. Modeling Approaches: Parsing and Supervision

Two dominant modeling paradigms exist for QDMR parsing:

1. **Sequence-to-Sequence (Seq2seq) Models**: Standard transformer encoder-decoder architectures (e.g., T5, BART, CopyNet–BERT) linearize QDMRs as token sequences and generate decompositions autoregressively. Gold QDMR sequences are used for direct supervision; copy mechanisms are common for referencing question spans [2104.08647][2305.14901].

2. **Graph-Based Non-Autoregressive Parsers**: Dependency-graph parsers, following a Biaffine style, treat tokens as graph nodes, predicting labeled edges that encode argument/operator relations. All edge predictions are made simultaneously, enabling a single forward pass without stepwise decoding. This approach yields $\approx16\times$ inference speed-up compared to seq2seq, moderately improved sample complexity, and better robustness to domain shift, at a small loss of maximum accuracy [2104.08647].

Auxiliary supervision—via jointly training seq2seq models with graph-based losses using Relation-Aware Transformers (Latent-RAT)—can further improve generalization and robustness, especially for long or compositional questions [2104.08647].

## 4. Applications in Multistep Question Answering and Pretraining

QDMR enables explicitly compositional modeling in multistep question answering (QA), supporting:

- **Chain-of-Questions (CoQ) Training**: QDMR guides language models to generate and answer sub-questions sequentially, treating sub-answers as latent variables. Training leverages a hybrid of Hard-Expectation Maximization (Hard-EM) for strong early signal and Memory Augmented Policy Optimization (MAPO) for late-stage convergence. CoQ demonstrates marked robustness gains over conventional neuro-symbolic and large language model methods on adversarial and contrast datasets (e.g., +16.8 to +24.3 F1 over GPT-3.5 on DROP/HOTPOTQA adversarial sets) [2305.14901].

- **Synthetic Context Generation**: Mapping QDMR decompositions to typed programs allows the systematic creation of "hard" synthetic contexts (TeaBReaC dataset), designed to enforce non-trivial, stepwise reasoning by the model while preventing shortcut exploitation. Pretraining language models on TeaBReaC yields substantial F1 improvements (+4–13, up to +20 on complex questions) and higher robustness on multi-step QA tasks [2205.12496].

- **Text-to-SQL Pipeline**: QDMR enables a weakly supervised approach to text-to-SQL parsing, where QDMRs (manual or predicted) serve as intermediate representations. SQL queries are synthesized algorithmically from (question, QDMR, answer) triples using execution-guided search and repair heuristics, achieving 91–97% of fully supervised SQL accuracy and 86–93% with only predicted QDMRs, thereby obviating SQL annotation [2112.06311].

## 5. Empirical Evaluation and Comparative Results

Empirical analyses highlight QDMR's strengths as both a modeling target and as auxiliary guidance for multi-step reasoning:

- **Parsing Accuracy**: On the BREAK dataset, state-of-the-art seq2seq (BART) achieves LF-EM of 0.496, CopyNet+BERT 0.470, and Biaffine graph parser 0.440, with a 16× inference speed-up for Biaffine over CopyNet+BERT [2104.08647].

- **Domain Generalization and Sample Complexity**: Non-autoregressive graph approaches and Latent-RAT (auxiliary graph supervision) exhibit smaller performance drops under domain shift (e.g., –43.1% vs. –50% for standard seq2seq), and require less data to reach a fixed performance threshold (notably +3–5 points LF-EM at 1–10% data) [2104.08647].

- **Compositional QA and Robustness**: Chain-of-Questions with QDMR supervision yields +9.0 F1 over strong neuro-symbolic methods and +24.3 F1 over GPT-3.5 on complex adversarial QA sets. These methods maintain performance under adversarial distributional shifts, demonstrating QDMR's capacity to encode and enforce genuine multi-step reasoning [2305.14901][2205.12496].

## 6. Interpretability, Debugging, and Downstream Impact

QDMR's explicit compositional structure enables fine-grained interpretability and debugging:

- The dependency-graph and stepwise forms provide token- or span-level explanation for each stage of reasoning, elucidating the execution role of every question part [2104.08647].

- Intermediate representations can be visualized, traced, or mapped to formal languages (e.g., SQL, typed programs), facilitating error analysis and annotation refinement [2112.06311][2205.12496].

- QDMR-guided pipelines serve as bridges for bootstrapping weak supervision in domains lacking formal annotations, and as scaffolding for curriculum learning and data synthesis [2112.06311][2205.12496].

## 7. Datasets and Empirical Resources

QDMR-based benchmarks and resources include:

| Name         | Description                                 | Reference          |
|--------------|---------------------------------------------|--------------------|
| BREAK        | Crowd-annotated QDMR decompositions         | [2104.08647]       |
| TeaBReaC     | Synthetic QDMR-guided multi-step QA         | [2205.12496]       |
| D_QDMR(+/bronze) | Human and model-predicted QDMRs         | [2305.14901]       |

QDMR annotations cover diverse QA domains: DROP (numerical), ComplexWebQuestions (web), HotpotQA (multi-hop), SPIDER (text-to-SQL), ComQA (factoid), and ATIS (spoken). TeaBReaC contains 525K synthetic multistep instances with 900+ reasoning patterns, supporting both pretraining and robust evaluation.

---

In sum, QDMR provides a rigorous, adaptable meaning representation for compositional question answering. It supports interpretable, data-efficient, and robust multi-step reasoning across neural and symbolic paradigms, and underpins principled approaches to program synthesis, data augmentation, and domain adaptation in complex QA tasks [2104.08647][2305.14901][2205.12496][2112.06311].

Source: https://www.emergentmind.com/topics/question-decomposition-meaning-representation-qdmr